|
1
|
Qiu F, Zhang R, Schwenkreis F, Legerlotz K. Predicting rheumatoid arthritis in the middle-aged and older population using patient-reported outcomes: insights from the SHARE cohort. Int J Med Inform 2025; 200:105915. [PMID: 40209390 DOI: 10.1016/j.ijmedinf.2025.105915] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2025] [Revised: 04/04/2025] [Accepted: 04/07/2025] [Indexed: 04/12/2025]
Abstract
BACKGROUND In light of global population aging and the increasing prevalence of Rheumatoid Arthritis (RA) with age, strategies are needed to address this public health challenge. Machine learning (ML) may play a vital role in early identification of RA, allowing an early start of treatment, thereby reducing costs. This study aims first to identify potential variables related to RA, and second to explore and evaluate the potential of ML to identify RA patients in people over 50 years. METHOD We developed ML predictive models (lightGBM, logistic regression, k nearest neighbor, naive Bayes, random forrest, and XGBoost) using patient-reported outcomes collected from the SHARE database (7th and 9th wave). RESULTS Difficulties in daily life such as stooping and pulling are risk factors for RA. Lifestyle activities participation is negatively associated with RA. ML models performed differently with the lightGBM model achieving the highest AUC (0.748, 95 % CI: 0.739-0.758), and logistic regression and lightGBM showing the highest accuracy at 0.902. The sensitivity of naive Bayes was highest at 0.442. Significant differences were observed in the Hosmer-Lemeshow test (P < 0.05). CONCLUSION The predictive models based on patient-reported outcome measures achieved fair performance with limited potential to early identify RA patients. Lifestyle activities and difficulties in daily life were associated with risk of RA and should be considered in anamnesis.
Collapse
Affiliation(s)
- Fanji Qiu
- Movement Biomechanics, Institute of Sport Sciences, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany.
| | - Rongrong Zhang
- School of Control and Computer Engineering, North China Electric Power University, 102206 Beijing, China
| | - Friedemann Schwenkreis
- Department of Business Information Systems, Baden-Wuerttemberg Cooperative State University Stuttgart, Paulinenstr. 50, 70178 Stuttgart, Germany
| | - Kirsten Legerlotz
- Movement Biomechanics, Institute of Sport Sciences, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany; Department of Movement and Training Sciences, Institute of Sport Sciences, University of Wuppertal, Gauss street 20, 42119 Wuppertal, Germany
| |
Collapse
|
|
2
|
Panagoulias DP, Tsoureli-Nikita E, Virvou M, Tsihrintzis GA. Dermacen analytica: A novel methodology integrating multi-modal large language models with machine learning in dermatology. Int J Med Inform 2025; 199:105898. [PMID: 40153891 DOI: 10.1016/j.ijmedinf.2025.105898] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2024] [Revised: 03/10/2025] [Accepted: 03/21/2025] [Indexed: 04/01/2025]
Abstract
OBJECTIVE To design, implement, evaluate, and quantify a novel and adaptable Artificial Intelligence-empowered methodology aimed at supporting a dermatologist's workflow in assessing and diagnosing skin conditions, leveraging AI's deep image analytic power and reasoning. Skin presents diverse conditions that no single AI solution can comprehensively address, suggesting that mimicking a medical professional's diagnostic process and creating strategic AI interventions may enhance decision-making. PATIENTS AND METHODS We employ large language, transformer-based vision models for image analysis, sophisticated machine learning tools for guideline-based segmentation, and measuring tasks in our system. As no single technology is sufficient on its own for efficient use by dermatologists, we apply a sequential logic with agency to improve outcomes. RESULTS Using natural language processing methods and incorporating human expert evaluation, our system achieved a weighted accuracy of 87% on the dataset used, demonstrating its reasoning and diagnostic capabilities. CONCLUSIONS This study serves as a proof of concept for the application of AI in dermatology, highlighting its potential to enhance the patient journey for which we approximate the value of such interventions in healthcare using graph theory with an associated cost-optimization objective function.
Collapse
Affiliation(s)
| | | | - Maria Virvou
- Department of Informatics, University of Piraeus, Piraeus 185 34, Greece.
| | | |
Collapse
|
|
3
|
Georgakopoulou VE, Spandidos DA, Corlateanu A. Diagnostic tools in respiratory medicine (Review). Biomed Rep 2025; 23:112. [PMID: 40420977 PMCID: PMC12105097 DOI: 10.3892/br.2025.1990] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2025] [Accepted: 04/30/2025] [Indexed: 05/28/2025] Open
Abstract
Recent advancements in diagnostic technologies have significantly transformed the landscape of respiratory medicine, aiming for early detection, improved specificity and personalized therapeutic strategies. Innovations in imaging such as multi-slice computed tomography (CT) scanners, high-resolution CT and magnetic resonance imaging (MRI) have revolutionized our ability to visualize and assess the structural and functional aspects of the respiratory system. These techniques are complemented by breakthroughs in molecular biology that have identified specific biomarkers and genetic determinants of respiratory diseases, enabling targeted diagnostic approaches. Additionally, functional tests including spirometry and exercise testing continue to provide valuable insights into pulmonary function and capacity. The integration of artificial intelligence is poised to further refine these diagnostic tools, enhancing their accuracy and efficiency. The present narrative review explores these developments and their impact on the management and outcomes of respiratory conditions, underscoring the ongoing shift towards more precise and less invasive diagnostic modalities in respiratory medicine.
Collapse
Affiliation(s)
| | - Demetrios A. Spandidos
- Laboratory of Clinical Virology, School of Medicine, University of Crete, 71003 Heraklion, Greece
| | - Alexandru Corlateanu
- Department of Pulmonology and Allergology, State University of Medicine and Pharmacy ‘Nicolae Testemitanu’, MD-2004 Chisinau, Moldova
| |
Collapse
|
|
4
|
Thakur RK, Aggarwal K, Sood N, Kumar A, Joshi S, Jindal P, Maurya R, Patel P, Kurmi BD. Harnessing advances in mechanisms, detection, and strategies to combat antimicrobial resistance. THE SCIENCE OF THE TOTAL ENVIRONMENT 2025; 982:179641. [PMID: 40373688 DOI: 10.1016/j.scitotenv.2025.179641] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/19/2025] [Revised: 04/28/2025] [Accepted: 05/08/2025] [Indexed: 05/17/2025]
Abstract
Antimicrobial resistance (AMR) is a growing global health crisis, threatening the effectiveness of antibiotics and other antimicrobial agents, leading to increased morbidity, mortality, and economic burdens. This review article provides a comprehensive analysis of AMR, beginning with a timeline of antibiotics discovery and the year of first observed resistance. Main mechanisms of AMR in bacteria, fungi, viruses, and parasites are summarized, and the main mechanisms of bacteria are given in detail. Additionally, we discussed in detail methods for detecting AMR, including phenotypic, genotypic, and advanced methods, which are crucial for identifying and monitoring AMR. In addressing AMR mitigation, we explore innovative interventions such as CRISPR-Cas systems, nanotechnology, antibody therapy, artificial intelligence (AI), and the One Health approach. Moreover, we discussed both finished and ongoing clinical trials for AMR. This review emphasizes the urgent need for global action and highlights promising technologies that could shape the future of AMR surveillance and treatment. By integrating interdisciplinary research and emerging clinical insights, this study aims to guide individuals toward impactful solutions in the battle against AMR.
Collapse
Affiliation(s)
- Ritik Kumar Thakur
- Department of Pharmaceutics, ISF College of Pharmacy, GT Road, Moga 142001, Punjab, India
| | - Kaushal Aggarwal
- Department of Pharmaceutics, ISF College of Pharmacy, GT Road, Moga 142001, Punjab, India
| | - Nayan Sood
- Department of Pharmaceutics, ISF College of Pharmacy, GT Road, Moga 142001, Punjab, India
| | - Aman Kumar
- Department of Pharmaceutics, ISF College of Pharmacy, GT Road, Moga 142001, Punjab, India
| | - Sachin Joshi
- Department of Pharmaceutical Quality Assurance, ISF College of Pharmacy, GT Road, Moga 142001, Punjab, India
| | - Priya Jindal
- Department of Pharmaceutical Quality Assurance, ISF College of Pharmacy, GT Road, Moga 142001, Punjab, India
| | - Rashmi Maurya
- Department of Pharmaceutics, ISF College of Pharmacy, GT Road, Moga 142001, Punjab, India
| | - Preeti Patel
- Department of Pharmaceutical Chemistry, ISF College of Pharmacy, GT Road, Moga 142001, Punjab, India.
| | - Balak Das Kurmi
- Department of Pharmaceutics, ISF College of Pharmacy, GT Road, Moga 142001, Punjab, India.
| |
Collapse
|
|
5
|
Lulic I, Lulic D, Pavicic Saric J, Bacak Kocman I, Rogic D. Personalized translational medicine: Investigating YKL-40 as early biomarker for clinical risk stratification in hepatocellular carcinoma recurrence post-liver transplantation. World J Transplant 2025; 15:103036. [DOI: 10.5500/wjt.v15.i2.103036] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/05/2024] [Revised: 01/05/2025] [Accepted: 01/14/2025] [Indexed: 02/21/2025] Open
Abstract
Hepatocellular carcinoma (HCC) recurrence after liver transplantation (LT) presents a significant challenge, with recurrence rates ranging from 8% to 20% globally. Current biomarkers, such as alpha-fetoprotein (AFP) and des-gamma-carboxy prothrombin (DCP), lack specificity, limiting their utility in risk stratification. YKL-40, a glycoprotein involved in extracellular matrix remodeling, hepatic stellate cell activation, and immune modulation, has emerged as a promising biomarker for post-LT surveillance. Elevated serum levels of YKL-40 are associated with advanced liver disease, tumor progression, and poorer post-LT outcomes, highlighting its potential to address gaps in early detection and personalized management of HCC recurrence. This manuscript synthesizes clinical and mechanistic evidence to evaluate YKL-40’s predictive utility in post-LT care. While preliminary findings demonstrate its specificity for liver-related pathologies, challenges remain, including assay standardization, lack of prospective validation, and the need to distinguish between malignant and non-malignant causes of elevated levels. Integrating YKL-40 into multi-biomarker panels with AFP and DCP could enhance predictive accuracy and enable tailored therapeutic strategies. Future research should focus on multicenter studies to validate YKL-40’s clinical utility, address confounding factors like graft rejection and systemic inflammation, and explore its role in predictive models driven by emerging technologies such as artificial intelligence. YKL-40 holds transformative potential in reshaping post-LT care through precision medicine, providing a pathway for better outcomes and improved management of high-risk LT recipients.
Collapse
Affiliation(s)
- Ileana Lulic
- Department of Anesthesiology, Intensive Care and Pain Medicine, Clinical Hospital Merkur, Zagreb 10000, Croatia
| | - Dinka Lulic
- Department of Anesthesiology, Intensive Care and Pain Medicine, Clinical Hospital Merkur, Zagreb 10000, Croatia
- Immediate Medical Care Unit, Saint James Hospital, Sliema SLM-1030, Malta
| | - Jadranka Pavicic Saric
- Department of Anesthesiology, Intensive Care and Pain Medicine, Clinical Hospital Merkur, Zagreb 10000, Croatia
| | - Iva Bacak Kocman
- Department of Anesthesiology, Intensive Care and Pain Medicine, Clinical Hospital Merkur, Zagreb 10000, Croatia
| | - Dunja Rogic
- Department of Laboratory Diagnostics, University Hospital Centre Zagreb, Zagreb 10000, Croatia
- Department of Medical Biochemistry and Hematology, Faculty of Pharmacy and Biochemistry, Zagreb 10000, Croatia
| |
Collapse
|
|
6
|
Pillay TS, Khan AI, Yenice S. Artificial intelligence (AI) in point-of-care testing. Clin Chim Acta 2025; 574:120341. [PMID: 40324611 DOI: 10.1016/j.cca.2025.120341] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2025] [Revised: 04/28/2025] [Accepted: 04/28/2025] [Indexed: 05/07/2025]
Abstract
The integration of artificial intelligence (AI) into point-of-care testing (POCT) represents a transformative leap in modern healthcare, addressing critical challenges in diagnostic accuracy, workflow efficiency, and equitable access. While POCT has revolutionized decentralized care through rapid results, its potential is hindered by variability in accuracy, integration hurdles, and resource constraints. AI technologies-encompassing machine learning, deep learning, and natural language processing-offer robust solutions: convolutional neural networks improve malaria detection in sub-Saharan Africa to 95 % sensitivity, while predictive analytics reduce device downtime by 20 % in resource-limited settings. AI-driven decision support systems curtail antibiotic misuse by 40 % through real-time data synthesis, and portable AI devices enable anaemia screening in rural India with 94 % accuracy, slashing diagnostic delays from weeks to hours. Despite these advancements, challenges persist, including data privacy risks, algorithmic opacity, and infrastructural gaps in low- and middle-income countries. Explainable AI frameworks and blockchain encryption are critical to building clinician trust and ensuring regulatory compliance. Future directions emphasize the convergence of AI with Internet of Things (IoT) and blockchain for predictive diagnostics, as demonstrated by AI-IoT systems forecasting dengue outbreaks 14 days in advance. Personalized medicine, powered by genomic and wearable data integration, further underscores AI potential to tailor therapies, reducing cardiovascular events by 25 %. Realizing this vision demands interdisciplinary collaboration, ethical governance, and equitable implementation to bridge global health disparities. By harmonizing innovation with accessibility, AI-enhanced POCT emerges as a cornerstone of proactive, patient-centered healthcare, poised to democratize diagnostics and drive sustainable health equity worldwide.
Collapse
Affiliation(s)
- Tahir S Pillay
- Department of Chemical Pathology, Faculty of Health Sciences and National Health Laboratory Service, Tshwane Academic Division, University of Pretoria, Pretoria, South Africa; Division of Chemical Pathology, Department of Pathology, University of Cape Town, Cape Town, South Africa.
| | - Adil I Khan
- Dept. of Pathology & Laboratory Medicine, Lewis Katz School of Medicine, Temple University, Philadelphia, PA, USA
| | - Sedef Yenice
- Group Florence Nightingale Hospitals, Istanbul, Türkiye
| |
Collapse
|
|
7
|
Stage MA, Creamer MM, Ruben MA. "Having providers who are trained and have empathy is life-saving": Improving primary care communication through thematic analysis with ChatGPT and human expertise. PEC INNOVATION 2025; 6:100371. [PMID: 39866208 PMCID: PMC11758403 DOI: 10.1016/j.pecinn.2024.100371] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/23/2024] [Revised: 11/29/2024] [Accepted: 12/23/2024] [Indexed: 01/28/2025]
Abstract
In the rapidly evolving field of healthcare research, Artificial Intelligence (AI) and conversational models like ChatGPT (Conversational Generative Pre-trained Transformer) offer promising tools for data analysis. The aim of this study was to: 1) apply ChatGPT methodology alongside human coding to analyze qualitative health services feedback, and 2) examine healthcare experiences among lesbian, gay, bisexual, transgender, and queer (LGBTQ+) patients (N = 41) to inform future intervention. The hybrid approach facilitated the identification of themes related to affirming care practices, provider education, communicative challenges and successes, and environmental cues. While ChatGPT accelerated the coding process, human oversight remained crucial for ensuring data integrity and context accuracy. This hybrid method promises significant improvements in analyzing patient feedback, providing actionable insights that could enhance patient-provider interactions and care for diverse populations. Innovation: This study is the first to combine ChatGPT with human coding for rapid thematic analysis of LGBTQ+ patient primary care experiences.
Collapse
Affiliation(s)
- Michelle A. Stage
- University of Rhode Island, 142 Flagg Road, Chafee Hall, Department of Psychology, Kingston, RI 02881, USA
| | - Mackenzie M. Creamer
- Northeastern University, 440 Huntington Ave, West Village H, Boston, MA 02115, USA
| | - Mollie A. Ruben
- University of Rhode Island, 142 Flagg Road, Chafee Hall, Department of Psychology, Kingston, RI 02881, USA
| |
Collapse
|
|
8
|
Buchtele N, Staudinger T. [Acute respiratory distress syndrome-quo vadis : Innovative and individualized treatment approaches]. Med Klin Intensivmed Notfmed 2025; 120:379-388. [PMID: 40261329 DOI: 10.1007/s00063-025-01273-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2025] [Accepted: 03/19/2025] [Indexed: 04/24/2025]
Abstract
Acute respiratory distress syndrome (ARDS) is a heterogeneous clinical syndrome characterized by variable pathophysiology and different therapeutic approaches. Recent guidelines emphasize the importance of prone positioning and venovenous extracorporeal membrane oxygenation (VV-ECMO) for the most severe cases, while routine recruitment maneuvers and extracorporeal CO2-removal techniques are no longer recommended. To further advance the personalization of ARDS therapy, the identification of ARDS phenotypes using latent class analysis offers promising approaches for individualized treatment. Additionally, adaptive platform trials and artificial intelligence (AI)-driven decision-support systems may optimize future ARDS management. The future of ARDS treatment is becoming increasingly individualized, based on improved patient stratification, innovative study designs, and the targeted use of modern technologies. This article summarizes recent developments in ARDS therapy, particularly regarding personalized treatment strategies, new study designs, and the application of artificial intelligence.
Collapse
Affiliation(s)
- Nina Buchtele
- Universitätsklinik für Innere Medizin I, Intensivstation 13i2, Medizinische Universität Wien, Währinger Gürtel 18-20, 1090, Wien, Österreich.
| | - Thomas Staudinger
- Universitätsklinik für Innere Medizin I, Intensivstation 13i2, Medizinische Universität Wien, Währinger Gürtel 18-20, 1090, Wien, Österreich
| |
Collapse
|
|
9
|
Balakrishnan S, Ranganathan P, Prabhudesai KS, Vijay R, Gawali VP, Kareenhalli V. MASLD Risk Score (MRS) and Random Forest model (RF Model): Novel tools for screening and severity assessment of MASLD. Comput Biol Med 2025; 192:110314. [PMID: 40328026 DOI: 10.1016/j.compbiomed.2025.110314] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2024] [Revised: 04/21/2025] [Accepted: 04/30/2025] [Indexed: 05/08/2025]
Abstract
BACKGROUND AND AIMS Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD) spans from simple steatosis to progressive forms like non-alcoholic steatohepatitis (NASH), fibrosis, and cirrhosis, making early diagnosis and grading crucial. This study aimed to develop and validate predictive models for diagnosing and assessing MASLD severity using routinely available biomarkers from both public and clinical datasets. APPROACH & RESULTS We developed a novel MASLD Risk Score (MRS) using data from the CDC NHANES (2000-2020) and validated it in a clinically profiled Indian cohort. Unlike existing indices, the predictors were derived through data-driven feature selection from large dataset, ensuring statistical robustness. It integrates novel (Uric Acid, HOMA-IR) and established (liver enzymes, triglycerides, waist circumference, BMI) biomarkers to improve metabolic profiling and predictive accuracy. The MRS also uniquely enables grading of MASLD severity, addressing a key limitation of previous models. The MRS achieved AUROCs of 0.91 (public) and 0.85 (clinical) with accuracies of 94 % and 82 %, respectively. A Random Forest (RF) model built on the same features provided AUROCs of 0.87 (public) and 0.94 (clinical), with accuracies of 83 % and 82 %. MRS parameters were optimized using a diverse population, improving generalizability across demographics. Both models showed strong correlation with ultrasonography results and outperformed existing indices. CONCLUSIONS The MRS offers a novel, interpretable, and cost-effective solution for MASLD screening. Its development from a large, demographically diverse population and incorporation of varied biomarkers supports generalizability. While results are promising, external validation in multi-center clinical settings is needed to confirm broad utility.
Collapse
Affiliation(s)
| | | | | | - Ria Vijay
- Bhaktivedanta Hospital and Research Institute, India
| | | | - Venkatesh Kareenhalli
- MetFlux Research Private Limited, India; Department of Chemical Engineering, Indian Institute of Technology Bombay, Mumbai, Maharashtra, India.
| |
Collapse
|
|
10
|
Aravazhi PS, Gunasekaran P, Benjamin NZY, Thai A, Chandrasekar KK, Kolanu ND, Prajjwal P, Tekuru Y, Brito LV, Inban P. The integration of artificial intelligence into clinical medicine: Trends, challenges, and future directions. Dis Mon 2025; 71:101882. [PMID: 40140300 DOI: 10.1016/j.disamonth.2025.101882] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/28/2025]
Abstract
BACKGROUND AND OBJECTIVES AI has emerged as a transformative force in clinical medicine, changing the diagnosis, treatment, and management of patients. Tools have been derived for working with ML, DL, and NLP algorithms to analyze large complex medical datasets with unprecedented accuracy and speed, thereby improving diagnostic precision, treatment personalization, and patient care outcomes. For example, CNNs have dramatically improved the accuracy of medical imaging diagnoses, and NLP algorithms have greatly helped extract insights from unstructured data, including EHRs. However, there are still numerous challenges that face AI integration into clinical workflows, including data privacy, algorithmic bias, ethical dilemmas, and problems with the interpretability of "black-box" AI models. These barriers have thus far prevented the widespread application of AI in health care, and its possible trends, obstacles, and future implications are necessary to be systematically explored. The purpose of this paper is, therefore, to assess the current trends in AI applications in clinical medicine, identify those obstacles that are hindering adoption, and identify possible future directions. This research hopes to synthesize evidence from other peer-reviewed articles to provide a more comprehensive understanding of the role that AI plays to advance clinical practices, improve patient outcomes, or enhance decision-making. METHODS A systematic review was done according to the PRISMA guidelines to explore the integration of Artificial Intelligence in clinical medicine, including trends, challenges, and future directions. PubMed, Cochrane Library, Web of Science, and Scopus databases were searched for peer-reviewed articles from 2014 to 2024 with keywords such as "Artificial Intelligence in Medicine," "AI in Clinical Practice," "Machine Learning in Healthcare," and "Ethical Implications of AI in Medicine." Studies focusing on AI application in diagnostics, treatment planning, and patient care reporting measurable clinical outcomes were included. Non-clinical AI applications and articles published before 2014 were excluded. Selected studies were screened for relevance, and then their quality was critically appraised to synthesize data reliably and rigorously. RESULTS This systematic review includes the findings of 8 studies that pointed out the transformational role of AI in clinical medicine. AI tools, such as CNNs, had diagnostic accuracy more than the traditional methods, particularly in radiology and pathology. Predictive models efficiently supported risk stratification, early disease detection, and personalized medicine. Despite these improvements, significant hurdles, including data privacy, algorithmic bias, and resistance from clinicians regarding the "black-box" nature of AI, had yet to be surmounted. XAI has emerged as an attractive solution that offers the promise to enhance interpretability and trust. As a whole, AI appeared promising in enhancing diagnostics, treatment personalization, and clinical workflows by dealing with systemic inefficiencies. CONCLUSION The transformation potential of AI in clinical medicine can transform diagnostics, treatment strategies, and efficiency. Overcoming obstacles such as concerns about data privacy, the danger of algorithmic bias, and difficulties with interpretability may pave the way for broader use and facilitate improvement in patient outcomes while transforming clinical workflows to bring sustainability into healthcare delivery.
Collapse
Affiliation(s)
| | | | | | - Andy Thai
- Internal Medicine, Alameda Health System, Highland Hospital, Oakland, USA
| | | | | | | | - Yogesh Tekuru
- RVM Institute of Medical Sciences and Research Center, Laxmakkapally, India
| | | | - Pugazhendi Inban
- Internal Medicine, St. Mary's General Hospital and Saint Clare's Health, NY, USA.
| |
Collapse
|
|
11
|
Xiao Y, Benedict S, Cui Y, Glide-Hurst C, Graves S, Jia X, Kry SF, Li H, Lin L, Matuszak M, Newpower M, Paganetti H, Qi XS, Roncali E, Rong Y, Sgouros G, Simone CB, Sunderland JJ, Taylor PA, Tchelebi L, Weldon M, Zou JW, Wuthrick EJ, Machtay M, Le QT, Buchsbaum JC. Embracing the Future of Clinical Trials in Radiation Therapy: An NRG Oncology CIRO Technology Retreat Whitepaper on Pioneering Technologies and AI-Driven Solutions. Int J Radiat Oncol Biol Phys 2025; 122:443-457. [PMID: 39848295 DOI: 10.1016/j.ijrobp.2025.01.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2024] [Revised: 12/20/2024] [Accepted: 01/12/2025] [Indexed: 01/25/2025]
Abstract
This white paper examines the potential of pioneering technologies and artificial intelligence-driven solutions in advancing clinical trials involving radiation therapy. As the field of radiation therapy evolves, the integration of cutting-edge approaches such as radiopharmaceutical dosimetry, FLASH radiation therapy, image guided radiation therapy, and artificial intelligence promises to improve treatment planning, patient care, and outcomes. Additionally, recent advancements in quantum science, linear energy transfer/relative biological effect, and the combination of radiation therapy and immunotherapy create new avenues for innovation in clinical trials. The paper aims to provide an overview of these emerging technologies and discuss their challenges and opportunities in shaping the future of radiation oncology clinical trials. By synthesizing knowledge from experts across various disciplines, this white paper aims to present a foundation for the successful integration of these innovations into radiation therapy research and practice, ultimately enhancing patient outcomes and revolutionizing cancer care.
Collapse
Affiliation(s)
- Ying Xiao
- Department of Radiation Oncology, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Stanley Benedict
- Department of Radiation Oncology, University of California at Davis, Comprehensive Cancer Center, Davis, California
| | - Yunfeng Cui
- Department of Radiation Oncology, Duke University, Durham, North Carolina
| | - Carri Glide-Hurst
- Department of Human Oncology, University of Wisconsin, Madison, Wisconsin
| | - Stephen Graves
- Department of Radiology, Division of Nuclear Medicine, University of Iowa, Iowa City, Iowa
| | - Xun Jia
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Stephen F Kry
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Heng Li
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Liyong Lin
- Department of Radiation Oncology, Emory University, Atlanta, Georgia
| | - Martha Matuszak
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Mark Newpower
- Department of Radiation Oncology, University of Oklahoma Health Sciences Center, Oklahoma City, Oklahoma
| | - Harald Paganetti
- Department of Radiation Oncology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - X Sharon Qi
- Department of Radiation Oncology, University of California Los Angeles, Los Angeles, California
| | - Emilie Roncali
- Department of Radiology, University of California at Davis, Davis, California
| | - Yi Rong
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota
| | - George Sgouros
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | | | - John J Sunderland
- Department of Radiology, Division of Nuclear Medicine, University of Iowa, Iowa City, Iowa
| | - Paige A Taylor
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Leila Tchelebi
- Department of Radiation Oncology, Northwell Health, Mt. Kisco, New York
| | - Michael Weldon
- Department of Radiation Oncology, The Ohio State University Medical Center, Columbus, Ohio
| | - Jennifer W Zou
- Department of Radiation Oncology, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Evan J Wuthrick
- Department of Radiation Oncology, Moffitt Cancer Center, Tampa, Florida
| | - Mitchell Machtay
- Department of Radiation Oncology, Penn State Health Milton S. Hershey Medical Center, Hershey, Pennsylvania
| | - Quynh-Thu Le
- Department of Radiation Oncology, Stanford University, Stanford, California
| | - Jeffrey C Buchsbaum
- Division of Cancer Treatment and Diagnosis, Radiation Research Program, National Cancer Institute, Bethesda, Maryland.
| |
Collapse
|
|
12
|
Darwish BA, Rehman SU, Sadek I, Salem NM, Kareem G, Mahmoud LN. From lab to real-life: A three-stage validation of wearable technology for stress monitoring. MethodsX 2025; 14:103205. [PMID: 39996105 PMCID: PMC11848792 DOI: 10.1016/j.mex.2025.103205] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2024] [Accepted: 02/04/2025] [Indexed: 02/26/2025] Open
Abstract
Stress negatively impacts health, contributing to hypertension, cardiovascular diseases, and immune dysfunction. While conventional diagnostic methods, such as self-reported questionnaires and basic physiological measurements, often lack the objectivity and precision needed for effective stress management, wearable devices present a promising avenue for early stress detection and management. This study conducts a three-stage validation of wearable technology for stress monitoring, transitioning from controlled experimental data to real-life scenarios. Using the controlled WESAD dataset, binary and five-class classification models were developed, achieving maximum accuracies of 99.78 %±0.15 % and 99.61 %±0.32 %, respectively. Electrocardiogram (ECG), Electrodermal Activity (EDA), and Respiration (RESP) were identified as reliable stress biomarkers. Validation was extended to the SWEET dataset, representing real-life data, to confirm generalizability and practical applicability. Furthermore, commercially available wearables supporting these modalities were reviewed, providing recommendations for optimal configurations in dynamic, real-world conditions. These findings demonstrate the potential of multimodal wearable devices to bridge the gap between controlled studies and practical applications, advancing early stress detection systems and personalized stress management strategies.•Stress detection methods were validated using multimodal wearable data in controlled (WESAD) and real-life (SWEET) datasets.•Commercial wearable technologies were reviewed, offering insights into their applicability for practical stress monitoring.
Collapse
Affiliation(s)
- Basil A. Darwish
- Biomedical Engineering Department, Faculty of Engineering, Helwan University, Egypt
- Computer Science, Artificial Intelligence Programme, University of Hertfordshire hosted by Global Academic Foundation, Egypt
| | - Shafiq Ul Rehman
- College of Information Technology, Kingdom University, Kingdom of Bahrain
| | - Ibrahim Sadek
- Biomedical Engineering Department, Faculty of Engineering, Helwan University, Egypt
| | - Nancy M. Salem
- Biomedical Engineering Department, Faculty of Engineering, Helwan University, Egypt
| | - Ghada Kareem
- Department of Biomedical Engineering, Higher Technological Institute, 10th Ramadan City, Egypt
| | - Lamees N. Mahmoud
- Biomedical Engineering Department, Faculty of Engineering, Helwan University, Egypt
| |
Collapse
|
|
13
|
Orakwue CJ, Tajrishi FZ, Gistand CM, Feng H, Ferdinand KC. Combating cardiovascular disease disparities: The potential role of artificial intelligence. Am J Prev Cardiol 2025; 22:100954. [PMID: 40161231 PMCID: PMC11951981 DOI: 10.1016/j.ajpc.2025.100954] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2024] [Revised: 02/20/2025] [Accepted: 03/07/2025] [Indexed: 04/02/2025] Open
Affiliation(s)
| | - Farbod Zahedi Tajrishi
- Department of Internal Medicine, Tulane University School of Medicine, New Orleans, LA, USA
| | - Constance M. Gistand
- Department of Internal Medicine, Tulane University School of Medicine, New Orleans, LA, USA
| | - Han Feng
- Tulane Research and Innovation for Arrhythmia Discoveries - TRIAD Center, Tulane University School of Medicine, New Orleans, LA, USA
| | - Keith C. Ferdinand
- Section of Cardiology, Tulane University School of Medicine, New Orleans, LA, USA
| |
Collapse
|
|
14
|
Luo L, Wang M, Liu Y, Li J, Bu F, Yuan H, Tang R, Liu C, He G. Sequencing and characterizing human mitochondrial genomes in the biobank-based genomic research paradigm. SCIENCE CHINA. LIFE SCIENCES 2025; 68:1610-1625. [PMID: 39843848 DOI: 10.1007/s11427-024-2736-7] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/25/2024] [Accepted: 09/18/2024] [Indexed: 01/24/2025]
Abstract
Human mitochondrial DNA (mtDNA) harbors essential mutations linked to aging, neurodegenerative diseases, and complex muscle disorders. Due to its uniparental and haploid inheritance, mtDNA captures matrilineal evolutionary trajectories, playing a crucial role in population and medical genetics. However, critical questions about the genomic diversity patterns, inheritance models, and evolutionary and medical functions of mtDNA remain unresolved or underexplored, particularly in the transition from traditional genotyping to large-scale genomic analyses. This review summarizes recent advancements in data-driven genomic research and technological innovations that address these questions and clarify the biological impact of nuclear-mitochondrial segments (NUMTs) and mtDNA variants on human health, disease, and evolution. We propose a streamlined pipeline to comprehensively identify mtDNA and NUMT genomic diversity using advanced sequencing and computational technologies. Haplotype-resolved mtDNA sequencing and assembly can distinguish authentic mtDNA variants from NUMTs, reduce diagnostic inaccuracies, and provide clearer insights into heteroplasmy patterns and the authenticity of paternal inheritance. This review emphasizes the need for integrative multi-omics approaches and emerging long-read sequencing technologies to gain new insights into mutation mechanisms, the influence of heteroplasmy and paternal inheritance on mtDNA diversity and disease susceptibility, and the detailed functions of NUMTs.
Collapse
Affiliation(s)
- Lintao Luo
- Institute of Rare Diseases, West China Hospital of Sichuan University, Sichuan University, Chengdu, 610000, China
- Department of Forensic Medicine, College of Basic Medicine, Chongqing Medical University, Chongqing, 400331, China
| | - Mengge Wang
- Institute of Rare Diseases, West China Hospital of Sichuan University, Sichuan University, Chengdu, 610000, China.
- Center for Archaeological Science, Sichuan University, Chengdu, 610000, China.
- Anti-Drug Technology Center of Guangdong Province, Guangzhou, 510230, China.
| | - Yunhui Liu
- Institute of Rare Diseases, West China Hospital of Sichuan University, Sichuan University, Chengdu, 610000, China
- Department of Forensic Medicine, College of Basic Medicine, Chongqing Medical University, Chongqing, 400331, China
| | - Jianbo Li
- Department of Forensic Medicine, College of Basic Medicine, Chongqing Medical University, Chongqing, 400331, China
| | - Fengxiao Bu
- Institute of Rare Diseases, West China Hospital of Sichuan University, Sichuan University, Chengdu, 610000, China
- Center for Archaeological Science, Sichuan University, Chengdu, 610000, China
| | - Huijun Yuan
- Institute of Rare Diseases, West China Hospital of Sichuan University, Sichuan University, Chengdu, 610000, China.
- Center for Archaeological Science, Sichuan University, Chengdu, 610000, China.
| | - Renkuan Tang
- Department of Forensic Medicine, College of Basic Medicine, Chongqing Medical University, Chongqing, 400331, China.
| | - Chao Liu
- Department of Forensic Medicine, College of Basic Medicine, Chongqing Medical University, Chongqing, 400331, China.
- Anti-Drug Technology Center of Guangdong Province, Guangzhou, 510230, China.
| | - Guanglin He
- Institute of Rare Diseases, West China Hospital of Sichuan University, Sichuan University, Chengdu, 610000, China.
- Center for Archaeological Science, Sichuan University, Chengdu, 610000, China.
- Anti-Drug Technology Center of Guangdong Province, Guangzhou, 510230, China.
| |
Collapse
|
|
15
|
Gustafson KA, Berman S, Gavaza P, Mohamed I, Devraj R, Abdel Aziz MH, Singh D, Southwood R, Ogunsanya ME, Chu A, Dave V, Prudencio J, Munir F, Hintze TD, Rowe C, Bernknopf A, Brand-Eubanks D, Hoffman A, Jones E, Miller V, Nogid A, Showman L. Pharmacy faculty and students perceptions of artificial intelligence: A National Survey. CURRENTS IN PHARMACY TEACHING & LEARNING 2025; 17:102344. [PMID: 40120500 DOI: 10.1016/j.cptl.2025.102344] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/02/2025] [Revised: 02/28/2025] [Accepted: 03/08/2025] [Indexed: 03/25/2025]
Abstract
INTRODUCTION This study explores the perceptions, familiarity, and utilization of artificial intelligence (AI) among pharmacy faculty and students across the United States. By identifying key gaps in AI education and training, it highlights the need for structured curricular integration to prepare future pharmacists for an evolving digital healthcare landscape. METHODS A 19-item Qualtrics™ survey was created to assess perceptions of AI use among pharmacy faculty and students and distributed utilizing publicly available contacts at schools of pharmacy and intern lists. The electronic survey was open from September 5th to November 22nd 2023. Responses were analyzed for trends and compared between faculty and student responses across four sub-domains. RESULTS A total of 235 pharmacy faculty and 405 pharmacy students completed the survey. Responses indicated high familiarity with AI in both groups but found differences in training. Both groups identified ethical considerations and training as major barriers to AI integration. Faculty were less likely to trust AI responses than students despite reporting similar rates of incorrect information. Students were more concerned than faculty about AI reducing pharmacy jobs, particularly in community and health-system settings. DISCUSSION This study highlights the need for intentional AI training tailored to pharmacy students, aiming to bridge the knowledge gap and equip them with the skills to navigate an AI-driven future. The inconsistency in how AI is addressed within the curriculum and the lack of established ethical guidelines display the need for clear and consistent institutional policies and professional guidance.
Collapse
Affiliation(s)
- Kyle A Gustafson
- Northeast Ohio Medical University, PO Box 95, 4209 St Rt 44, Rootstown, OH 44272, United States of America.
| | - Sarah Berman
- University of the Incarnate Word, Feik School of Pharmacy, 703 E. Hildebrand, San Antonio, TX 78212, United States of America.
| | - Paul Gavaza
- Loma Linda University School of Pharmacy, 11139 Anderson St, Loma Linda, CA 92350, United States of America.
| | - Islam Mohamed
- California Northstate University, 9700 W Taron Dr, Elk Grove, CA 95757, United States of America.
| | - Radhika Devraj
- Southern Illinois University Edwardsville, 6 Hairpin Dr, Edwardsville, IL 62026, United States of America.
| | - May H Abdel Aziz
- The University of Texas at Tyler, 3900 University Blvd, Tyler, TX 75799, United States of America.
| | - Divita Singh
- Temple University School of Pharmacy, 3307 N Broad St, Philadelphia, PA 19140, United States of America.
| | - Robin Southwood
- College of Pharmacy, University of Georgia, 240 W Green St, Athens, GA 30602, United States of America.
| | - Motolani E Ogunsanya
- University of Oklahoma Health Sciences Center, TSET Health Promotion Research Center, 1100 N Lindsay Ave, Oklahoma City, OK 73104, United States of America.
| | - Angela Chu
- Roseman University of Health Sciences, 10920 S River Frint Pkwy, South Jordan, UT 84095, United States of America.
| | - Vivek Dave
- St. John Fisher University, Wegmans School of Pharmacy, 3690 East Ave, Rochester, NY 14618, United States of America.
| | - Jarred Prudencio
- University of Hawaii at Hilo, 200 W Kawili St, Hilo, HI 96720, United States of America.
| | - Faria Munir
- University of Illinois Chicago, 1200 W Harrison St, Chicago, IL 60607, United States of America.
| | - Trager D Hintze
- Alice L Walton School of Medicine, 805 Mcclain Rd STE 800, Bentonville, AR 72712, United States of America
| | - Casey Rowe
- University of Florida College of Pharmacy - Orlando Campus, 6550 Sanger Rd, Orlando, FL 32827, United States of America.
| | - Allison Bernknopf
- Ferris State University, 1201 S State St, Big Rapids, MI 49307, United States of America.
| | - Damianne Brand-Eubanks
- Washington State University College of Pharmacy and Pharmaceutical Sciences, 200 University Pkwy, Yakima, WA 98901, United States of America.
| | - Alexander Hoffman
- Northeast Ohio Medical University, PO Box 95, 4209 St Rt 44, Rootstown, OH 44272, United States of America.
| | - Ellen Jones
- Harding University College of Pharmacy, 915 E Market, Searcy, AR 72143, United States of America.
| | - Victoria Miller
- University of Louisiana Monroe College of Pharmacy, 1800 Bienville Dr, Monroe, LA 71201, United States of America.
| | - Anna Nogid
- Fairleigh Dickinson School of Pharmacy & Health Sciences, 230 Park Ave, Florham Park, NJ 07932, United States of America.
| | - Leanne Showman
- Southwestern Oklahoma State University College of Pharmacy, 100 Campus Dr, Weatherford, OK 73096, United States of America.
| |
Collapse
|
|
16
|
van der Linden LR, Vavliakis I, de Groot TM, Jutte PC, Doornberg JN, Lozano-Calderon SA, Groot OQ. Artificial Intelligence in bone Metastases: A systematic review in guideline adherence of 92 studies. J Bone Oncol 2025; 52:100682. [PMID: 40337637 PMCID: PMC12056386 DOI: 10.1016/j.jbo.2025.100682] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2024] [Revised: 02/09/2025] [Accepted: 04/15/2025] [Indexed: 05/09/2025] Open
Abstract
Background The last decade has witnessed a surge in artificial intelligence (AI). With bone metastases becoming more prevalent, there is an increasing call for personalized treatment options, a domain where AI can greatly contribute. However, integrating AI into clinical settings has proven to be difficult. Therefore, we aimed to provide an overview of AI modalities for treating bone metastases and recommend implementation-worthy models based on TRIPOD, CLAIM, and UPM scores. Methods This systematic review included 92 studies on AI models in bone metastases between 2008 and 2024. Using three assessment tools we provided a reliable foundation for recommending AI modalities fit for clinical use (TRIPOD or CLAIM ≥ 70 % and UPM score ≥ 10). Results Most models focused on survival prediction (44/92;48%), followed by imaging studies (37/92;40%). Median TRIPOD completeness was 70% (IQR 64-81%), CLAIM completeness was 57% (IQR 48-67%), and UPM score was 7 (IQR 5-9). In total, 10% (9/92) AI modalities were deemed fit for clinical use. Conclusion Transparent reporting, utilizing the aforementioned three evaluation tools, is essential for effectively integrating AI models into clinical practice, as currently, only 10% of AI models for bone metastases are deemed fit for clinical use. Such transparency ensures that both patients and clinicians can benefit from clinically useful AI models, potentially enhancing AI-driven personalized cancer treatment.
Collapse
Affiliation(s)
- Lotte R. van der Linden
- Department of Orthopaedic Surgery, University Medical Center Groningen, Groningen, the Netherlands
- Department of Orthopaedic Surgery, Massachusetts General Hospital, Boston, MA, USA
| | - Ioannis Vavliakis
- Department of Orthopaedic Surgery, University Medical Center Groningen, Groningen, the Netherlands
| | - Tom M. de Groot
- Department of Orthopaedic Surgery, University Medical Center Groningen, Groningen, the Netherlands
- Department of Orthopaedic Surgery, Massachusetts General Hospital, Boston, MA, USA
| | - Paul C. Jutte
- Department of Orthopaedic Surgery, University Medical Center Groningen, Groningen, the Netherlands
| | - Job N. Doornberg
- Department of Orthopaedic Surgery, University Medical Center Groningen, Groningen, the Netherlands
| | | | - Olivier Q. Groot
- Department of Orthopaedic Surgery, Massachusetts General Hospital, Boston, MA, USA
- Department of Orthopaedic Surgery, University Medical Center Utrecht, Utrecht, the Netherlands
| |
Collapse
|
|
17
|
Naureen M, Siddiqui S, Nasir S, Khan A. Awareness of the Role of Artificial Intelligence in Health Care among Undergraduate Nursing Students: A Descriptive Cross-Ssectional Study. NURSE EDUCATION TODAY 2025; 149:106673. [PMID: 40068331 DOI: 10.1016/j.nedt.2025.106673] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/03/2024] [Revised: 02/25/2025] [Accepted: 03/06/2025] [Indexed: 04/07/2025]
Abstract
BACKGROUND Artificial intelligence (AI) has the potential to revolutionize healthcare by improving efficiency and reducing errors; however, challenges such as inadequate funding and lack of awareness among healthcare professionals hinder its integration into healthcare service delivery. AIM To assess the awareness of undergraduate student nurses regarding the role of AI in healthcare. DESIGN A descriptive cross-sectional design was used. SETTINGS The study was conducted at two nursing colleges in Pakistan: The Foundation University College of Nursing and the Institute of Nursing Wah Medical College. PARTICIPANTS A sample of 162 student nurses was selected, consisting of BSc Nursing students from the two nursing institutions. METHODS Data were collected using a pre-validated questionnaire adapted from Ahmad et al. (2023), comprising multiple-choice and Likert scale questions. The questionnaire assessed demographic information and awareness of AI, including barriers and advantages of AI in healthcare. Descriptive statistics were used for data analysis. Frequencies and percentages were calculated for demographic variables and responses from participants. RESULTS Of the total sample, 59.9 % of students had heard of AI in healthcare, while only 43.8 % had the requisite technical skills to understand AI literature. Additionally, 38.3 % had never encountered AI applications in their profession. The primary barriers to AI education were the lack of specialized courses (35.8 %) and mentorship (41.4 %), while key benefits included faster healthcare procedures (51.2 %) and a reduction in medical errors (32.7 %). CONCLUSIONS Although many student nurses are aware of AI, there is a substantial gap in technical knowledge and practical application. To address this, nursing curricula should include dedicated AI courses and practical training modules. Enhanced educational resources and support networks are crucial for overcoming existing barriers and leveraging AI's potential to transform healthcare practices.
Collapse
Affiliation(s)
- Misbah Naureen
- AFPGMI College of Nursing, NUMS University Rawalpindi, Pakistan.
| | - Sana Siddiqui
- Army Medical College Rawalpindi, NUMS University Rawalpindi, Pakistan
| | | | - Asghar Khan
- Batkhela College of Nursing, & Health Sciences, Batkhela Malakand, Pakistan
| |
Collapse
|
|
18
|
Li S, Wang Y, Chen L, Chen T, Du J, Su H, Jiang H, Wu Q, Zhang L, Bao J, Zhao M. Virtual agents among participants with methamphetamine use disorders: Acceptability and usability study. J Telemed Telecare 2025; 31:742-751. [PMID: 38260973 DOI: 10.1177/1357633x231219039] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/24/2024]
Abstract
IntroductionWhile the potential future role of virtual agents (VAs) in treating addiction is promising, participants' attitudes toward the use of VAs in psychotherapy remain insufficiently investigated. This lack of investigation could pose barriers to the adoption of VA-led psychotherapy for people with substance use disorders (SUD). This research aims to explore the acceptability and usability of VAs for people with methamphetamine use disorder.MethodsFollowing a single session of psychotherapy led by VAs through the Echo-app, a group of 49 individuals actively seeking treatment for current DSM-V substance dependence (with a mean age of 39.06 ± 8.02) completed self-administered questionnaires and participated in focus group interviews. These questionnaires aimed to investigate participants' preference regarding the type of psychotherapy and their willingness to engage in VA-led psychotherapy, taking into account their diverse psychological needs.ResultsQuantitative data were subjected to analysis through both descriptive and inferential statistical methods. Interestingly, participants exhibited a significantly higher acceptability for traditional face-to-face psychotherapy compared to email-based psychotherapy (p = 0.042), but there was no statistically significant difference between their acceptance of traditional psychotherapy and VA-led psychotherapy (p = 0.059). The questionnaire outcomes indicated participants' willingness to engage in VA-led psychotherapy for purposes such as relapse prevention intervention, addressing emotional issues, managing somatic experiences, and facilitating social and family functional recovery. Furthermore, the participants' attitudes toward VA-led psychotherapy were predicted by factors including the need for anxiety-focused psychotherapy (p = 0.027; OR [95%CI] = 0.14[0.03,0.80]), the presence of chronic somatic diseases (p = 0.017; OR [95%CI] = 13.58[1.59,116.03]), and marital status (p = 0.031; OR [95%CI] = 5.02[1.16,21.79]).DiscussionThrough the interviews, the study uncovered the factors that either supported or hindered participants' experiences with VA-led psychotherapy, while also gathering suggestions for future improvements. This research highlights the willingness and practicality of individuals with SUD in embracing VA-led psychotherapy. The findings are anticipated to contribute to the refinement of VA-led tools to better align with the preferences and needs of the users.
Collapse
Affiliation(s)
- Shuo Li
- Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Yue Wang
- Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Liyu Chen
- Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Tianzhen Chen
- Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Jiang Du
- Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Hang Su
- Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Haifeng Jiang
- Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Qianying Wu
- Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Lei Zhang
- Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Jiayi Bao
- Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Min Zhao
- Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Shanghai Key Laboratory of Psychotic Disorders, Shanghai Mental Health Center, Shanghai Jiaotong University School of Medicine, Shanghai, China
- CAS Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, China
| |
Collapse
|
|
19
|
Ratti E, Morrison M, Jakab I. Ethical and social considerations of applying artificial intelligence in healthcare-a two-pronged scoping review. BMC Med Ethics 2025; 26:68. [PMID: 40420080 DOI: 10.1186/s12910-025-01198-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2024] [Accepted: 03/17/2025] [Indexed: 05/28/2025] Open
Abstract
BACKGROUND Artificial Intelligence (AI) is being designed, tested, and in many cases actively employed in almost every aspect of healthcare from primary care to public health. It is by now well established that any application of AI carries an attendant responsibility to consider the ethical and societal aspects of its development, deployment and impact. However, in the rapidly developing field of AI, developments such as machine learning, neural networks, generative AI, and large language models have the potential to raise new and distinct ethical and social issues compared to, for example, automated data processing or more 'basic' algorithms. METHODS This article presents a scoping review of the ethical and social issues pertaining to AI in healthcare, with a novel two-pronged design. One strand of the review (SR1) consists of a broad review of the academic literature restricted to a recent timeframe (2021-23), to better capture up to date developments and debates. The second strand (SR2) consists of a narrow review, limited to prior systematic and scoping reviews on the ethics of AI in healthcare, but extended over a longer timeframe (2014-2024) to capture longstanding and recurring themes and issues in the debate. This strategy provides a practical way to deal with an increasingly voluminous literature on the ethics of AI in healthcare in a way that accounts for both the depth and evolution of the literature. RESULTS SR1 captures the heterogeneity of audience, medical fields, and ethical and societal themes (and their tradeoffs) raised by AI systems. SR2 provides a comprehensive picture of the way scoping reviews on ethical and societal issues in AI in healthcare have been conceptualized, as well as the trends and gaps identified. CONCLUSION Our analysis shows that the typical approach to ethical issues in AI, which is based on the appeal to general principles, becomes increasingly unlikely to do justice to the nuances and specificities of the ethical and societal issues raised by AI in healthcare, as the technology moves from abstract debate and discussion to real world situated applications and concerns in healthcare settings.
Collapse
Affiliation(s)
- Emanuele Ratti
- Department of Philosophy, Cotham House University of Bristol, Bristol, BS6 6JL, UK
| | - Michael Morrison
- Helex - Centre for Health, Law and Emerging Technologies, Faculty of Law, University of Oxford, St Cross Building, Room 201St Cross Road, Oxford, OX1 3UL, UK.
- Institute for Science, Innovation and Society, School of Anthropology and Museum Ethnography, University of Oxford, 64 Banbury Road, Oxford, OX2 6PN, UK.
| | - Ivett Jakab
- YAGHMA B.V., 6C , Poortweg, Delft, Netherlands
| |
Collapse
|
|
20
|
Rizzo M. AI in Neurology: Everything, Everywhere, all at Once PART 2: Speech, Sentience, Scruples, and Service. Ann Neurol 2025. [PMID: 40421866 DOI: 10.1002/ana.27229] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2024] [Revised: 02/10/2025] [Accepted: 02/17/2025] [Indexed: 05/28/2025]
Abstract
Artificial intelligence (AI) applications are finding use in real-world neurological settings. Whereas part 1 of this 3-part review series focused on the birth of AI and its foundational principles, this part 2 review shifts gears to explore more practical aspects of neurological care. The review details how large language models, generative AI, and robotics are supporting diagnostic accuracy, patient interaction, and treatment personalization. Special attention is given to ethical and philosophical facets of AI that nonetheless impact practical aspects of care and patient safety, such as accountability for AI-driven decisions and the "black box" nature of many algorithms. We will discuss whether AI systems can develop sentience, and the implications for human-AI collaboration. By examining human-robot interactions in neurology, this part 2 review highlights the profound impact AI could have on patient care and, as covered in the ensuing part 3, on global health care delivery and data analytics, while maintaining ethical oversight and human control. ANN NEUROL 2025.
Collapse
Affiliation(s)
- Matthew Rizzo
- Department of Neurological Sciences, University of Nebraska Medical Center, Omaha, NE
| |
Collapse
|
|
21
|
Lederman O, Llana A, Murray J, Stanton R, Chugh R, Haywood D, Burdett A, Warman G, Walker J, Hart NH. Promises and perils of generative artificial intelligence: a narrative review informing its ethical and practical applications in clinical exercise physiology. BMC Sports Sci Med Rehabil 2025; 17:131. [PMID: 40420209 DOI: 10.1186/s13102-025-01182-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2024] [Accepted: 05/12/2025] [Indexed: 05/28/2025]
Abstract
Generative Artificial Intelligence (GenAI) is transforming various sectors, including healthcare, offering both promising opportunities and notable risks. The infancy and rapid development of GenAI raises questions regarding its effective, safe, and ethical use by health professionals, including clinical exercise physiologists. This narrative review aims to explore existing interdisciplinary literature and summarise the ethical and practical considerations of integrating GenAI into clinical exercise physiology practice. Specifically, it examines the 'promises' of improved exercise programming and healthcare delivery, as well as the 'perils' related to data privacy, person-centred care, and equitable access. Recommendations for the responsible integration of GenAI in clinical exercise physiology are described, in addition to recommendations for future research to address gaps in knowledge. Future directions, including the roles and responsibilities of specific stakeholder groups are discussed, highlighting the need for clear professional guidelines in facilitating safe and ethical deployment of GenAI into clinical exercise physiology practice. Synthesis of current literature serves as an essential step in guiding strategies to ensure the safe, ethical, and effective integration of GenAI in clinical exercise physiology, providing a foundation for future guidelines, training, and research to enhance service delivery while maintaining high standards of practice.
Collapse
Affiliation(s)
- Oscar Lederman
- Human Performance Research Centre, School of Sport, Exercise and Rehabilitation, Faculty of Health, University of Technology Sydney (UTS), Moore Park, Sydney, NSW, Australia.
- Discipline of Psychiatry and Mental Health, School of Clinical Medicine, University of New South Wales, Sydney, NSW, Australia.
| | - Alessandro Llana
- Human Performance Research Centre, School of Sport, Exercise and Rehabilitation, Faculty of Health, University of Technology Sydney (UTS), Moore Park, Sydney, NSW, Australia
| | - James Murray
- Human Performance Research Centre, School of Sport, Exercise and Rehabilitation, Faculty of Health, University of Technology Sydney (UTS), Moore Park, Sydney, NSW, Australia
| | - Robert Stanton
- School of Health, Medical and Applied Sciences, Central Queensland University, Rockhampton, QLD, Australia
| | - Ritesh Chugh
- School of Engineering and Technology, Central Queensland University, Melbourne, VIC, Australia
| | - Darren Haywood
- Human Performance Research Centre, School of Sport, Exercise and Rehabilitation, Faculty of Health, University of Technology Sydney (UTS), Moore Park, Sydney, NSW, Australia
- Department of Mental Health, St. Vincent's Hospital Melbourne, Fitzroy, VIC, Australia
| | - Amanda Burdett
- Human Performance Research Centre, School of Sport, Exercise and Rehabilitation, Faculty of Health, University of Technology Sydney (UTS), Moore Park, Sydney, NSW, Australia
| | - Geoff Warman
- Human Performance Research Centre, School of Sport, Exercise and Rehabilitation, Faculty of Health, University of Technology Sydney (UTS), Moore Park, Sydney, NSW, Australia
- School of Health, Medical and Applied Sciences, Central Queensland University, Rockhampton, QLD, Australia
| | - Joanne Walker
- Human Performance Research Centre, School of Sport, Exercise and Rehabilitation, Faculty of Health, University of Technology Sydney (UTS), Moore Park, Sydney, NSW, Australia
| | - Nicolas H Hart
- Human Performance Research Centre, School of Sport, Exercise and Rehabilitation, Faculty of Health, University of Technology Sydney (UTS), Moore Park, Sydney, NSW, Australia
- Exercise Medicine Research Institute, School of Medical and Health Sciences, Edith Cowan University, Perth, WA, Australia
| |
Collapse
|
|
22
|
Gisselbaek M, Berger-Estilita J, Devos A, Ingrassia PL, Dieckmann P, Saxena S. Bridging the gap between scientists and clinicians: addressing collaboration challenges in clinical AI integration. BMC Anesthesiol 2025; 25:269. [PMID: 40419984 DOI: 10.1186/s12871-025-03130-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2025] [Accepted: 05/09/2025] [Indexed: 05/28/2025] Open
Abstract
This article explores challenges for bridging the gap between scientists and healthcare professionals in artifical intelligence (AI) integration. It highlights barriers, the role of interdisciplinary research centers, and the importance of diversity, equity, and inclusion. Collaboration, education, and ethical AI development are essential for optimizing AI's impact in perioperative medicine.
Collapse
Affiliation(s)
- Mia Gisselbaek
- Division of Anesthesiology, Department of Anesthesiology, Clinical Pharmacology, Intensive Care and Emergency Medicine, Geneva University Hospitals and Faculty of Medicine, Geneva, Switzerland
- Unit of Development and Research in Medical Education (UDREM), Faculty of Medicine, University of Geneva, Geneva, Switzerland
| | - Joana Berger-Estilita
- Institute for Medical Education, University of Bern, Bern, Switzerland
- INTESIS@RISE, Centre for Health Technology and Services Research, Faculty of Medicine, University of Porto, Porto, Portugal
| | - Arnout Devos
- ETH AI Center, Swiss Federal Institute of Technology Zurich (ETH Zurich), Zürich, Switzerland
| | - Pierre Luigi Ingrassia
- Centro di Simulazione (CeSi), Centro Professionale Sociosanitario Medico-Tecnico, Lugano, Switzerland
| | - Peter Dieckmann
- Copenhagen Academy for Medical Education and Simulation (CAMES), Capital Region of Denmark, Herlev, Denmark
- Department of Quality and Health Technology, University in Stavanger, Stavanger, Norway
- Department of Public Health, Copenhagen University, Copenhagen, Denmark
| | - Sarah Saxena
- Department of Anesthesiology, Helora, Mons, Belgium.
- Department of Surgery, Research Institute for Health Sciences and Technology, UMons, University of Mons, Mons, Belgium.
| |
Collapse
|
|
23
|
Oftring ZS, Deutsch K, Tolks D, Jungmann F, Kuhn S. Novel Blended Learning on Artificial Intelligence for Medical Students: Qualitative Interview Study. JMIR MEDICAL EDUCATION 2025; 11:e65220. [PMID: 40418795 DOI: 10.2196/65220] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/09/2024] [Revised: 03/03/2025] [Accepted: 04/06/2025] [Indexed: 05/28/2025]
Abstract
Background Artificial intelligence (AI) systems are becoming increasingly relevant in everyday clinical practice, with Food and Drug Administration-approved AI solutions now available in many specialties. This development has far-reaching implications for doctors and the future medical profession, highlighting the need for both practicing physicians and medical students to acquire the knowledge, skills, and attitudes necessary to effectively use and evaluate these technologies. Currently, however, there is limited experience with AI-focused curricular training and continuing education. Objective This paper first introduces a novel blended learning curriculum including one module on AI for medical students in Germany. Second, this paper presents findings from a qualitative postcourse evaluation of students' knowledge and attitudes toward AI and their overall perception of the course. Methods Clinical-year medical students can attend a 5-day elective course called "Medicine in the Digital Age," which includes one dedicated AI module alongside 4 others on digital doctor-patient communication; digital health applications and smart devices; telemedicine; and virtual/augmented reality and robotics. After course completion, participants were interviewed in semistructured small group interviews. The interview guide was developed deductively from existing evidence and research questions compiled by our group. A subset of interview questions focused on students' knowledge, skills, and attitudes regarding medical AI, and their overall course assessment. Responses were analyzed using Mayring's qualitative content analysis. This paper reports on the subset of students' statements about their perception and attitudes toward AI and the elective's general evaluation. Results We conducted a total of 18 group interviews, in which all 35 (100%) participants (female=11, male=24) from 3 consecutive course runs participated. This produced a total of 214 statements on AI, which were assigned to the 3 main categories "Areas of Application," "Future Work," and "Critical Reflection." The findings indicate that students have a nuanced and differentiated understanding of AI. Additionally, 610 statements concerned the elective's overall assessment, demonstrating great learning benefits and high levels of acceptance of the teaching concept. All 35 students would recommend the elective to peers. Conclusions The evaluation demonstrated that the AI module effectively generates competences regarding AI technology, fosters a critical perspective, and prepares medical students to engage with the technology in a differentiated manner. The curriculum is feasible, beneficial, and highly accepted among students, suggesting it could serve as a teaching model for other medical institutions. Given the growing number and impact of medical AI applications, there is a pressing need for more AI-focused curricula and further research on their educational impact.
Collapse
Affiliation(s)
- Zoe S Oftring
- Institute for Digital Medicine, Philipps University Marburg and University Clinic Giessen & Marburg, Baldingerstrasse 1, Marburg, 35042, Germany, 49 (0)6421 ext 58
- Department of Paediatrics, University Clinic Giessen & Marburg, Marburg, Germany
| | - Kim Deutsch
- Institute of Educational Science, Johannes Gutenberg University, Mainz, Germany
| | - Daniel Tolks
- Institute of Anatomy, Rostock University Medical Centre, Rostock, Germany
- Professorship in Health Management, International University of Applied Science, Hamburg, Germany
| | - Florian Jungmann
- Xcare Group Radiology, Nuclear Medicine and Radiotherapy, Saarlouis, Germany
| | - Sebastian Kuhn
- Institute for Digital Medicine, Philipps University Marburg and University Clinic Giessen & Marburg, Baldingerstrasse 1, Marburg, 35042, Germany, 49 (0)6421 ext 58
| |
Collapse
|
|
24
|
Milecki L, Bodard S, Kalogeiton V, Poinard F, Tissier AM, Boudhabhay I, Correas JM, Anglicheau D, Vakalopoulou M, Timsit MO. Renal Transplant Survival Prediction From Unsupervised Deep Learning-Based Radiomics on Early Dynamic Contrast-Enhanced MRI. Acad Radiol 2025:S1076-6332(25)00428-3. [PMID: 40413148 DOI: 10.1016/j.acra.2025.05.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2025] [Revised: 04/21/2025] [Accepted: 05/01/2025] [Indexed: 05/27/2025]
Abstract
RATIONALE AND OBJECTIVES End-stage renal disease is characterized by an irreversible decline in kidney function. Despite a risk of chronic dysfunction of the transplanted kidney, renal transplantation is considered the most effective solution among available treatment options. Clinical attributes of graft survival prediction, such as allocation variables or results of pathological examinations, have been widely studied. Nevertheless, medical imaging is clinically used only to assess current transplant status. This study investigated the use of unsupervised deep learning-based algorithms to identify rich radiomic features that may be linked to graft survival from early dynamic contrast-enhanced magnetic resonance imaging data of renal transplants. MATERIALS AND METHODS A retrospective cohort of 108 transplanted patients (mean age 50 +/- 15, 67 men) undergoing systematic magnetic resonance imaging follow-up examinations (2013 to 2015) was used to train deep convolutional neural network models based on an unsupervised contrastive learning approach. 5-year graft survival analysis was performed from the obtained artificial intelligence radiomics features using penalized Cox models and Kaplan-Meier estimates. RESULTS Using a validation set of 48 patients (mean age 54 +/- 13, 30 men) having 1-month post-transplantation magnetic resonance imaging examinations, the proposed approach demonstrated promising 5-year graft survival capability with a 72.7% concordance index from the artificial intelligence radiomics features. Unsupervised clustering of these radiomics features enabled statistically significant stratification of patients (p=0.029). CONCLUSION This proof-of-concept study exposed the promising capability of artificial intelligence algorithms to extract relevant radiomics features that enable renal transplant survival prediction. Further studies are needed to demonstrate the robustness of this technique, and to identify appropriate procedures for integration of such an approach into multimodal and clinical settings.
Collapse
Affiliation(s)
- Léo Milecki
- MICS, CentraleSupelec, Paris-Saclay University, Inria Saclay, 9 Rue Joliot Curie, 91190 Gif-sur-Yvette, France (L.M., M.V.).
| | - Sylvain Bodard
- Department of Adult Radiology, Necker Hospital, APHP, 149 Rue de Sèvres, 75015 Paris, France (S.B., A.M.T., J.M.C.)
| | - Vicky Kalogeiton
- LIX, École Polytechnique, CNRS, Institut Polytechnique de Paris, 1 Rue Honoré d'Estienne d'Orves, 91120 Palaiseau, France (V.K.)
| | - Florence Poinard
- Department of Urology and Renal Transplantation, Georges Pompidou European Hospital, APHP, 20 Rue Leblanc, 75015 Paris, France (F.P., M.O.T.)
| | - Anne-Marie Tissier
- Department of Adult Radiology, Necker Hospital, APHP, 149 Rue de Sèvres, 75015 Paris, France (S.B., A.M.T., J.M.C.)
| | - Idris Boudhabhay
- Department of Nephrology and Kidney Transplantation, Necker Hospital, APHP, 149 Rue de Sèvres, 75015 Paris, France (I.B., D.A.)
| | - Jean-Michel Correas
- Department of Adult Radiology, Necker Hospital, APHP, 149 Rue de Sèvres, 75015 Paris, France (S.B., A.M.T., J.M.C.); UFR Médecine, Paris-Cité University, 15 Rue de l'Ecole de Médecine, 75006 Paris, France (J.M.C., D.A., M.O.T.)
| | - Dany Anglicheau
- Department of Nephrology and Kidney Transplantation, Necker Hospital, APHP, 149 Rue de Sèvres, 75015 Paris, France (I.B., D.A.); UFR Médecine, Paris-Cité University, 15 Rue de l'Ecole de Médecine, 75006 Paris, France (J.M.C., D.A., M.O.T.)
| | - Maria Vakalopoulou
- MICS, CentraleSupelec, Paris-Saclay University, Inria Saclay, 9 Rue Joliot Curie, 91190 Gif-sur-Yvette, France (L.M., M.V.)
| | - Marc-Olivier Timsit
- Department of Urology and Renal Transplantation, Georges Pompidou European Hospital, APHP, 20 Rue Leblanc, 75015 Paris, France (F.P., M.O.T.); UFR Médecine, Paris-Cité University, 15 Rue de l'Ecole de Médecine, 75006 Paris, France (J.M.C., D.A., M.O.T.)
| |
Collapse
|
|
25
|
Heudel P, Ahmed M, Renard F, Attye A. Leveraging Digital Twins for Stratification of Patients with Breast Cancer and Treatment Optimization in Geriatric Oncology: Multivariate Clustering Analysis. JMIR Cancer 2025; 11:e64000. [PMID: 40408774 DOI: 10.2196/64000] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2024] [Revised: 01/22/2025] [Accepted: 02/24/2025] [Indexed: 05/25/2025] Open
Abstract
Background Defining optimal adjuvant therapeutic strategies for older adult patients with breast cancer remains a challenge, given that this population is often overlooked and underserved in clinical research and decision-making tools. objectives This study aimed to develop a prognostic and treatment guidance tool tailored to older adult patients using artificial intelligence (AI) and a combination of clinical and biological features. Methods A retrospective analysis was conducted on data from women aged 70+ years with HER2-negative early-stage breast cancer treated at the French Léon Bérard Cancer Center between 1997 and 2016. Manifold learning and machine learning algorithms were applied to uncover complex data relationships and develop predictive models. Predictors included age, BMI, comorbidities, hemoglobin levels, lymphocyte counts, hormone receptor status, Scarff-Bloom-Richardson grade, tumor size, and lymph node involvement. The dimension reduction technique PaCMAP was used to map patient profiles into a 3D space, allowing comparison with similar cases to estimate prognoses and potential treatment benefits. Results Out of 1229 initial patients, 793 were included after data refinement. The selected predictors demonstrated high predictive efficacy for 5-year mortality, with mean area under the curve scores of 0.81 for Random Forest Classification and 0.76 for Support Vector Classifier. The tool categorized patients into prognostic clusters and enabled the estimation of treatment outcomes, such as chemotherapy benefits. Unlike traditional models that focus on isolated factors, this AI-based approach integrates multiple clinical and biological features to generate a comprehensive biomedical profile. Conclusions This study introduces a novel AI-driven prognostic tool for older adult patients with breast cancer, enhancing treatment guidance by leveraging advanced machine learning techniques. The model provides a more nuanced understanding of disease dynamics and therapeutic strategies, emphasizing the importance of personalized oncology care.
Collapse
Affiliation(s)
- Pierre Heudel
- Department of Medical Oncology, Centre Leon Bérard, 28 rue Laennec, Lyon, 69008, France, 33 478782952
| | | | | | | |
Collapse
|
|
26
|
Khan M, Ahuja K, Tsirikos AI. AI and machine learning in paediatric spine deformity surgery. Bone Jt Open 2025; 6:569-581. [PMID: 40407025 PMCID: PMC12100669 DOI: 10.1302/2633-1462.65.bjo-2024-0089.r1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 05/26/2025] Open
Abstract
Paediatric spine deformity surgery is a high-stakes procedure. It demands the surgeon to have exceptional anatomical knowledge and precise visuospatial awareness. There is increasing demand for precision medicine, which rapid advancements in computational technologies have made possible with the recent explosion of AI and machine learning (ML). We present the surgical and ethical applications of AI and ML in diagnosis, prognosis, image processing, and outcomes in the field of paediatric spine deformity.
Collapse
Affiliation(s)
- Mohsin Khan
- Scottish National Spine Deformity Centre, Royal Hospital for Children and Young People, Edinburgh, UK
| | - Kaustubh Ahuja
- Scottish National Spine Deformity Centre, Royal Hospital for Children and Young People, Edinburgh, UK
| | - Athanasios I Tsirikos
- Scottish National Spine Deformity Centre, Royal Hospital for Children and Young People, Edinburgh, UK
| |
Collapse
|
|
27
|
Jaiteh M, Phalane E, Shiferaw YA, Amusa LB, Twinomurinzi H, Phaswana-Mafuya RN. Application of Machine Learning and Emerging Health Technologies in the Uptake of HIV Testing: Bibliometric Analysis of Studies Published From 2000 to 2024. Interact J Med Res 2025; 14:e64829. [PMID: 40402556 DOI: 10.2196/64829] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2024] [Revised: 12/12/2024] [Accepted: 12/12/2024] [Indexed: 05/23/2025] Open
Abstract
Background The global targets for HIV testing for achieving the Joint United Nations Programme on HIV/AIDS (UNAIDS) 95-95-95 targets are still short. Identifying gaps and opportunities for HIV testing uptake is crucial in fast-tracking the second (initiate people living with HIV on antiretroviral therapy) and third (viral suppression) UNAIDS goals. Machine learning and health technologies can precisely predict high-risk individuals and facilitate more effective and efficient HIV testing methods. Despite this advancement, there exists a research gap regarding the extent to which such technologies are integrated into HIV testing strategies worldwide. Objective The study aimed to examine the characteristics, citation patterns, and contents of published studies applying machine learning and emerging health technologies in HIV testing from 2000 to 2024. Methods This bibliometric analysis identified relevant studies using machine learning and emerging health technologies in HIV testing from the Web of Science database using synonymous keywords. The Bibliometrix R package was used to analyze the characteristics, citation patterns, and contents of 266 articles. The VOSviewer software was used to conduct network visualization. The analysis focused on the yearly growth rate, citation analysis, keywords, institutions, countries, authorship, and collaboration patterns. Key themes and topics were driven by the authors' most frequent keywords, which aided the content analysis. Results The analysis revealed a scientific annual growth rate of 15.68%, with an international coauthorship of 8.22% and an average citation count of 17.47 per document. The most relevant sources were from high-impact journals such as the Journal of Internet Medicine Research, JMIR mHealth and uHealth, JMIR Research Protocols, mHealth, AIDS Care-Psychological and Socio-Medical Aspects of AI, and BMC Public Health, and PLOS One. The United States of America, China, South Africa, the United Kingdom, and Australia produced the highest number of contributions. Collaboration analysis showed significant networks among universities in high-income countries, including the University of North Carolina, Emory University, the University of Michigan, San Diego State University, the University of Pennsylvania, and the London School of Hygiene and Tropical Medicine. The discrepancy highlights missed opportunities in strategic partnerships between high-income and low-income countries. The results further demonstrate that machine learning and health technologies enhance the effective and efficient implementation of innovative HIV testing methods, including HIV self-testing among priority populations. Conclusions This study identifies trends and hotspots of machine learning and health technology research in relation to HIV testing across various countries, institutions, journals, and authors. The trends are higher in high-income countries with a greater focus on technology applications for HIV self-testing among young people and priority populations. These insights will inform future researchers about the dynamics of research outputs and help them make scholarly decisions to address research gaps in this field.
Collapse
Affiliation(s)
- Musa Jaiteh
- South African Medical Research Council/University of Johannesburg Pan African Centre for Epidemics Research Extramural Unit, Faculty of Health Sciences, University of Johannesburg, Auckland Park Bunting Road Campus, PO Box 524, Auckland Park, Johannesburg, 2006, South Africa, 27 632376425, 27 115591496
| | - Edith Phalane
- South African Medical Research Council/University of Johannesburg Pan African Centre for Epidemics Research Extramural Unit, Faculty of Health Sciences, University of Johannesburg, Auckland Park Bunting Road Campus, PO Box 524, Auckland Park, Johannesburg, 2006, South Africa, 27 632376425, 27 115591496
| | - Yegnanew A Shiferaw
- Department of Statistics, Faculty of Science, University of Johannesburg, Johannesburg, South Africa
| | - Lateef Babatunde Amusa
- Center of Applied Data Science, University of Johannesburg, Johannesburg, South Africa
- Department of Statistics, University of Ilorin, Ilorin, Nigeria
| | - Hossana Twinomurinzi
- Center of Applied Data Science, University of Johannesburg, Johannesburg, South Africa
| | - Refilwe Nancy Phaswana-Mafuya
- South African Medical Research Council/University of Johannesburg Pan African Centre for Epidemics Research Extramural Unit, Faculty of Health Sciences, University of Johannesburg, Auckland Park Bunting Road Campus, PO Box 524, Auckland Park, Johannesburg, 2006, South Africa, 27 632376425, 27 115591496
| |
Collapse
|
|
28
|
Badawy MK, Carrion D, Mahesh M. Medical physicists at the forefront of multidisciplinary AI integration in healthcare. Phys Med 2025; 135:105007. [PMID: 40409215 DOI: 10.1016/j.ejmp.2025.105007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/02/2025] [Revised: 05/01/2025] [Accepted: 05/19/2025] [Indexed: 05/25/2025] Open
Affiliation(s)
- M K Badawy
- Monash Imaging, Monash Health, Clayton, Victoria, Australia; Department of Medical Imaging and Radiation Sciences, Monash University, Clayton, Victoria, Australia.
| | - D Carrion
- Monash Imaging, Monash Health, Clayton, Victoria, Australia
| | - M Mahesh
- The Russell H Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| |
Collapse
|
|
29
|
Yang HC, Hao ATH, Liu SC, Chang YC, Tsai YT, Weng SJ, Chan MC, Wang CY, Xu YY. Prediction of Spontaneous Breathing Trial Outcome in Critically Ill-Ventilated Patients Using Deep Learning: Development and Verification Study. JMIR Med Inform 2025; 13:e64592. [PMID: 40397953 DOI: 10.2196/64592] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2024] [Revised: 03/17/2025] [Accepted: 04/20/2025] [Indexed: 05/23/2025] Open
Abstract
BACKGROUND Long-term ventilator-dependent patients often face problems such as decreased quality of life, increased mortality, and increased medical costs. Respiratory therapists must perform complex and time-consuming ventilator weaning assessments, which typically take 48-72 hours. Traditional disengagement methods rely on manual evaluation and are susceptible to subjectivity, human errors, and low efficiency. OBJECTIVE This study aims to develop an artificial intelligence-based prediction model to predict whether a patient can successfully pass a spontaneous breathing trial (SBT) using the patient's clinical data collected before SBT initiation. Instead of comparing different SBT strategies or analyzing their impact on extubation success, this study focused on establishing a data-driven approach under a fixed SBT strategy to provide an objective and efficient assessment tool. Through this model, we aim to enhance the accuracy and efficiency of ventilator weaning assessments, reduce unnecessary SBT attempts, optimize intensive care unit resource usage, and ultimately improve the quality of care for ventilator-dependent patients. METHODS This study used a retrospective cohort study and developed a novel deep learning architecture, hybrid CNN-MLP (convolutional neural network-multilayer perceptron), for analysis. Unlike the traditional CNN-MLP classification method, hybrid CNN-MLP performs feature learning and fusion by interleaving CNN and MLP layers so that data features can be extracted and integrated at different levels, thereby improving the flexibility and prediction accuracy of the model. The study participants were patients aged 20 years or older hospitalized in the intensive care unit of a medical center in central Taiwan between January 1, 2016, and December 31, 2022. A total of 3686 patients were included in the study, and 6536 pre-SBT clinical records were collected before each SBT of these patients, of which 3268 passed the SBT and 3268 failed. RESULTS The model performed well in predicting SBT outcomes. The training dataset's precision is 99.3% (2443/2460 records), recall is 93.5% (2443/2614 records), specificity is 99.3% (2597/2614 records), and F1-score is 0.963. In the test dataset, the model maintains accuracy with a precision of 89.2% (561/629 records), a recall of 85.8% (561/654 records), a specificity of 89.6% (586/654 records), and an F1-score of 0.875. These results confirm the reliability of the model and its potential for clinical application. CONCLUSIONS This study successfully developed a deep learning-based SBT prediction model that can be used as an objective and efficient ventilator weaning assessment tool. The model's performance shows that it can be integrated into clinical workflow, improve the quality of patient care, and reduce ventilator dependence, which is an important step in improving the effectiveness of respiratory therapy.
Collapse
Affiliation(s)
- Hui-Chiao Yang
- Department of Chest Medicine, Division of Respiratory Therapy, Taichung Veterans General Hospital, Taichung, Taiwan
| | - Angelica Te-Hui Hao
- Department of Nursing, Hungkuang University, Taichung, Taiwan
- Department of Information Management, National Central University, Taoyuan, Taiwan
| | - Shih-Chia Liu
- Department of Nursing, Hungkuang University, Taichung, Taiwan
- Department of Industrial Engineering and Enterprise Information, Tunghai University, Taichung, Taiwan
| | - Yu-Cheng Chang
- Department of Computer and Communications Center, Taichung Veterans General Hospital, Taichung, Taiwan
| | - Yao-Te Tsai
- Department of Information Management, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan
| | - Shao-Jen Weng
- Department of Industrial Engineering and Enterprise Information, Tunghai University, Taichung, Taiwan
| | - Ming-Cheng Chan
- Department of Critical Care Medicine, Taichung Veterans General Hospital, Taichung, Taiwan
| | - Chen-Yu Wang
- Department of Critical Care Medicine, Taichung Veterans General Hospital, Taichung, Taiwan
| | - Yeong-Yuh Xu
- Department of Artificial Intelligence and Computer Engineering, National Chin-Yi University of Technology, Taichung, Taiwan
| |
Collapse
|
|
30
|
Rudroff T. Digital Biomarkers and AI for Remote Monitoring of Fatigue Progression in Neurological Disorders: Bridging Mechanisms to Clinical Applications. Brain Sci 2025; 15:533. [PMID: 40426703 DOI: 10.3390/brainsci15050533] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2025] [Revised: 05/14/2025] [Accepted: 05/19/2025] [Indexed: 05/29/2025] Open
Abstract
Digital biomarkers for fatigue monitoring in neurological disorders represent an innovative approach to bridge the gap between mechanistic understanding and clinical application. This perspective paper examines how smartphone-derived measures, analyzed through artificial intelligence methods, can transform fatigue assessment from subjective, episodic reporting to continuous, objective monitoring. The proposed framework for smartphone-based digital phenotyping captures passive data (movement patterns, device interactions, and sleep metrics) and active assessments (ecological momentary assessments, cognitive tests, and voice analysis). These digital biomarkers can be validated through a multimodal approach connecting them to neuroimaging markers, clinical assessments, performance measures, and patient-reported experiences. Building on the previous research on frontal-striatal metabolism in multiple sclerosis and Long-COVID-19 patients, digital biomarkers could enable early warning systems for fatigue episodes, objective treatment response monitoring, and personalized fatigue management strategies. Implementation considerations include privacy protection, equity concerns, and regulatory pathways. By integrating smartphone-derived digital biomarkers with AI analysis approaches, the future envisions fatigue in neurological disorders no longer as an invisible, subjective experience but rather as a quantifiable, treatable phenomenon with established neural correlates and effective interventions. This transformative approach has significant potential to enhance both clinical care and the research for millions affected by disabling fatigue symptoms.
Collapse
Affiliation(s)
- Thorsten Rudroff
- PET Centre, University of Turku, Turku University Hospital, 20520 Turku, Finland
| |
Collapse
|
|
31
|
Picchio V, Pontecorvi V, Dhori X, Bordin A, Floris E, Cozzolino C, Frati G, Pagano F, Chimenti I, De Falco E. The emerging role of artificial intelligence applied to exosome analysis: from cancer biology to other biomedical fields. Life Sci 2025; 375:123752. [PMID: 40409585 DOI: 10.1016/j.lfs.2025.123752] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2025] [Revised: 05/06/2025] [Accepted: 05/20/2025] [Indexed: 05/25/2025]
Abstract
In recent years, exosomes versatility has prompted their study in the biomedical field for diagnostic, prognostic, and therapeutic applications. Exosomes are bi-lipid small extracellular vesicles (30-150 nm) secreted by various cell types, containing proteins, lipids, and DNA/RNA. They mediate intercellular communication and can influence multiple human physiological and pathological processes. So far, exosome analysis has revealed their role as promising diagnostic tools for human pathologies. Concurrently, artificial intelligence (AI) has revolutionised multiple sectors, including medicine, owing to its ability to analyse large datasets and identify complex patterns. The combination of exosome analysis with AI processing has displayed a novel diagnostic approach for cancer and other diseases. This review explores the current applications and prospects of the combined use of exosomes and AI in medicine. Firstly, we provide a biological overview of exosomes and their relevance in cancer biology. Then we explored exosome isolation techniques and Raman spectroscopy/SERS analysis. Finally, we present a summarised essential guide of AI methods for non-experts, emphasising the advancements made in AI applications for exosome characterisation and profiling in oncology research, as well as in other human diseases.
Collapse
Affiliation(s)
- Vittorio Picchio
- Department of Angio Cardio Neurology, IRCCS Neuromed, 86077 Pozzilli, Italy
| | - Virginia Pontecorvi
- Department of Medical Surgical Sciences and Biotechnologies, Sapienza University, 04100 Latina, Italy
| | - Xhulio Dhori
- CINECA, Super Computing Applications and Innovation Department, 000185 Roma, Italy
| | - Antonella Bordin
- Department of Medical Surgical Sciences and Biotechnologies, Sapienza University, 04100 Latina, Italy
| | - Erica Floris
- Department of Medical Surgical Sciences and Biotechnologies, Sapienza University, 04100 Latina, Italy
| | - Claudia Cozzolino
- Department of Medical Surgical Sciences and Biotechnologies, Sapienza University, 04100 Latina, Italy
| | - Giacomo Frati
- Department of Angio Cardio Neurology, IRCCS Neuromed, 86077 Pozzilli, Italy; Department of Medical Surgical Sciences and Biotechnologies, Sapienza University, 04100 Latina, Italy
| | - Francesca Pagano
- Institute of Biochemistry and Cell Biology, National Council of Research (IBBC-CNR), 00015 Monterotondo,Italy
| | - Isotta Chimenti
- Department of Angio Cardio Neurology, IRCCS Neuromed, 86077 Pozzilli, Italy; Department of Medical Surgical Sciences and Biotechnologies, Sapienza University, 04100 Latina, Italy; CINECA, Super Computing Applications and Innovation Department, 000185 Roma, Italy; Institute of Biochemistry and Cell Biology, National Council of Research (IBBC-CNR), 00015 Monterotondo,Italy; Maria Cecilia Hospital, GVM Care & Research, 48033 Cotignola, Italy.
| | - Elena De Falco
- Department of Angio Cardio Neurology, IRCCS Neuromed, 86077 Pozzilli, Italy; Department of Medical Surgical Sciences and Biotechnologies, Sapienza University, 04100 Latina, Italy; CINECA, Super Computing Applications and Innovation Department, 000185 Roma, Italy; Institute of Biochemistry and Cell Biology, National Council of Research (IBBC-CNR), 00015 Monterotondo,Italy; Maria Cecilia Hospital, GVM Care & Research, 48033 Cotignola, Italy
| |
Collapse
|
|
32
|
Wang M, Wu P, Ma J, Ma X, Yang N, Jia S, Yan N. Enhanced prognosis and regional cooperative rescue systems for acute myocardial infarction: insights from chest pain centers in Ningxia, China. Intern Emerg Med 2025:10.1007/s11739-025-03962-y. [PMID: 40392480 DOI: 10.1007/s11739-025-03962-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/24/2025] [Accepted: 04/28/2025] [Indexed: 05/22/2025]
Abstract
Chest Pain Centers (CPC) demonstrated improved outcomes for patients with acute myocardial infarction (AMI) globally. However, the long-term impact of CPC establishment in economically developing areas, such as Ningxia, China, remains unclear. This study aimed to assess the long-term prognosis and efficacy of collaborative regional rescue systems centered on CPC for ST-segment elevation myocardial infarction (STEMI) patients in Ningxia. This retrospective cohort study analyzed 5344 STEMI patients from the Ningxia Myocardial Infarction Registry (2014-2019). Based on CPC establishment, patients were segregated into two groups: pre-CPC (n = 2141) and post-CPC (n = 3203). Kaplan-Meier survival analysis and Cox proportional hazards models were employed to compare the groups and evaluate long-term outcomes, including mortality and major adverse cardiovascular and cerebrovascular events (MACCEs). A total of 5344 acute STEMI patients were included, with 2141 (40.06%) in the pre-CPC group and 3203 (59.94%) in the post-CPC group. In comparison to the pre-CPC group, the post-CPC group exhibited lower all-cause mortality rates at 30 days (4.53% vs. 6.68%, p = 0.001), 1 year (6.24% vs. 9.11%, p = 0.001), and 3 years (8.55% vs. 11.86%, p < 0.001). Additionally, the post-CPC group showed decreased rates of MACCEs at 30 days (7.90% vs. 10.00%, p = 0.008) and 3 years (18.86% vs. 23.12%, p < 0.001). Kaplan-Meier survival analysis yielded similar results. After adjusting for confounding factors using COX multivariable regression, the CPC establishment was found to be a protective factor for all-cause mortality and MACCEs within 30 days (MACCEs: HR = 0.72, 95%CI 0.59-0.88, p = 0.005; all-cause mortality: HR = 0.59, 95%CI 0.46-0.77, p < 0.001), 1 year (MACCEs events: HR = 0.80, 95%CI 0.68-0.94, p = 0.006; all-cause mortality: HR = 0.59, 95%CI 0.44-0.69, p < 0.001), and 3 years (MACCEs: HR = 0.71, 95%CI 0.62-0.81, p < 0.001; all-cause mortality: HR = 0.55, 95%CI 0.46-0.67, p < 0.001). The establishment of Chest Pain Centers and implementation of regional cooperative rescue systems significantly improved the long-term prognosis of STEMI patients in Ningxia. These findings underscore the importance of developing CPC in underdeveloped regions to enhance cardiovascular emergency care and reduce mortality and morbidity associated with acute myocardial infarction.
Collapse
Affiliation(s)
- Mohan Wang
- The First Clinical College of Ningxia Medical University, Yinchuan, 750004, China
| | - Peng Wu
- The First Clinical College of Ningxia Medical University, Yinchuan, 750004, China
| | - Juan Ma
- Heart Centre and Department of Cardiovascular Diseases, General Hospital of Ningxia Medical University, Yinchuan, 750004, China
| | - Xueping Ma
- Heart Centre and Department of Cardiovascular Diseases, General Hospital of Ningxia Medical University, Yinchuan, 750004, China
- Institute of Medical Sciences, General Hospital of Ningxia Medical University, Yinchuan, 750004, China
- National Health Commission Key Laboratory of Metabolic Cardiovascular Diseases Research, Ningxia Medical University, Yinchuan, 750004, China
| | - Na Yang
- The First Clinical College of Ningxia Medical University, Yinchuan, 750004, China
| | - Shaobin Jia
- Heart Centre and Department of Cardiovascular Diseases, General Hospital of Ningxia Medical University, Yinchuan, 750004, China.
- Institute of Medical Sciences, General Hospital of Ningxia Medical University, Yinchuan, 750004, China.
- National Health Commission Key Laboratory of Metabolic Cardiovascular Diseases Research, Ningxia Medical University, Yinchuan, 750004, China.
- Ningxia Key Laboratory of Vascular Injury and Repair Research, Ningxia Medical University, Yinchuan, 750004, China.
| | - Ning Yan
- Heart Centre and Department of Cardiovascular Diseases, General Hospital of Ningxia Medical University, Yinchuan, 750004, China.
- Institute of Medical Sciences, General Hospital of Ningxia Medical University, Yinchuan, 750004, China.
- National Health Commission Key Laboratory of Metabolic Cardiovascular Diseases Research, Ningxia Medical University, Yinchuan, 750004, China.
| |
Collapse
|
|
33
|
Zeng P, Song R, Chen S, Li X, Li H, Chen Y, Gong Z, Cai G, Lin Y, Shi M, Huang K, Chen Z. Expert-guided StyleGAN2 image generation elevates AI diagnostic accuracy for maxillary sinus lesions. COMMUNICATIONS MEDICINE 2025; 5:185. [PMID: 40394291 PMCID: PMC12092618 DOI: 10.1038/s43856-025-00907-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2024] [Accepted: 05/12/2025] [Indexed: 05/22/2025] Open
Abstract
BACKGROUND The progress of artificial intelligence (AI) research in dental medicine is hindered by data acquisition challenges and imbalanced distributions. These problems are especially apparent when planning to develop AI-based diagnostic or analytic tools for various lesions, such as maxillary sinus lesions (MSL) including mucosal thickening and polypoid lesions. Traditional unsupervised generative models struggle to simultaneously control the image realism, diversity, and lesion-type specificity. This study establishes an expert-guided framework to overcome these limitations to elevate AI-based diagnostic accuracy. METHODS A StyleGAN2 framework was developed for generating clinically relevant MSL images (such as mucosal thickening and polypoid lesion) under expert control. The generated images were then integrated into training datasets to evaluate their effect on ResNet50's diagnostic performance. RESULTS Here we show: 1) Both lesion subtypes achieve satisfactory fidelity metrics, with structural similarity indices (SSIM > 0.996) and maximum mean discrepancy values (MMD < 0.032), and clinical validation scores close to those of real images; 2) Integrating baseline datasets with synthetic images significantly enhances diagnostic accuracy for both internal and external test sets, particularly improving area under the precision-recall curve (AUPRC) by approximately 8% and 14% for mucosal thickening and polypoid lesions in the internal test set, respectively. CONCLUSIONS The StyleGAN2-based image generation tool effectively addressed data scarcity and imbalance through high-quality MSL image synthesis, consequently boosting diagnostic model performance. This work not only facilitates AI-assisted preoperative assessment for maxillary sinus lift procedures but also establishes a methodological framework for overcoming data limitations in medical image analysis.
Collapse
Affiliation(s)
- Peisheng Zeng
- Hospital of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University and Guangdong Provincial Key Laboratory of Stomatology, Guangzhou, Guangdong, China
| | - Rihui Song
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Shijie Chen
- Hospital of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University and Guangdong Provincial Key Laboratory of Stomatology, Guangzhou, Guangdong, China
| | - Xiaohang Li
- School of Mechanical and Automation Engineering, Wuyi University, Jiangmen, Guangdong, China
| | - Haopeng Li
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Yue Chen
- School of Information Technology, Guangdong Industry Polytechnic University, Foshan, Guangdong, China
| | - Zhuohong Gong
- Hospital of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University and Guangdong Provincial Key Laboratory of Stomatology, Guangzhou, Guangdong, China
| | - Gengbin Cai
- Hospital of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University and Guangdong Provincial Key Laboratory of Stomatology, Guangzhou, Guangdong, China
| | - Yixiong Lin
- Hospital of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University and Guangdong Provincial Key Laboratory of Stomatology, Guangzhou, Guangdong, China
| | - Mengru Shi
- Hospital of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University and Guangdong Provincial Key Laboratory of Stomatology, Guangzhou, Guangdong, China.
| | - Kai Huang
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China.
| | - Zetao Chen
- Hospital of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University and Guangdong Provincial Key Laboratory of Stomatology, Guangzhou, Guangdong, China.
| |
Collapse
|
|
34
|
Federico L, Fusaro DD, Coppola GC, Gregori M, Durante S. Application of ChatGPT 4.0 in radiological dose management: Perceptions of radiographers with varying expertise. Radiography (Lond) 2025; 31:102972. [PMID: 40398374 DOI: 10.1016/j.radi.2025.102972] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2025] [Revised: 03/19/2025] [Accepted: 04/28/2025] [Indexed: 05/23/2025]
Abstract
INTRODUCTION Conversational Artificial Intelligence (CAI) is transforming healthcare by introducing innovative tools for decision support and training. ChatGPT 4.0, an advanced generative language model, represents a promising resource for radiographers, particularly in complex areas such as Interventional Radiology (IR). This study evaluates the utility of ChatGPT 4.0 in supporting radiographers with varying levels of experience in radiological dose management. METHODS A questionnaire consisting of 12 questions was developed, divided into three levels of difficulty (basic, intermediate, and advanced) relating to dose management in IR. The responses generated by ChatGPT 4.0 were evaluated by six radiographers divided into two groups: experts (more than five years of experience) and non-experienced (with experience in general radiology but no direct involvement in IR), according to three criteria: clarity, accuracy, and reliability, using a five-point Likert scale. Data were analyzed using the U test, Wilcoxon test, and ANOVA to identify differences between the groups. RESULTS The Mann-Whitney U test showed general agreement between the groups, with only one question approaching statistical significance (p = 0.059). The Wilcoxon test showed no significant differences for individual questions (p > 0.05). ANOVA showed significant differences in clarity (p < 0.05) and accuracy (p < 0.05), whereas differences in reliability were less pronounced. CONCLUSION ChatGPT 4.0 proves to be an effective tool for supporting non-experienced radiographers, facilitating learning, and reducing professional anxiety. However, greater technical sophistication is required to meet the needs of experts, that expressed higher expectations for clarity and accuracy. IMPLICATIONS FOR PRACTICE Integrating CAI into radiography can enhance continuous education and optimize clinical practices, supporting both the professional development of radiographers and operational safety. Future adaptations and updates could make such tools more useful for advanced tasks.
Collapse
Affiliation(s)
- L Federico
- Department of Radiology, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138, Bologna, Italy; Alma Mater Studiorum, University of Bologna, 40138, Bologna, Italy; Italian Association of Interventional Radiographers (AITRI), Via S. Gregorio, 53, Milan 20124, Italy.
| | - D D Fusaro
- Alma Mater Studiorum, University of Bologna, 40138, Bologna, Italy
| | - G C Coppola
- Institute of Cardiology, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138, Bologna, Italy; Italian Association of Interventional Radiographers (AITRI), Via S. Gregorio, 53, Milan 20124, Italy
| | - M Gregori
- Alma Mater Studiorum, University of Bologna, 40138, Bologna, Italy; Institute of Cardiology, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138, Bologna, Italy
| | - S Durante
- Alma Mater Studiorum, University of Bologna, 40138, Bologna, Italy; Department of Healthcare Professions, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138, Bologna, Italy; Italian Association of Interventional Radiographers (AITRI), Via S. Gregorio, 53, Milan 20124, Italy
| |
Collapse
|
|
35
|
Fuchs B, Heesen P. Data-Driven Defragmentation: Achieving Value-Based Sarcoma and Rare Cancer Care Through Integrated Care Pathway Mapping. J Pers Med 2025; 15:203. [PMID: 40423074 DOI: 10.3390/jpm15050203] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2025] [Revised: 05/07/2025] [Accepted: 05/08/2025] [Indexed: 05/28/2025] Open
Abstract
Sarcomas, a rare and complex group of cancers, require multidisciplinary care across multiple healthcare settings, often leading to delays, redundant testing, and fragmented data. This fragmented care landscape obstructs the implementation of Value-Based Healthcare (VBHC), where care efficiency is tied to measurable patient outcomes.ShapeHub, an interoperable digital platform, aims to streamline sarcoma care by centralizing patient data across providers, akin to a logistics system tracking an item through each stage of delivery. ShapeHub integrates diagnostics, treatment records, and specialist consultations into a unified dataset accessible to all care providers, enabling timely decision-making and reducing diagnostic delays. In a case study within the Swiss Sarcoma Network, ShapeHub has shown substantial impact, improving diagnostic pathways, reducing unplanned surgeries, and optimizing radiotherapy protocols. Through AI-driven natural language processing, Fast Healthcare Interoperability Resources, and Health Information Exchanges, HIEs, the platform transforms unstructured records into real-time, actionable insights, enhancing multidisciplinary collaboration and clinical outcomes. By identifying redundancies, ShapeHub also contributes to cost efficiency, benchmarking treatment costs across institutions and optimizing care pathways. This data-driven approach creates a foundation for precision medicine applications, including digital twin technology, to predict treatment responses and personalize care plans. ShapeHub offers a scalable model for managing rare cancers and complex diseases, harmonizing care pathways, improving precision oncology, and transforming VBHC into a reality. This article outlines the potential of ShapeHub to overcome fragmented data barriers and improve patient-centered care.
Collapse
Affiliation(s)
- Bruno Fuchs
- Sarcoma Center, Department of Orthopaedics and Trauma, LUKS University Hospital, 6000 Lucerne, Switzerland
- IPU, Department of Orthopaedics and Trauma, LUKS University Hospital, 6000 Lucerne, Switzerland
- Faculty of Health Sciences and Medicine, University of Lucerne, 6005 Lucerne, Switzerland
- Sarkomzentrum KSW, Klinik für Orthopädie und Traumatologie, Kantonsspital Winterthur, 8400 Winterthur, Switzerland
| | - Philip Heesen
- Medical Faculty, University of Zurich, 8032 Zurich, Switzerland
| |
Collapse
|
|
36
|
Pariso P, Picariello M, Marino A. AI integration in energy management: enhancing efficiency in Italian hospitals. HEALTH ECONOMICS REVIEW 2025; 15:40. [PMID: 40388050 PMCID: PMC12087131 DOI: 10.1186/s13561-025-00638-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/30/2024] [Accepted: 05/05/2025] [Indexed: 05/20/2025]
Abstract
BACKGROUND In the rapidly evolving healthcare landscape, artificial intelligence (AI) is revolutionizing hospital operations by enhancing operational efficiency and patient care. This study focuses on the integration of AI in energy management within Italian hospitals and the role of energy managers. METHODS A comprehensive questionnaire was developed to understand current practices, challenges, and opportunities in AI adoption within hospital energy management. The study targeted regions in Italy with the highest concentration of hospital energy managers. A quantitative approach was employed, and the collected data were statistically analysed for reliability and validity using SPSS. RESULTS The analysis revealed significant benefits of integrating AI in energy management, including optimized energy consumption, predictive maintenance, and greater sustainability. Energy managers' roles are evolving to leverage AI technologies effectively, ensuring compliance with energy regulations and promoting eco-friendly practices. CONCLUSIONS This research underscores AI's transformative potential in creating smarter, greener, and more efficient hospital environments. The findings highlight the importance of adopting AI-driven energy management solutions to enhance hospital efficiency. Future trends indicate further advancements in AI applications, necessitating ongoing adaptation and training for energy managers to exploit these technologies fully.
Collapse
Affiliation(s)
- Paolo Pariso
- Università Degli Studi Della Campania, L. Vanvitelli "- Dipartimento di Ingegneria, Via Roma, 29, Aversa (CE), Italy.
| | - Michele Picariello
- Università Degli Studi Della Campania, L. Vanvitelli "- Dipartimento di Ingegneria, Via Roma, 29, Aversa (CE), Italy
| | - Alfonso Marino
- Università Degli Studi Della Campania, L. Vanvitelli "- Dipartimento di Ingegneria, Via Roma, 29, Aversa (CE), Italy
| |
Collapse
|
|
37
|
Karabuğa B, Karaçin C, Büyükkör M, Bayram D, Aydemir E, Kaya OB, Yılmaz ME, Çamöz ES, Ergün Y. The Role of Artificial Intelligence (ChatGPT-4o) in Supporting Tumor Board Decisions. J Clin Med 2025; 14:3535. [PMID: 40429531 DOI: 10.3390/jcm14103535] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2025] [Revised: 05/09/2025] [Accepted: 05/16/2025] [Indexed: 05/29/2025] Open
Abstract
Background/Objectives: Artificial intelligence (AI) has emerged as a promising field in the era of personalized oncology due to its potential to save time and workforce while serving as a supportive tool in patient management decisions. Although several studies in the literature have explored the integration of AI into oncology practice across different tumor types, available data remain limited. In our study, we aimed to evaluate the role of AI in the management of complex cancer cases by comparing the decisions of an in-house tumor board and ChatGPT-4o for patients with various tumor types. Methods: A total of 102 patients with diverse cancer types were included. Treatment and follow-up decisions proposed by both the tumor board and ChatGPT-4o were independently evaluated by two medical oncologists using a 5-point Likert scale. Results: Analysis of agreement levels showed high inter-rater reliability (κ = 0.722, p < 0.001 for tumor board decisions; κ = 0.794, p < 0.001 for ChatGPT decisions). However, concordance between the tumor board and ChatGPT was low, as reflected in the assessments of both raters (Rater 1: κ = 0.211, p = 0.003; Rater 2: κ = 0.376, p < 0.001). Both raters more frequently agreed with the tumor board decisions, and a statistically significant difference between tumor board and AI decisions was observed for both (Rater 1: Z = +4.548, p < 0.001; Rater 2: Z = +3.990, p < 0.001). Conclusions: These findings suggest that AI, in its current form, is not yet capable of functioning as a standalone decision-maker in the management of challenging oncology cases. Clinical experience and expert judgment remain the most critical factors in guiding patient care.
Collapse
Affiliation(s)
- Berkan Karabuğa
- Department of Medical Oncology, Dr. Abdurrahman Yurtaslan Ankara Oncology Research and Training Hospital, 06200 Ankara, Turkey
| | - Cengiz Karaçin
- Department of Medical Oncology, Dr. Abdurrahman Yurtaslan Ankara Oncology Research and Training Hospital, 06200 Ankara, Turkey
| | - Mustafa Büyükkör
- Department of Medical Oncology, Dr. Abdurrahman Yurtaslan Ankara Oncology Research and Training Hospital, 06200 Ankara, Turkey
| | - Doğan Bayram
- Department of Medical Oncology, Gülhane Research and Training Hospital, 06010 Ankara, Turkey
| | - Ergin Aydemir
- Department of Medical Oncology, Dr. Abdurrahman Yurtaslan Ankara Oncology Research and Training Hospital, 06200 Ankara, Turkey
| | - Osman Bilge Kaya
- Department of Medical Oncology, Dr. Abdurrahman Yurtaslan Ankara Oncology Research and Training Hospital, 06200 Ankara, Turkey
| | - Mehmet Emin Yılmaz
- Department of Medical Oncology, Dr. Abdurrahman Yurtaslan Ankara Oncology Research and Training Hospital, 06200 Ankara, Turkey
| | - Elif Sertesen Çamöz
- Department of Medical Oncology, Dr. Abdurrahman Yurtaslan Ankara Oncology Research and Training Hospital, 06200 Ankara, Turkey
| | - Yakup Ergün
- Department of Medical Oncology, Bower Hospital, 21100 Diyarbakır, Turkey
| |
Collapse
|
|
38
|
Amer H, Flanagan KL, Kampan NC, Itsiopoulos C, Scott CL, Kartikasari AER, Plebanski M. Interleukin-6 Is a Crucial Factor in Shaping the Inflammatory Tumor Microenvironment in Ovarian Cancer and Determining Its Hot or Cold Nature with Diagnostic and Prognostic Utilities. Cancers (Basel) 2025; 17:1691. [PMID: 40427188 DOI: 10.3390/cancers17101691] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2025] [Revised: 05/05/2025] [Accepted: 05/09/2025] [Indexed: 05/29/2025] Open
Abstract
Ovarian cancer (OC) remains the leading cause of cancer-related deaths among women, often diagnosed at advanced stages due to the lack of effective early diagnostic procedures. To reduce the high mortality rates in OC, reliable biomarkers are urgently needed, especially to detect OC at its earliest stage, predict specific drug responses, and monitor patients. The cytokine interleukin-6 (IL6) is associated with low survival rates, treatment resistance, and recurrence. In this review, we summarize the role of IL6 in inflammation and how IL6 contributes to ovarian tumorigenesis within the tumor microenvironment, influencing whether the tumor is subsequently classified as "hot" or "cold". We further dissect the molecular and cellular mechanisms through which IL6 production and downstream signaling are regulated, to enhance our understanding of its involvement in OC development, as well as OC resistance to treatment. We highlight the potential of IL6 to be used as a reliable diagnostic biomarker to help detect OC at its earliest stage, and as a part of predictive and prognostic signatures to improve OC management. We further discuss ways to leverage artificial intelligence and machine learning to integrate IL6 into diverse biomarker-based strategies.
Collapse
Affiliation(s)
- Hina Amer
- School of Health and Biomedical Sciences, RMIT University, Bundoora, VIC 3082, Australia
| | - Katie L Flanagan
- School of Health and Biomedical Sciences, RMIT University, Bundoora, VIC 3082, Australia
- School of Medicine and Health Sciences, University of Tasmania, Launceston, TAS 7250, Australia
- Tasmanian Vaccine Trial Centre, Clifford Craig Foundation, Launceston General Hospital, Launceston, TAS 7250, Australia
| | - Nirmala C Kampan
- Department of Obstetrics and Gynecology, Faculty of Medicine, Universiti Kebangsaan Malaysia, Kuala Lumpur 56000, Malaysia
| | - Catherine Itsiopoulos
- School of Health and Biomedical Sciences, RMIT University, Bundoora, VIC 3082, Australia
| | - Clare L Scott
- The Walter and Eliza Hall Institute of Medical Research, Parkville, VIC 3052, Australia
- Faculty of Medicine, Dentistry, and Health Sciences, The University of Melbourne, Parkville, VIC 3052, Australia
- The Royal Women's Hospital, Parkville, VIC 3052, Australia
| | | | - Magdalena Plebanski
- School of Health and Biomedical Sciences, RMIT University, Bundoora, VIC 3082, Australia
| |
Collapse
|
|
39
|
S Woods S, M Greene S, Adams L, Cordovano G, F Hudson M. From E-Patients to AI Patients: The Tidal Wave Empowering Patients, Redefining Clinical Relationships, and Transforming Care. J Particip Med 2025; 17:e75794. [PMID: 40378413 PMCID: PMC12101788 DOI: 10.2196/75794] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2025] [Accepted: 04/22/2025] [Indexed: 05/18/2025] Open
Abstract
Unlabelled Artificial intelligence (AI) and large language models offer significant potential to enhance many aspects of daily life. Patients and caregivers are increasingly using AI for their own knowledge and to address personal challenges. The growth of AI has been extraordinary; however, the field is only beginning to explore its intersection with participatory medicine. For many years, the Journal of Participatory Medicine has published insights on tech-enabled patient empowerment and strategies to enhance patient-clinician relationships. This theme issue, Patient and Consumer Use of AI for Health, will explore the use of AI for health from the perspective of patients and the public.
Collapse
Affiliation(s)
- Susan S Woods
- Fork Food Lab, 95 Darling Ave, South Portland, ME, 04106, United States
| | - Sarah M Greene
- National Academy of Medicine, Washington, DC, United States
| | - Laura Adams
- National Academy of Medicine, Washington, DC, United States
| | | | | |
Collapse
|
|
40
|
Ta’an W, Damrah S, Al-Hammouri MM, Williams B. Professional identity and its relationships with AI readiness and interprofessional collaboration. PLoS One 2025; 20:e0322794. [PMID: 40378129 PMCID: PMC12083793 DOI: 10.1371/journal.pone.0322794] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2024] [Accepted: 03/27/2025] [Indexed: 05/18/2025] Open
Abstract
BACKGROUND In contemporary healthcare practices, the convergence of Artificial Intelligence (AI) and interprofessional collaboration represents a transformative era marked by unprecedented opportunities and challenges. The introduction of AI technologies is assumed to lead to changes in the nature of interprofessional collaboration that require revisiting the already established professional identity; however, research is lacking in the area. OBJECTIVE To examine professional identity and its relationships with AI readiness domains and interprofessional collaboration components. METHODS A multisite cross-sectional research design was used to recruit 512 participants from different healthcare professions in Jordan between November 14th, 2023, and February 13th, 2024. The Medical Artificial Intelligence Readiness Scale and the Readiness for Interprofessional Learning Scale were used in data collection. Data analysis included descriptive, correlation, and comparative analyses. RESULTS Professional identity significantly and positively correlated with artificial intelligence readiness total and subscale scores with ρ ranging from 0.37 to 0.47 (p < .01). In addition, professional identity significantly correlated with interprofessional teamwork and collaboration (ρ=0.79, p < .01) and the roles and responsibilities components of interprofessional collaboration (ρ=0.37, p < .01). Professional identity was significantly higher among male participants and participants with experience of five years or higher. CONCLUSION The study sets the grounding roles to develop the healthcare workforce's professional identity within the dynamic healthcare environment in the age of artificial intelligence and interprofessional collaboration. The study highlights areas of development for healthcare managers and practitioners, such as AI interprofessional collaboration-based training, targeting both artificial intelligence domains and interprofessional collaboration components while preserving a positive professional identity.
Collapse
Affiliation(s)
- Wafa’a Ta’an
- Community and Mental Health Nursing Department, Faculty of Nursing, Jordan University of Science and Technology, Irbid, Jordan
| | - Sadeq Damrah
- Department of Mathematics and Physics, College of Engineering, Australian University, Safat, Kuwait
| | - Mohammed M. Al-Hammouri
- Community and Mental Health Nursing Department, Faculty of Nursing, Jordan University of Science and Technology, Irbid, Jordan
| | - Brett Williams
- Department of Paramedicine, Monash University, Clayton, Victoria, Australia
| |
Collapse
|
|
41
|
Wang HN, An JH, Wang FQ, Hu WQ, Zong L. Predicting gastric cancer survival using machine learning: A systematic review. World J Gastrointest Oncol 2025; 17:103804. [DOI: 10.4251/wjgo.v17.i5.103804] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/03/2024] [Revised: 02/20/2025] [Accepted: 02/26/2025] [Indexed: 05/15/2025] Open
Abstract
BACKGROUND Gastric cancer (GC) has a poor prognosis, and the accurate prediction of patient survival remains a significant challenge in oncology. Machine learning (ML) has emerged as a promising tool for survival prediction, though concerns regarding model interpretability, reliance on retrospective data, and variability in performance persist.
AIM To evaluate ML applications in predicting GC survival and to highlight key limitations in current methods.
METHODS A comprehensive search of PubMed and Web of Science in November 2024 identified 16 relevant studies published after 2019. The most frequently used ML models were deep learning (37.5%), random forests (37.5%), support vector machines (31.25%), and ensemble methods (18.75%). The dataset sizes varied from 134 to 14177 patients, with nine studies incorporating external validation.
RESULTS The reported area under the curve values were 0.669–0.980 for overall survival, 0.920–0.960 for cancer-specific survival, and 0.710–0.856 for disease-free survival. These results highlight the potential of ML-based models to improve clinical practice by enabling personalized treatment planning and risk stratification.
CONCLUSION Despite challenges concerning retrospective studies and a lack of interpretability, ML models show promise; prospective trials and multidimensional data integration are recommended for improving their clinical applicability.
Collapse
Affiliation(s)
- Hong-Niu Wang
- Department of Gastrointestinal Surgery, Changzhi People’s Hospital, The Affiliated Hospital of Changzhi Medical College, Changzhi 046000, Shanxi Province, China
- Graduate School of Medicine, Changzhi Medical College, Changzhi 046000, Shanxi Province, China
| | - Jia-Hao An
- Department of Graduate School of Medicine, Changzhi Medical College, Changzhi 046000, Shanxi Province, China
| | - Fu-Qiang Wang
- Department of Gastrointestinal Surgery, Changzhi People’s Hospital, The Affiliated Hospital of Changzhi Medical College, Changzhi 046000, Shanxi Province, China
| | - Wen-Qing Hu
- Department of Gastrointestinal Surgery, Changzhi People’s Hospital, The Affiliated Hospital of Changzhi Medical College, Changzhi 046000, Shanxi Province, China
| | - Liang Zong
- Department of Gastrointestinal Surgery, Changzhi People’s Hospital, The Affiliated Hospital of Changzhi Medical College, Changzhi 046000, Shanxi Province, China
| |
Collapse
|
|
42
|
Oei CW, Ng EYK, Ng MHS, Chan YM, Subbhuraam V, Chan LG, Acharya UR. Automated Risk Prediction of Post-Stroke Adverse Mental Outcomes Using Deep Learning Methods and Sequential Data. Bioengineering (Basel) 2025; 12:517. [PMID: 40428136 DOI: 10.3390/bioengineering12050517] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2025] [Revised: 04/25/2025] [Accepted: 05/13/2025] [Indexed: 05/29/2025] Open
Abstract
Depression and anxiety are common comorbidities of stroke. Research has shown that about 30% of stroke survivors develop depression and about 20% develop anxiety. Stroke survivors with such adverse mental outcomes are often attributed to poorer health outcomes, such as higher mortality rates. The objective of this study is to use deep learning (DL) methods to predict the risk of a stroke survivor experiencing post-stroke depression and/or post-stroke anxiety, which is collectively known as post-stroke adverse mental outcomes (PSAMO). This study studied 179 patients with stroke, who were further classified into PSAMO versus no PSAMO group based on the results of validated depression and anxiety questionnaires, which are the industry's gold standard. This study collected demographic and sociological data, quality of life scores, stroke-related information, medical and medication history, and comorbidities. In addition, sequential data such as daily lab results taken seven consecutive days after admission are also collected. The combination of using DL algorithms, such as multi-layer perceptron (MLP) and long short-term memory (LSTM), which can process complex patterns in the data, and the inclusion of new data types, such as sequential data, helped to improve model performance. Accurate prediction of PSAMO helps clinicians make early intervention care plans and potentially reduce the incidence of PSAMO.
Collapse
Affiliation(s)
- Chien Wei Oei
- Management Information Department, Office of Clinical Epidemiology, Analytics and kNowledge (OCEAN), Tan Tock Seng Hospital, Singapore 308433, Singapore
- School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore 639798, Singapore
| | - Eddie Yin Kwee Ng
- School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore 639798, Singapore
| | - Matthew Hok Shan Ng
- Rehabilitation Research Institute of Singapore, Nanyang Technological University, Singapore 308232, Singapore
| | - Yam Meng Chan
- Department of General Surgery, Vascular Surgery Service, Tan Tock Seng Hospital, Singapore 308433, Singapore
| | | | - Lai Gwen Chan
- Department of Psychiatry, Tan Tock Seng Hospital, Singapore 308433, Singapore
- Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore 308232, Singapore
| | - U Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Brisbane, QLD 4305, Australia
| |
Collapse
|
|
43
|
Wang J, You W, He W, Yan J, Zhang Y. Artificial Intelligence-Guided Cancer Engineering for Tumor Normalization Executed by Tumor Lysosomal-Triggered Supramolecular Chiral Peptide. ACS NANO 2025; 19:17273-17286. [PMID: 40302018 PMCID: PMC12080376 DOI: 10.1021/acsnano.4c14264] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/10/2024] [Revised: 04/04/2025] [Accepted: 04/22/2025] [Indexed: 05/01/2025]
Abstract
Cancer engineering for tumor normalization offers a promising therapeutic strategy to reverse malignant cells and their supportive tumor microenvironment into a more benign state. Herein, an artificial intelligence (AI) approach was developed using mRNA data from patients with lung adenocarcinoma to facilitate the identification of aberrant signaling pathways, specifically focusing on PD-L1, Wnt, and macropinocytosis. Targeting these characteristics, we have developed a supramolecular construct called cancer corrector (CCtor) with the aim of harnessing the enhanced macropinocytosis observed in cancer cells. Undergoing cleavage and subsequent drug release triggered by the lysosomal protease in cancer cells, CCtor rectifies the aberrant hyperactivity of both Wnt and PD-L1 signaling pathways. This dual-action therapeutic strategy not only restores normalcy to cancer cells but also exerts an exceptionally robust therapeutic effect. This work exemplifies a future direction for cancer therapies by combining AI with molecular engineering to significantly improve patient outcomes through tumor behavior normalization.
Collapse
Affiliation(s)
- Jingmei Wang
- Department
of Infectious Diseases and Hepatology, The
Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an 710004, P. R. China
- Institute
for Stem Cell & Regenerative Medicine, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an 710004, P. R. China
| | - Weiming You
- Department
of Infectious Diseases and Hepatology, The
Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an 710004, P. R. China
- State
Key Laboratory of Shaanxi for Natural Medicines Research and Engineering, Xi’an 710061, P. R. China
| | - Wangxiao He
- Department
of Medical Oncology and Department of Talent Highland, The First Affiliated Hospital of Xi’an Jiaotong
University, Xi’an 710061, P. R. China
| | - Jin Yan
- Department
of Infectious Diseases and Hepatology, The
Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an 710004, P. R. China
- National
& Local Joint Engineering Research Center of Biodiagnosis and
Biotherapy, The Second Affiliated Hospital
of Xi’an Jiaotong University, Xi’an 710004, P. R. China
| | - Yanmin Zhang
- Department
of Infectious Diseases and Hepatology, The
Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an 710004, P. R. China
- State
Key Laboratory of Shaanxi for Natural Medicines Research and Engineering, Xi’an 710061, P. R. China
- School of
Pharmacy, Health Science Center, Xi’an
Jiaotong University, Xi’an 710061, P. R. China
| |
Collapse
|
|
44
|
Orhan K, Costa ALF, de Castro Lopes SLP. Closing Editorial: Advancements in Artificial Intelligence for Dentomaxillofacial Radiology-Current Trends and Future Directions. Diagnostics (Basel) 2025; 15:1222. [PMID: 40428215 DOI: 10.3390/diagnostics15101222] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2025] [Accepted: 05/12/2025] [Indexed: 05/29/2025] Open
Abstract
Artificial intelligence (AI) continues to redefine diagnostic approaches across medical disciplines, and its impact on dentomaxillofacial radiology has increased exponentially in recent years [...].
Collapse
Affiliation(s)
- Kaan Orhan
- Department of Dentomaxillofacial Radiology, Faculty of Dentistry, Ankara University, Ankara 06560, Turkey
- Department of Dental and Maxillofacial Radiodiagnostics, Medical University of Lublin, 20-059 Lublin, Poland
- Medical Design Application and Research Center (MEDITAM), Ankara University, Ankara 06000, Turkey
| | - Andre Luiz Ferreira Costa
- Postgraduate Program in Dentistry, Cruzeiro do Sul University (UNICSUL), São Paulo 08060-070, SP, Brazil
| | - Sérgio Lúcio Pereira de Castro Lopes
- Department of Diagnosis and Surgery, São José dos Campos School of Dentistry, São Paulo State University (UNESP), São José dos Campos 12245-000, SP, Brazil
| |
Collapse
|
|
45
|
Freitas LRSD, Freitas JAOD, Penna GO, Duarte EC. Evaluating Machine Learning Models for Predicting Late Leprosy Diagnosis by Physical Disability Grade in Brazil (2018-2022). Trop Med Infect Dis 2025; 10:131. [PMID: 40423361 DOI: 10.3390/tropicalmed10050131] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2025] [Revised: 03/14/2025] [Accepted: 03/18/2025] [Indexed: 05/28/2025] Open
Abstract
The severity of physical disability at leprosy diagnosis reflects the timeliness of case detection and the effectiveness of disease surveillance. This study evaluates machine learning models to predict factors associated with late leprosy diagnosis-defined as grade 2 physical disability (G2D)-in Brazil from 2018 to 2022. Using an observational cross-sectional design, we analyzed data from the Notifiable Diseases Information System and trained four machine learning models: Random Forest, LightGBM, CatBoost, XGBoost, and an Ensemble model. Model performance was assessed through accuracy, area under the receiver operating characteristic curve (AUC-ROC), recall, precision, F1 score, specificity, and Matthew's correlation coefficient (MCC). An increasing trend in G2D prevalence was observed, averaging 11.6% over the study period and rising to 13.1% in 2022. The Ensemble model and LightGBM demonstrated the highest predictive performance, particularly in the north and northeast regions (accuracy: 0.85, AUC-ROC: 0.93, recall: 0.90, F1 score: 0.83, MCC: 0.70), with similar results in other regions. Key predictors of G2D included the number of nerves affected, clinical form, education level, and case detection mode. These findings underscore the potential of machine learning to enhance early detection strategies and reduce the burden of disability in leprosy, particularly in regions with persistent health disparities.
Collapse
Affiliation(s)
| | | | - Gerson Oliveira Penna
- Escola de Governo Fiocruz Brasília, Fundação Oswaldo Cruz, Brasília 70904-130, Brazil
- Núcleo de Medicina Tropical, Universidade de Brasília, Brasília 70910-900, Brazil
| | | |
Collapse
|
|
46
|
Paton C. Understanding research on artificial intelligence in healthcare. BMJ MEDICINE 2025; 4:e001614. [PMID: 40395650 PMCID: PMC12090526 DOI: 10.1136/bmjmed-2025-001614] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Received: 04/16/2025] [Accepted: 04/24/2025] [Indexed: 05/22/2025]
Affiliation(s)
- Chris Paton
- Liggins Institute, University of Auckland, Auckland, New Zealand
| |
Collapse
|
|
47
|
Zudin BA, Timoshevsky AA, Derbenev DP. [The prognostication of need in IT-specialists in health care]. PROBLEMY SOTSIAL'NOI GIGIENY, ZDRAVOOKHRANENIIA I ISTORII MEDITSINY 2025; 33:1609. [PMID: 40349246 DOI: 10.32687/0869-866x-2025-33-2-288-294] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/10/2025] [Accepted: 05/10/2025] [Indexed: 05/14/2025]
Abstract
In conditions of global digitization of health care, characterized by widespread implementation of information technologies into medical practice, the problem of prognostication of need for qualified IT specialists capable to ensure effective functioning and development of digital infrastructure of health care becomes especially relevant. The article considers modern trends in health care development, emphasizing increased role of IT specialists in providing high-quality and efficient medical care, and also analyzes main areas of activity of IT specialists in health care. The analysis demonstrated that, despite active development of digital health care in Russia, the country to a certain extent lags behind leaders in this field in terms of saturation of health care with qualified IT specialists. The study presents prognostication of need in IT specialists in health care in 2025-2026, characterized by dominance of software developers, as well as increasing of need for data analysts, cybersecurity specialists and DevOps engineers. To meet increasing need for IT specialists in health care in Russia, it is necessary to improve education system, to develop professional retraining programs and to organize favorable conditions for work of IT specialists in health care, including competitive salaries and opportunities for professional growth.
Collapse
Affiliation(s)
- B A Zudin
- The State Budget Institution "The Research Institute of Health Care Organization and Medical Management" of the Moscow Health Care Department, 115184, Moscow, Russia
| | - A A Timoshevsky
- The State Budget Institution "The Research Institute of Health Care Organization and Medical Management" of the Moscow Health Care Department, 115184, Moscow, Russia
| | - D P Derbenev
- The State Budget Institution "The Research Institute of Health Care Organization and Medical Management" of the Moscow Health Care Department, 115184, Moscow, Russia
| |
Collapse
|
|
48
|
He Q, Wang H, Zhang Y, Chen A, Fu Y, Xue G, Liu K, Huang S, Xu Y, Yu B. Two-dimensional materials based two-transistor-two-resistor synaptic kernel for efficient neuromorphic computing. Nat Commun 2025; 16:4340. [PMID: 40346103 PMCID: PMC12064777 DOI: 10.1038/s41467-025-59815-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2024] [Accepted: 05/06/2025] [Indexed: 05/11/2025] Open
Abstract
Neuromorphic computing based on two-dimensional materials represents a promising hardware approach for data-intensive applications. Central to this new paradigm are memristive devices, which serve as the essential components in synaptic kernels. However, large-scale implementation of synaptic matrix using two-dimensional materials is hindered by challenges related to random component variation and array-level integration. Here, we develop a 16 × 16 computing kernel based on two-transistor-two-resistor unit with three-dimensional heterogeneous integration compatibility to boost energy efficiency and computing performance. We demonstrate the 4-bit weight characteristics of artificial synapses with low stochasticity. The synaptic array demonstration validates the practicality of utilizing emerging two-dimensional materials for monolithic three-dimensional heterogeneous integration. Additionally, we introduce the Gaussian noise quantization weight-training scheme alongside the ConvMixer convolution architecture to achieve image dataset identification with high accuracy. Our findings indicate that the synaptic kernel can significantly improve detection accuracy and inference performance on the CIFAR-10 dataset.
Collapse
Affiliation(s)
- Qian He
- College of Integrated Circuits, Zhejiang University, Hangzhou, Zhejiang, China
| | - Hailiang Wang
- College of Integrated Circuits, Zhejiang University, Hangzhou, Zhejiang, China
| | - Yishu Zhang
- College of Integrated Circuits, Zhejiang University, Hangzhou, Zhejiang, China.
- ZJU-Hangzhou Global Scientific and Technological Innovation Center, Hangzhou, Zhejiang, China.
| | - Anzhe Chen
- College of Integrated Circuits, Zhejiang University, Hangzhou, Zhejiang, China
| | - Yu Fu
- Department of Physics, Key Laboratory of Quantum State Construction and Manipulation (Ministry of Education), Renmin University of China, Beijing, China
| | - Guodong Xue
- State Key Laboratory for Mesoscopic Physics, Frontiers Science Center for Nano-optoelectronics, School of Physics, Peking University, Beijing, China
| | - Kaihui Liu
- State Key Laboratory for Mesoscopic Physics, Frontiers Science Center for Nano-optoelectronics, School of Physics, Peking University, Beijing, China
| | - Shiman Huang
- College of Integrated Circuits, Zhejiang University, Hangzhou, Zhejiang, China
| | - Yang Xu
- College of Integrated Circuits, Zhejiang University, Hangzhou, Zhejiang, China
| | - Bin Yu
- College of Integrated Circuits, Zhejiang University, Hangzhou, Zhejiang, China.
| |
Collapse
|
|
49
|
Duckworth C, Burns D, Fernandez CL, Wright M, Leyland R, Stammers M, George M, Boniface M. Predicting onward care needs at admission to reduce discharge delay using explainable machine learning. Sci Rep 2025; 15:16033. [PMID: 40341633 PMCID: PMC12062306 DOI: 10.1038/s41598-025-00825-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2024] [Accepted: 04/30/2025] [Indexed: 05/10/2025] Open
Abstract
Early identification of patients who require onward referral to social care can prevent delays to discharge from hospital. We introduce an explainable machine learning (ML) model to identify potential social care needs at the first point of admission. This model was trained using routinely collected data on patient admissions, hospital spells and discharge at a large tertiary hospital in the UK between 2017 and 2023. The model performance (one-vs-rest AUROC = 0.915 [0.907 0.924] (95% confidence interval), is comparable to clinician's predictions of discharge care needs, despite working with only a subset of the information available to the clinician. We find that ML and clinicians perform better for identifying different types of care needs, highlighting the added value of a potential system supporting decision making. We also demonstrate the ability for ML to provide automated initial discharge need assessments, in the instance where initial clinical assessment is delayed and provide reasoning for the decision. Finally, we demonstrate that combining clinician and machine predictions, in a hybrid model, provides even more accurate early predictions of onward social care requirements (OVR AUROC = 0.936 [0.928 0.943]) and demonstrates the potential for human-in-the-loop decision support systems in clinical practice.
Collapse
Affiliation(s)
- Chris Duckworth
- IT Innovation Centre, Digital Health and Biomedical Engineering, University of Southampton, Southampton, UK.
| | - Dan Burns
- IT Innovation Centre, Digital Health and Biomedical Engineering, University of Southampton, Southampton, UK
| | | | - Mark Wright
- University Hospital Southampton Foundation Trust, Southampton, UK
| | - Rachael Leyland
- University Hospital Southampton Foundation Trust, Southampton, UK
| | - Matthew Stammers
- Southampton Emerging Therapies and Technologies Centre, University Hospital Southampton Foundation Trust, Southampton, UK
| | - Michael George
- Southampton Emerging Therapies and Technologies Centre, University Hospital Southampton Foundation Trust, Southampton, UK
| | - Michael Boniface
- IT Innovation Centre, Digital Health and Biomedical Engineering, University of Southampton, Southampton, UK
| |
Collapse
|
|
50
|
El Arab RA, Alkhunaizi M, Alhashem YN, Al Khatib A, Bubsheet M, Hassanein S. Artificial intelligence in vaccine research and development: an umbrella review. Front Immunol 2025; 16:1567116. [PMID: 40406131 PMCID: PMC12095282 DOI: 10.3389/fimmu.2025.1567116] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2025] [Accepted: 04/07/2025] [Indexed: 05/26/2025] Open
Abstract
Background The rapid development of COVID-19 vaccines highlighted the transformative potential of artificial intelligence (AI) in modern vaccinology, accelerating timelines from years to months. Nevertheless, the specific roles and effectiveness of AI in accelerating and enhancing vaccine research, development, distribution, and acceptance remain dispersed across various reviews, underscoring the need for a unified synthesis. Methods We conducted an umbrella review to consolidate evidence on AI's contributions to vaccine discovery, optimization, clinical testing, supply-chain logistics, and public acceptance. Five databases were systematically searched up to January 2025 for systematic, scoping, narrative, and rapid reviews, as well as meta-analyses explicitly focusing on AI in vaccine contexts. Quality assessments were performed using the ROBIS and AMSTAR 2 tools to evaluate risk of bias and methodological rigor. Results Among the 27 reviews, traditional machine learning approaches-random forests, support vector machines, gradient boosting, and logistic regression-dominated tasks from antigen discovery and epitope prediction to supply‑chain optimization. Deep learning architectures, including convolutional and recurrent neural networks, generative adversarial networks, and variational autoencoders, proved instrumental in multiepitope vaccine design and adaptive clinical trial simulations. AI‑driven multi‑omic integration accelerated epitope mapping, shrinking discovery timelines by months, while predictive analytics optimized manufacturing workflows and supply‑chain operations (including temperature‑controlled, "cold‑chain" logistics). Sentiment analysis and conversational AI tools demonstrated promising capabilities for real‑time monitoring of public attitudes and tailored communication to address vaccine hesitancy. Nonetheless, persistent challenges emerged-data heterogeneity, algorithmic bias, limited regulatory frameworks, and ethical concerns over transparency and equity. Discussion and implications These findings illustrate AI's transformative potential across the vaccine lifecycle but underscore that translating promise into practice demands five targeted action areas: robust data governance and multi‑omics consortia to harmonize and share high‑quality datasets; comprehensive regulatory and ethical frameworks featuring transparent model explainability, standardized performance metrics, and interdisciplinary ethics committees for ongoing oversight; the adoption of adaptive trial designs and manufacturing simulations that enable real‑time safety monitoring and in silico process modeling; AI‑enhanced public engagement strategies-such as routinely audited chatbots, real‑time sentiment dashboards, and culturally tailored messaging-to mitigate vaccine hesitancy; and a concerted focus on global equity and pandemic preparedness through capacity building, digital infrastructure expansion, routine bias audits, and sustained funding in low‑resource settings. Conclusion This umbrella review confirms AI's pivotal role in accelerating vaccine development, enhancing efficacy and safety, and bolstering public acceptance. Realizing these benefits requires not only investments in infrastructure and stakeholder engagement but also transparent model documentation, interdisciplinary ethics oversight, and routine algorithmic bias audits. Moreover, bridging the gap from in silico promise to real‑world impact demands large‑scale validation studies and methods that can accommodate heterogeneous evidence, ensuring AI‑driven innovations deliver equitable global health outcomes and reinforce pandemic preparedness.
Collapse
Affiliation(s)
| | - May Alkhunaizi
- Almoosa College of Health Sciences, Alhasa, Saudi Arabia
- Pediatric Department, Almoosa Specialist Hospital, Alhasa, Saudi Arabia
| | | | | | | | - Salwa Hassanein
- Almoosa College of Health Sciences, Alhasa, Saudi Arabia
- Department of Community Health Nursing, Cairo University, Cairo, Egypt
| |
Collapse
|