Artificial intelligence (AI) text-to-image generators have a propensity to reflect stereotypes. This study investigates the perception of race and gender of AI-generated portraits of otolaryngologists, evaluating their accuracy against workforce demographics and whether they amplify existing social biases.

Three text-to-image platforms (DALL-E3, Runway, Midjourney) were prompted to generate portrait photos of otolaryngologists based on 29 categories, including personality traits, fellowship, and academic rank. 580 portrait photos were made per platform. Two reviewers characterized the gender and race of the 1740 portraits. Statistical analysis compared the demographics of AI outputs to existing demographic information.

Of the 1740 AI-generated otolaryngologists generated, 88% of images were labeled as White, 4% Black, 6% Asian, 2% Indeterminate/Other race, 88% male, and 12% female. Across academic rank, the representation of White individuals was 97% (department chairs), 90% (program directors), 93% (professors), and 78% (residents). Male representation ranged from 90% (department chairs), 75% (program directors), 100% (professors), and 87% (residents). Runway produced more images of male (89% vs. 88% vs. 85%, p = 0.043) and White (92% vs. 88% vs. 80%, p < 0.001) otolaryngologists than DALL-E3 and Midjourney, respectively.

Text-to-image platforms demonstrated racial and gender biases, with notable differences compared to actual demographics. These platforms often underrepresented females and racial minority groups and overrepresented White males. These disparities underscore the need for the awareness of biases in AI, especially as these tools become more integrated into patient-facing platforms. Left unchecked, these biases risk marginalizing minority populations and reinforcing societal stereotypes.

4.

Nuclear magnetic resonance (NMR) spectroscopy is crucial for elucidating molecular structures, but NMR data extraction remains largely manual and time-consuming. We developed NMRExtractor, a locally deployable tool using a fine-tuned large language model, to address this challenge. By processing 5 734 869 open-source scientific publications, we created NMRBank, a dataset containing 225 809 entries with compound IUPAC names, NMR conditions, 1H and 13C NMR chemical shifts, data confidence levels, and reference information. Our analysis reveals that NMRBank's chemical space significantly surpasses existing public NMR datasets. The extraction process is highly scalable, allowing automatic processing of new research papers and continuous updates to NMRBank. This approach not only expands the available open NMR data space but also provides a foundation for AI-based NMR predictions and related chemical research. By automating data extraction and creating a comprehensive, regularly updated NMR database, NMRExtractor and NMRBank address the scarcity of publicly available experimental NMR data, potentially accelerating progress in various fields of chemical research.

There is a growing concern about artificial intelligence (AI) applications in healthcare that can disadvantage already under-represented and marginalised groups (eg, based on gender or race).

Our objectives are to canvas the range of strategies stakeholders endorse in attempting to mitigate algorithmic bias, and to consider the ethical question of responsibility for algorithmic bias.

The study involves in-depth, semistructured interviews with healthcare workers, screening programme managers, consumer health representatives, regulators, data scientists and developers.

Findings reveal considerable divergent views on three key issues. First, views on whether bias is a problem in healthcare AI varied, with most participants agreeing bias is a problem (which we call the bias-critical view), a small number believing the opposite (the bias-denial view), and some arguing that the benefits of AI outweigh any harms or wrongs arising from the bias problem (the bias-apologist view). Second, there was a disagreement on the strategies to mitigate bias, and who is responsible for such strategies. Finally, there were divergent views on whether to include or exclude sociocultural identifiers (eg, race, ethnicity or gender-diverse identities) in the development of AI as a way to mitigate bias.

Based on the views of participants, we set out responses that stakeholders might pursue, including greater interdisciplinary collaboration, tailored stakeholder engagement activities, empirical studies to understand algorithmic bias and strategies to modify dominant approaches in AI development such as the use of participatory methods, and increased diversity and inclusion in research teams and research participant recruitment and selection.

Nanopsychiatry, operating at the nanoscale, leverages engineered nanomaterials and nanodevices to revolutionize psychiatric diagnostics and therapeutics. This review systematically analyzes the implementation of advanced nanomaterials, including quantum dots, carbon nanotubes (CNTs), and metal nanoparticles, in neural interface systems for neurotransmitter detection and drug monitoring. We evaluate the integration of nanoscale architectures in developing high-specificity biosensors for key neurotransmitters such as dopamine, serotonin, and glutamate. The review critically examines recent advances in nanomaterial-based electrochemical and optical sensing platforms, incorporating modified electrodes with conducting polymers, metallic nanocomposites, and functionalized graphene derivatives. These systems demonstrate enhanced sensitivity and selective multi-analyte detection capabilities in complex biological matrices. We analyze how these nanosensors complement conventional neuroimaging techniques, enabling monitoring of neurochemical dynamics in psychiatric conditions with improved spatial and temporal resolution. Furthermore, we assess the development of flexible, nanomaterial-enhanced wearable biosensors incorporating screen-printed electrodes and microfluidic systems. These devices achieve continuous monitoring of neurological biomarkers, facilitating quantitative assessment of psychiatric symptoms and treatment responses. The integration of machine learning algorithms with these nanoscale sensing platforms enables data processing and pattern recognition for personalized psychiatric interventions.

Information overload in electronic health records requires effective solutions to alleviate clinicians' administrative tasks. Automatically summarizing clinical text has gained significant attention with the rise of large language models. While individual studies show optimism, a structured overview of the research landscape is lacking.

This study aims to present the current state of the art on clinical text summarization using large language models, evaluate the level of evidence in existing research and assess the applicability of performance findings in clinical settings.

This scoping review complied with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. Literature published between January 1, 2019, and June 18, 2024, was identified from 5 databases: PubMed, Embase, Web of Science, IEEE Xplore, and ACM Digital Library. Studies were excluded if they did not describe transformer-based models, did not focus on clinical text summarization, did not engage with free-text data, were not original research, were nonretrievable, were not peer-reviewed, or were not in English, French, Spanish, or German. Data related to study context and characteristics, scope of research, and evaluation methodologies were systematically collected and analyzed by 3 authors independently.

A total of 30 original studies were included in the analysis. All used observational retrospective designs, mainly using real patient data (n=28, 93%). The research landscape demonstrated a narrow research focus, often centered on summarizing radiology reports (n=17, 57%), primarily involving data from the intensive care unit (n=15, 50%) of US-based institutions (n=19, 73%), in English (n=26, 87%). This focus aligned with the frequent reliance on the open-source Medical Information Mart for Intensive Care dataset (n=15, 50%). Summarization methodologies predominantly involved abstractive approaches (n=17, 57%) on single-document inputs (n=4, 13%) with unstructured data (n=13, 43%), yet reporting on methodological details remained inconsistent across studies. Model selection involved both open-source models (n=26, 87%) and proprietary models (n=7, 23%). Evaluation frameworks were highly heterogeneous. All studies conducted internal validation, but external validation (n=2, 7%), failure analysis (n=6, 20%), and patient safety risks analysis (n=1, 3%) were infrequent, and none reported bias assessment. Most studies used both automated metrics and human evaluation (n=16, 53%), while 10 (33%) used only automated metrics, and 4 (13%) only human evaluation.

Key barriers hinder the translation of current research into trustworthy, clinically valid applications. Current research remains exploratory and limited in scope, with many applications yet to be explored. Performance assessments often lack reliability, and clinical impact evaluations are insufficient raising concerns about model utility, safety, fairness, and data privacy. Advancing the field requires more robust evaluation frameworks, a broader research scope, and a stronger focus on real-world applicability.

Gingivitis and periodontitis, are widespread conditions with diverse influence on oral and systemic health. Traditional diagnostic methods in periodontology often rely on subjective clinical assessments, which can lead to variability and inconsistencies in care. Imbibing artificial intelligence (AI) facilitates a significant solution by enhancing precision metrics, treatment planning, and personalized care. Studies published between 2018 and 2024 was conducted to evaluate AI applications in periodontal maintenance. Databases such as PubMed, Cochrane, Web of Science and Scopus were searched using keywords like "artificial intelligence," "machine learning," and "periodontitis." Studies employing AI for diagnosis, prognosis, or periodontal maintenance using clinical or radiographic data were included. Deep learning algorithms such as convolutional neural networks (CNNs) and segmentation techniques were analyzed for their diagnostic accuracy. AI demonstrated superior performance in detecting periodontal conditions, with accuracy rates surpassing 90% in some studies. Advanced models, such as Multi-Label U-Net, exhibited high precision in radiographic analyses, outperforming traditional methods. Additionally, AI facilitated predictive analytics for disease progression and personalized treatment strategies. AI has transformed periodontal care, offering accuracy, personalized care, and efficient workflow integration. Addressing challenges like standardization and ethical concerns is critical for its broader adoption.

This survey paper explores the transformative role of Machine Learning (ML) and Artificial Intelligence (AI) in Cardiopulmonary Resuscitation (CPR), marking a paradigm shift from conventional, manually driven resuscitation practices to intelligent, data-driven interventions. It examines the evolution of CPR through the lens of predictive modeling, AI-enhanced devices, and real-time decision-making tools that collectively aim to improve resuscitation outcomes and survival rates. Unlike prior surveys that either focus solely on traditional CPR methods or offer general insights into ML applications in healthcare, this work provides a novel interdisciplinary synthesis tailored specifically to the domain of CPR. It presents a comprehensive taxonomy that classifies ML techniques into four key CPR-related tasks: rhythm analysis, outcome prediction, non-invasive blood pressure and chest compression modeling, and real-time detection of pulse and Return of Spontaneous Circulation (ROSC). The paper critically evaluates emerging ML approaches-including Reinforcement Learning (RL) and transformer-based models-while also addressing real-world implementation barriers such as model interpretability, data limitations, and deployment in high-stakes clinical settings. Furthermore, it highlights the role of eXplainable AI (XAI) in fostering clinical trust and adoption. By bridging the gap between resuscitation science and advanced ML techniques, this survey establishes a structured foundation for future research and practical innovation in ML-enhanced CPR. It offers clear insights, identifies unexplored opportunities, and sets a forward-looking research agenda identifying emerging trends and practical implementation challenges aiming to improve both the reliability and effectiveness of CPR in real-world emergencies.

 Even though several initiatives have been undertaken in different locations worldwide to collect clinical data in homeopathy, it is important to further investigate these aspects in the context of health care in India.

 The study aimed to gather and analyze patients' clinical data and to derive insights into homeopathic treatment using an internet-based software program for data storage, retrieval and repertorization.

 A multi-center observational study was conducted across 14 homeopathy outpatient clinics in India that are affiliated with the Central Council for Research in Homoeopathy (CCRH). Patient symptoms and demographic details were documented anonymously, and prescriptions were guided by repertorial suggestions from the Vithoulkas Compass software. During follow-up visits, treatment outcome was also recorded using an online assessment form. A retrospective analysis of data on patients' demographics, follow-up visits, morbidity (International Classification of Diseases 11th Revision), rubrics used, prescribed medicines and the level of improvement was achieved using Microsoft Excel-generated pivot tables.

 Throughout the study duration of one year a total of 2,811 patients attended the 14 outpatient clinics, of whom 2,468 were new patients with a total of 2,172 initial homeopathic prescription entries. Across the study, there were 3,491 prescriptions and 1,628 follow-up consultations for 868 follow-up patients, all of which data were thoroughly analyzed. The highest frequency of patients was in the 20-49 age group, and a higher proportion of the patients overall was female. Musculoskeletal, dermatological and respiratory complaints were the most frequently reported. The rubrics "Desire for sweets" and "Desire for spices" emerged as the most commonly used in the repertorizations. Further, Sulphur stood out as the most commonly prescribed medicine overall. With homeopathic treatment, some degree of clinical improvement was reported in 86% of the follow-up cases.

 Homeopathy is prescribed in CCRH outpatient clinics for a wide range of ailments in people across India, with at least some clinical improvement noted in a high proportion of those patients. The large-scale systematic data collection in these clinics has provided clear insights into the use and clinical value of homeopathy in India, with the potential to build a substantive nationwide data inventory over time.

This study explores uses of artificial intelligence (AI) in health professions education for nonpsychomotor skills training at undergraduate, postgraduate, and continuing health professions education levels for education program development, delivery, and evaluation.

This scoping review was conducted in 5 stages: (1) planning and research, (2) search strategy, (3) screening and selection, (4) review and recording data, and (5) synthesis. Seven bibliographic databases were searched using terms for artificial intelligence and continuing health professional education to capture articles that used AI for the purposes of nonpsychomotor skills training for health professions education and involved health care professionals and/or trainees. Databases were searched for articles published from January 1, 2001, to March 26, 2024. The original searches were performed on July 26, 2021, and again on March 26, 2024. Two reviewers independently screened, reviewed, and extracted data. Data extraction was performed using Kern's 6-step curriculum development framework to guide analysis.

In total, 9,914 studies related to AI in health professions education for nonpsychomotor skills training were screened. Of these, 103 studies were identified that met the inclusion criteria. Of these 103 studies, 52 (50%) were cohort studies. The most common learner population was health care professional students (67 studies [65%]). Most studies (76 [74%]) were set in nonclinical settings. Sixty-eight studies (66%) fit under step 6 of Kern's criteria (evaluation and assessment), illustrating that AI is predominantly being used for the purposes of evaluation and assessment of learners and programs.

Most studies in the literature illustrate that AI is being applied in a nonpsychomotor context to evaluate health professional education programs and assess learners. Additional opportunities to use AI in curriculum design and implementation could include identification of learning needs for training, personalizing learning with AI principles, and evaluating health care professional education programs.

Neurosymbolic artificial intelligence (AI) is an increasingly active area of research that combines symbolic reasoning methods with deep learning to leverage their complementary benefits. As knowledge graphs (KGs) are becoming a popular way to represent heterogeneous and multirelational data, methods for reasoning on graph structures have attempted to follow this neurosymbolic paradigm. Traditionally, such approaches have utilized either rule-based inference or generated representative numerical embeddings from which patterns could be extracted. However, several recent studies have attempted to bridge this dichotomy to generate models that facilitate interpretability, maintain competitive performance, and integrate expert knowledge. Therefore, we survey methods that perform neurosymbolic reasoning tasks on KGs and propose a novel taxonomy by which we can classify them. Specifically, we propose three major categories: 1) logically informed embedding approaches; 2) embedding approaches with logical constraints; and 3) rule-learning approaches. Alongside the taxonomy, we provide a tabular overview of the approaches and links to their source code, if available, for more direct comparison. Finally, we discuss the unique characteristics and limitations of these methods and then propose several prospective directions toward which this field of research could evolve.

Ten percent of adults in the United States have a diagnosis of diabetes and up to a third of these individuals will develop a diabetic foot ulcer (DFU) in their lifetime. Of those who develop a DFU, a fifth will ultimately require amputation with a mortality rate of up to 70% within five years. The human suffering, economic burden, and disproportionate impact of diabetes on communities of color has led to increasing interest in the use of computer vision (CV) and machine learning (ML) techniques to aid the detection, characterization, monitoring, and even prediction of DFUs. Remote monitoring and automated classification are expected to revolutionize wound care by allowing patients to self-monitor their wound pathology, assist in the remote triaging of patients by clinicians, and allow for more immediate interventions when necessary. This scoping review provides an overview of applicable CV and ML techniques. This includes automated CV methods developed for remote assessment of wound photographs, as well as predictive ML algorithms that leverage heterogeneous data streams. We discuss the benefits of such applications and the role they may play in diabetic foot care moving forward. We highlight both the need for, and possibilities of, computational sensing systems to improve diabetic foot care and bring greater knowledge to patients in need.

Artificial intelligence (AI) is transforming healthcare by enhancing diagnostics, personalizing medicine and improving surgical precision. However, its integration into healthcare systems raises significant ethical and legal challenges. This review explores key ethical principles-autonomy, beneficence, non-maleficence, justice, transparency and accountability-highlighting their relevance in AI-driven decision-making. Legal challenges, including data privacy and security, liability for AI errors, regulatory approval processes, intellectual property and cross-border regulations, are also addressed. As AI systems become increasingly autonomous, questions of responsibility and fairness must be carefully considered, particularly with the potential for biased algorithms to amplify healthcare disparities. This paper underscores the importance of multi-disciplinary collaboration between technologists, healthcare providers, legal experts and policymakers to create adaptive, globally harmonized frameworks. Public engagement is emphasized as essential for fostering trust and ensuring ethical AI adoption. With AI technologies advancing rapidly, a flexible regulatory environment that evolves with innovation is critical. Aligning AI innovation with ethical and legal imperatives will lead to a safer, more equitable healthcare system for all.

Artificial Intelligence (AI) is transforming speech-language pathology (SLP) and dysphagia management, offering innovative solutions for assessment, diagnosis, and rehabilitation. This narrative review examines AI applications in these fields from 2014 to 2024, with particular focus on implementation challenges in Latin America. We analyze key AI technologies-including deep learning, machine learning algorithms, and natural language processing-that have demonstrated high accuracy in detecting voice disorders, analyzing swallowing function, and supporting personalized rehabilitation. The review identifies three primary domains of AI application: diagnostic tools with improved sensitivity for speech-language disorders, rehabilitation technologies that enable customized therapy, and telehealth platforms that expand access to specialized care in underserved regions. However, significant barriers persist, particularly in Latin America, where limited infrastructure, insufficient linguistic adaptation, and scarce regional datasets hamper widespread implementation. Our pilot study evaluating commercially available large language models for rehabilitation planning demonstrates their potential utility in generating structured therapy activities, especially in resource-constrained settings. While AI shows promise in enhancing clinical workflows and expanding service delivery, the evidence suggests that current applications remain predominantly focused on diagnosis rather than integrated rehabilitation. This review highlights the need for culturally and linguistically adapted AI models, expanded regional research collaborations, and regulatory frameworks that ensure ethical AI integration into SLP and dysphagia care, positioning these technologies as complementary tools that enhance rather than replace clinical expertise.

In recent years, Artificial Intelligence (AI) is transforming healthcare systems globally and improved the efficiency of its delivery. Countries like Saudi Arabia are facing unique adoption challenges in their public healthcare, these challenges are specific to AI literacy, understanding and effective usage of AI technologies. In addition, cultural, regulatory and operational barriers increase the complication of integrating AI literacy into public healthcare operations. In spite of its critical contribution in enabling sustainable healthcare development, limited studies have addressed these adoption challenges. Our study explores the AI literacy adoption barriers in context to Saudi Arabian public healthcare sector, focusing on its relevance for advancing healthcare operations and achieving Sustainable Development Goals (SDGs). The research aims to identifying and addressing the adoption challenges of Artificial Intelligence literacy within the public healthcare in Saudi Arabia. The research aims to enhance the understanding of AI literacy, its necessity for enhancing healthcare operations, and the specific hurdles that impede its successful AI adoption in Saudi Arabia's public healthcare ecosystem. The research employs a qualitative analysis using the T-O-E framework to explore the adoption challenges of AI literacy. Additionally, the Best-Worse Method (BWM) is applied to evaluate the adoption challenges to AI literacy adoption across various operational levels within Saudi Arabia's public healthcare supply chain. The study uncovers substantial adoption challenges at operational, tactical, and strategic level, including institutional readiness, data privacy, and compliance with regulatory frameworks. These challenges complicate the adoption of AI literacy in the Saudi public healthcare supply chains. The research offers critical insights into the various issues affecting the promotion of AI literacy in Saudi Arabia's public healthcare sector. This evidence-based study provides essential commendations for healthcare professionals and policymakers to effectively address the identified challenges, nurturing an environment beneficial to the integration of AI literacy and advancing the goals of sustainable healthcare development.

Background: Digital health interventions have the potential to improve health at a large scale globally by improving access to healthcare services and health-related information, but they tend to benefit more affluent and privileged groups more than those less privileged. Methods: In this narrative review, we describe how this 'digital health divide' can manifest across three different levels reflecting inequalities in access, skills and benefits or outcomes (i.e. the first, second, and tertiary digital divide). We also discuss four key causes of this digital divide: (i)) digital health literacy as a fundamental determinant; (ii) other personal, social, community, and societal level determinants; (iii) how technology and intervention development contribute to; and (iv) how current research practice exacerbates the digital health divide by developing a biased evidence base. Finally, we formulate implications for research, policy, and practice. Results: Specific recommendations for research include to keep digital health interventions and measurement instruments up to date with fastpaced technological changes, and to involve diverse populations in digital intervention development and evaluation research. For policy and practice, examples of recommendations are to insist on inclusive and accessible design of health technology and to ensure support for digital health intervention enactment prioritises those most vulnerable to the digital divide. Conclusion: We conclude by highlighting the importance of addressing the digital health divide to ensure that as digital technologies' inevitable presence grows, it does not leave those who could benefit most from innovative health technology behind.

Background/Objectives: Diabetes is a common public health disease that affects patients mentally, physically, and economically. It requires lifestyle changes such as blood sugar control and regular contact with healthcare services. Artificial intelligence has developed rapidly in many different areas in recent years, including healthcare and nursing. The aim of this study is to explore how artificial intelligence can be used as a tool for patients with diabetes mellitus. Methods: An integrative literature review design was chosen according to Whittemore and Knafl (2005). Electronic searches in databases were conducted across Pub-Med, CINAHL Complete (EBSCO), and ACM Digital Library until September 2024. A total set of quantitative and qualitative articles (n = 15) was selected and reviewed using a Mixed Method Appraisal Tool. Results: Artificial intelligence is an effective tool for patients with diabetes mellitus, and various models are used. Three themes emerged: artificial intelligence as a tool for blood sugar monitoring for patients with diabetes mellitus, artificial intelligence as a decision support for diabetic wounds and complications, and patients' requests for artificial intelligence capabilities in relation to tools. Artificial intelligence can create better conditions for patient self-care. Conclusions: Artificial intelligence is a valuable tool for patients with diabetes mellitus and enables the district nurse to focus more on person-centered care. The technology facilitates the patient's blood sugar monitoring. However, more research is needed to ensure the safety of AI technology, the protection of patient privacy, and clarification of laws and regulations within diabetes care.

Self-reported pain scores are often used for pain assessments and require effective communication. On the other hand, observer-based assessments are resource-intensive and require training. We developed an automated system to assess pain intensity in adult patients based on changes in facial expression. We recruited adult patients undergoing surgery or interventional pain procedures in two public healthcare institutions in Singapore. The patients' facial expressions were videotaped from a frontal view with varying body poses using a customized mobile application. The collected videos were trimmed into multiple 1 s clips and categorized into three levels of pain: no pain, mild pain, or significant pain. A total of 468 facial key points were extracted from each video frame. A customized spatial temporal attention long short-term memory (STA-LSTM) deep learning network was trained and validated using the extracted keypoints to detect pain levels by analyzing facial expressions in both the spatial and temporal domains. Model performance was evaluated using accuracy, sensitivity, recall, and F1-score. Two hundred patients were recruited, with 2008 videos collected for further clipping into 10,274 1 s clips. Videos from 160 patients (7599 clips) were used for STA-LSTM training, while the remaining 40 patients' videos (2675 clips) were set aside for validation. By differentiating the polychromous levels of pain (no pain versus mild pain versus significant pain requiring clinical intervention), we reported the optimal performance of STA-LSTM model, with accuracy, sensitivity, recall, and F1-score all at 0.8660. Our proposed solution has the potential to facilitate objective pain assessment in clinical settings through the developed STA-LSTM model, enabling healthcare professionals and caregivers to perform pain assessments effectively in both inpatient and outpatient settings.

This scoping review aims to identify and summarise artificial intelligence (AI) methods applied to patient-reported outcome measures (PROMs) for prediction of patient outcomes, such as survival, quality of life, or treatment decisions.

AI models have been successfully applied to predict outcomes for patients using mainly clinically focused data. However, systematic guidance for utilising AI and PROMs for patient outcome predictions is lacking. This leads to inconsistency of model development and evaluation, limited practical implications, and poor translation to clinical practice.

This review was conducted across Web of Science, IEEE Xplore, ACM, Digital Library, Cochrane Central Register of Controlled Trials, Medline and Embase databases. Adapted search terms identified published research using AI models with patient-reported data for outcome predictions. Papers using PROMs data as input variables in AI models for prediction of patient outcomes were included.

Three thousand and seventy-seven records were screened, 94 of which were included in the analysis. AI models applied to PROMs data for outcome predictions are most commonly used in orthopaedics and oncology. Poor reporting of model hyperparameters and inconsistent techniques of handling class imbalance and missingness in data were found. The absence of external model validation, participants' ethnicity information and stakeholders involvement was common.

The results highlight inconsistencies in conducting and reporting of AI research involving PROMs in patients' outcomes predictions, which reduces the reproducibility of the studies. Recommendations for external validation and stakeholders' involvement are given to increase the opportunities for applying AI models in clinical practice.

The landscape of early drug discovery is rapidly evolving, fueled by significant advancements in artificial intelligence (AI) and machine learning (ML), which are transforming the way drugs are discovered. As traditional drug discovery faces growing challenges in terms of time, cost, and efficacy, there is a pressing need to integrate these emerging technologies to enhance the discovery process.

In this perspective, the authors explore the role of AI and ML in modern early drug discovery and discuss their application in drug target identification, compound screening, and biomarker discovery. This article is based on a thorough literature search using the PubMed database to identify relevant studies that highlight the use of AI/ML models in computational chemistry, systems biology, and data-driven approaches to drug development. Emphasis is placed on how these technologies address key challenges such as data integration, predictive performance, and cost-efficiency in the drug discovery pipeline.

AI and ML have the potential to revolutionize early drug discovery by improving the accuracy and speed of identifying viable drug candidates. However, successful integration of these technologies requires overcoming challenges related to data quality, model interpretability, and the need for interdisciplinary collaboration.

The aim of this cross-sectional observational analytical study was to assess the accuracy and consistency of responses provided by Google Gemini (GG), a free-access high-performance multimodal large language model, to questions related to the European Society of Endodontology position statement on the management of traumatized permanent teeth (MTPT).

Three academic endodontists developed a set of 99 yes/no questions covering all areas of the MTPT. Nine general dentists and 22 endodontic specialists evaluated these questions for clarity and comprehension through an iterative process. Two academic dental trauma experts categorized the knowledge required to answer each question into three levels. The three academic endodontists submitted the 99 questions to the GG, resulting in 297 responses, which were then assessed for accuracy and consistency. Accuracy was evaluated using the Wald binomial method, while the consistency of GG responses was assessed using the kappa-Fleiss coefficient with a confidence interval of 95%. A 5% significance level chi-squared test was used to evaluate the influence of question level of knowledge on accuracy and consistency.

The responses generated by Gemini showed an overall moderate accuracy of 80.81%, with no significant differences found between the responses of the academic endodontists. Overall, high consistency (95.96%) was demonstrated, with no significant differences between GG responses across the three accounts. The analysis also revealed no correlation between question level of knowledge and accuracy or consistency, with no significant differences.

The results of this study could significantly impact the potential use of Gemini as a free-access source of information for clinicians in the MTPT.

Interest in the potential applications of artificial intelligence in medicine, anesthesiology, and the world at large has never been higher. The Anesthesia Research Council steering committee formed an anesthesiologist artificial intelligence expert workgroup charged with evaluating the current state of artificial intelligence in anesthesiology, providing examples of future artificial intelligence applications and identifying barriers to artificial intelligence progress. The workgroup's findings are summarized here, starting with a brief introduction to artificial intelligence for clinicians, followed by overviews of current and anticipated artificial intelligence-focused research and applications in anesthesiology. Anesthesiology's progress in artificial intelligence is compared to that of other medical specialties, and barriers to artificial intelligence development and implementation in our specialty are discussed. The workgroup's recommendations address stakeholders in policymaking, research, development, implementation, training, and use of artificial intelligence-based tools for perioperative care.

Interest in the potential applications of artificial intelligence in medicine, anesthesiology, and the world at large has never been higher. The Anesthesia Research Council steering committee formed an anesthesiologist artificial intelligence expert workgroup charged with evaluating the current state of artificial intelligence in anesthesiology, providing examples of future artificial intelligence applications and identifying barriers to artificial intelligence progress. The workgroup's findings are summarized here, starting with a brief introduction to artificial intelligence for clinicians, followed by overviews of current and anticipated artificial intelligence-focused research and applications in anesthesiology. Anesthesiology's progress in artificial intelligence is compared to that of other medical specialties, and barriers to artificial intelligence development and implementation in our specialty are discussed. The workgroup's recommendations address stakeholders in policymaking, research, development, implementation, training, and use of artificial intelligence-based tools for perioperative care.

Class imbalances in healthcare data, characterized by a disproportionate number of positive cases compared to negative ones, can lead to biased machine learning models that favor the majority class. Ensuring good performance across all classes is crucial for improving healthcare delivery and patient safety. Traditional oversampling methods like SMOTE and its variants face several limitations: they struggle with capturing complex data distributions, handling heterogeneous data types, and natively supporting multi-class datasets. To address these issues, we propose a deep learning based solution using an Auxiliary-guided Conditional Variational Autoencoder (ACVAE) enhanced with contrastive learning. Additionally, we introduce an ensemble technique where ACVAE creates synthetic positive samples, followed by the use of the Edited Centroid-Displacement Nearest Neighbor (ECDNN) algorithm to reduce the majority class. This combined approach takes advantage of ACVAE's ability to produce diverse oversampled data and ECDNN's skill in handling noise through selective undersampling, leading to a more balanced and informative dataset. Our experiments on 12 different health datasets show the effectiveness of our method. We conduct a thorough evaluation of our approach against traditional oversampling techniques and several benchmark machine learning models. The results demonstrate notable improvements in model performance across various metrics, highlighting the potential of deep learning based synthetic oversampling to address class imbalances in healthcare data.

The STRIDE-HF (Systematic Tool for Risk Identification and Decision-making in Emergency Heart Failure) emergency department (ED) risk tool was previously found to accurately predict the risk of a 30-day serious adverse event (SAE), including 30-day mortality, cardiopulmonary resuscitation, intra-aortic balloon pump insertion, intubation, new dialysis, myocardial infarction, or coronary revascularization.

The aim of this study was to prospectively validate STRIDE-HF across 21 community EDs among patients in the ED with acute heart failure (AHF) from January 1, 2023, to December 31, 2023, and to assess the safety of the real-time use of risk estimates in a 2-ED pilot study.

Model area under the receiver operator curve (AUROC) and area under the precision recall curve (AUPRC), sensitivity, specificity, and positive and negative predictive values and likelihood ratios at key clinical thresholds are reported. In the clinical pilot, the rates of 30-day SAEs among patients who were at lower risk by STRIDE-HF and were discharged after ED or observation care were reported.

There were 13,274 patients in the ED in the prospective validation; the median age was 76 years, 50.8% were female, and 44.5% were non-White; and 11.4%, 24.8%, 31.9%, and 31.9% of patients were at very low, low, moderate, and high risk, respectively. The 30-day SAE rates among very-low-risk and low-risk patients were 3.4% and 6.7%, respectively, and the 30-day mortality rates were <1% and <2%, respectively. STRIDE-HF was highly sensitive among low-risk patients (97.6%; 95% CI: 96.8%-98.2%); AUROC was 0.75 (95% CI: 0.74-0.76), and AUPRC was 0.43 (95% CI: 0.39-0.44). There were 845 patients in the pilot study; among patients classified by STRIDE-HF criteria as being at very low risk who were discharged, none experienced a 30-day SAE.

STRIDE-HF maintained high predictive accuracy for 30-day SAE in prospective validation in this large, diverse, multicenter cohort; the use of risk estimates in real time safely identified low-risk patients appropriate for discharge.

Artificial intelligence (AI) applications are having increasing impacts in the biomedical sciences. Modern AI tools enable uncovering hidden patterns in large datasets, forecasting outcomes, and numerous other applications. Despite the availability and power of these tools, the rapid expansion and complexity of AI applications can be daunting, and there is a conspicuous absence of consensus on their ethical and responsible use. Misapplication of AI can result in invalid, unclear, or biased outcomes, exacerbated by the unfamiliarity of many biomedical researchers with the underlying mathematical and computational principles. To address these challenges, this review and tutorial paper aims to achieve three primary objectives: (1) highlight prevalent data science applications in biomedical research, including data visualization, dimensionality reduction, missing data imputation, and predictive model training and evaluation; (2) provide comprehensible explanations of the mathematical foundations underpinning these methodologies; and (3) guide readers on the effective use and interpretation of software tools for implementing these methods in biomedical contexts. While introductory, this guide covers core principles essential for understanding advanced applications, empowering readers to critically interpret results, assess tools, and explore the potential and limitations of machine learning in their research. Ultimately, this paper serves as a practical foundation for biomedical researchers to confidently navigate the growing intersection of AI and biomedicine.

Artificial intelligence (AI) is increasingly used in healthcare, including dental and periodontal diagnostics, due to its ability to analyze complex datasets with speed and precision. Backgrounds and Objectives: This study aimed to evaluate the reliability of AI-assisted dental-periodontal diagnoses compared to diagnoses made by senior specialists, specialists, and general dentists. Material and Methods: A comparative study was conducted involving 60 practitioners divided into three groups-general dentists, specialists, and senior specialists-along with an AI diagnostic system (Planmeca Romexis 6.4.7.software). Participants evaluated six high-quality panoramic radiographic images representing various dental and periodontal conditions. Diagnoses were compared against a reference "gold standard" validated by a dental imaging expert and senior clinician. A statistical analysis was performed using SPSS 26.0, applying chi-square tests, ANOVA, and Bonferroni correction to ensure robust results. Results: AI's consistency in identifying subtle conditions was comparable to that of senior specialists, while general dentists showed greater variability in their evaluations. The key findings revealed that AI and senior specialists consistently demonstrated the highest performance in detecting attachment loss and alveolar bone loss, with AI achieving a mean score of 6.12 in identifying teeth with attachment loss, compared to 5.43 for senior specialists, 4.58 for specialists, and 3.65 for general dentists. The ANOVA highlighted statistically significant differences between groups, particularly in the detection of attachment loss on the maxillary arch (F = 3.820, p = 0.014). Additionally, AI showed high consistency in detecting alveolar bone loss, with comparable performance to senior specialists. Conclusions: AI systems exhibit significant potential as reliable tools for dental and periodontal assessment, complementing the expertise of human practitioners. However, further validation in clinical settings is necessary to address limitations such as algorithmic bias and atypical cases. AI integration in dentistry can enhance diagnostic precision and patient outcomes while reducing variability in clinical assessments.

Artificial intelligence (AI) has demonstrated remarkable diagnostic accuracy in controlled clinical trials, sometimes rivaling or even surpassing experienced clinicians. However, AI's real-world effectiveness is frequently diminished when applied to diverse clinical settings, owing to methodological shortcomings, limited multicenter studies, and insufficient real-world validations.

This narrative review critically examines the discrepancy between AI's robust performance in clinical trials and its inconsistent real-world implementation. Our goal is to synthesize methodological, ethical, and operational challenges impeding AI integration and propose a comprehensive framework to bridge this gap.

We conducted a thematic synthesis of peer-reviewed studies from the PubMed, IEEE Xplore, and Scopus databases, targeting studies from 2014 to 2024. Included studies addressed diagnostic, therapeutic, or operational AI applications and related implementation challenges in healthcare. Non-peer-reviewed articles and studies without rigorous analysis were excluded.

Our synthesis identified key barriers to AI's real-world deployment, including algorithmic bias from homogeneous datasets, workflow misalignment, increased clinician workload, and ethical concerns surrounding transparency, accountability, and data privacy. Additionally, scalability remains a challenge due to interoperability issues, insufficient methodological rigor, and inconsistent reporting standards. To address these challenges, we introduce the AI Healthcare Integration Framework (AI-HIF), a structured model incorporating theoretical and operational strategies for responsible AI implementation in healthcare.

Translating AI from controlled environments to real-world clinical practice necessitates a multifaceted, interdisciplinary approach. Future research should prioritize large-scale pragmatic trials and observational studies to empirically validate the proposed AI Healthcare Integration Framework (AI-HIF) in diverse, real-world healthcare contexts.

Artificial intelligence (AI) is delivering value across all aspects of clinical practice. However, bias may exacerbate healthcare disparities. This review examines the origins of bias in healthcare AI, strategies for mitigation, and responsibilities of relevant stakeholders towards achieving fair and equitable use. We highlight the importance of systematically identifying bias and engaging relevant mitigation activities throughout the AI model lifecycle, from model conception through to deployment and longitudinal surveillance.

The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. In addition, the field has increasingly prioritized marginal performance gains on a few, narrowly scoped benchmarks over clinical applicability, slowing down meaningful algorithmic progress. This trend often results in excessive fine-tuning of existing methods on selected datasets rather than fostering clinically relevant innovations. In response, this work introduces a comprehensive benchmark for the MedMNIST+ dataset collection, designed to diversify the evaluation landscape across several imaging modalities, anatomical regions, classification tasks and sample sizes. We systematically reassess commonly used Convolutional Neural Networks (CNNs) and Vision Transformer (ViT) architectures across distinct medical datasets, training methodologies, and input resolutions to validate and refine existing assumptions about model effectiveness and development. Our findings suggest that computationally efficient training schemes and modern foundation models offer viable alternatives to costly end-to-end training. Additionally, we observe that higher image resolutions do not consistently improve performance beyond a certain threshold. This highlights the potential benefits of using lower resolutions, particularly in prototyping stages, to reduce computational demands without sacrificing accuracy. Notably, our analysis reaffirms the competitiveness of CNNs compared to ViTs, emphasizing the importance of comprehending the intrinsic capabilities of different architectures. Finally, by establishing a standardized evaluation framework, we aim to enhance transparency, reproducibility, and comparability within the MedMNIST+ dataset collection as well as future research. Code is available at (https://github.com/sdoerrich97/rethinking-model-prototyping-MedMNISTPlus).

Humans continuously face threats from emerging novel pathogens and antimicrobial resistant bacteria or fungi, which requires urgently and efficient solutions. Alternatively, microbes also produce compounds or chemicals highly valuable to humans of which require continuous refinement and improvement of yields. Artificial intelligence (AI) is a promising tool to search for solutions combatting against diseases and facilitating productivity underpinned by robust research providing accurate information. However, the extent of AI credibility is yet to be fully understood. In terms of human bias, AI could arguably act as a means of ensuring scientific objectivity to increase accuracy and precision, however, whether this is possible or not has not been fully discussed. Human bias and error can be introduced at any step of the research process, including conducting experiments and data processing, through to influencing clinical applications. Despite AI's contribution to advancing knowledge, the question remains, is AI able to achieve objectivity in microbiological research? Here, the benefits, drawbacks, and responsibilities of AI utilization in microbiological research and clinical applications were discussed.

This paper introduces the Team Card (TC) as a protocol to address harmful biases in the development of clinical artificial intelligence (AI) systems by emphasizing the often-overlooked role of researchers' positionality. While harmful bias in medical AI, particularly in Clinical Decision Support (CDS) tools, is frequently attributed to issues of data quality, this limited framing neglects how researchers' worldviews-shaped by their training, backgrounds, and experiences-can influence AI design and deployment. These unexamined subjectivities can create epistemic limitations, amplifying biases and increasing the risk of inequitable applications in clinical settings. The TC emphasizes reflexivity-critical self-reflection-as an ethical strategy to identify and address biases stemming from the subjectivity of research teams. By systematically documenting team composition, positionality, and the steps taken to monitor and address unconscious bias, TCs establish a framework for assessing how diversity within teams impacts AI development. Studies across business, science, and organizational contexts demonstrate that diversity improves outcomes, including innovation, decision-making quality, and overall performance. However, epistemic diversity-diverse ways of thinking and problem-solving-must be actively cultivated through intentional, collaborative processes to mitigate bias effectively. By embedding epistemic diversity into research practices, TCs may enhance model performance, improve fairness and offer an empirical basis for evaluating how diversity influences bias mitigation efforts over time. This represents a critical step toward developing inclusive, ethical, and effective AI systems in clinical care. A publicly available prototype presenting our TC is accessible at https://www.teamcard.io/team/demo.

Artificial intelligence (AI) has revolutionized the field of cardiovascular imaging, serving as a unifying force that brings together multiple modalities under a single platform. The utility of noninvasive imaging ranges from diagnostic assessment and guiding interventions to prognostic stratification. Multimodality imaging has demonstrated important potential, particularly in patients with heterogeneous diseases, such as heart failure and atrial fibrillation. Facilitating complex interventional procedures requires accurate image acquisition and interpretation along with precise decision-making. The unique nature of interventional cardiology procedures benefiting from different imaging modalities presents an ideal target for the development of AI-assisted decision-making tools to improve workflow in the catheterization laboratory and personalize the need for transcatheter interventions. This review explores the advancements of AI in noninvasive cardiovascular imaging and interventional cardiology, addressing the clinical use and challenges of current imaging modalities, emerging trends, and promising applications as well as considerations for safe implementation of AI tools in clinical practice. Current practice has moved well beyond the question of whether we should or should not use AI in clinical health care settings. AI, in all its forms, has become deeply embedded in clinical workflows, particularly in cardiovascular imaging and interventional cardiology. It can, in the future, not only add precision and quantification but also serve as a means by which to fuse and link multimodalities together. It is only by understanding how AI techniques work, that the field can be harnessed for the greater good and avoid uninformed bias or misleading diagnoses.

This study systematically explores the ethical and regulatory considerations surrounding the integration of artificial intelligence (AI) and machine learning (ML) in nursing practice, with a focus on patient autonomy, data privacy, algorithmic bias, and accountability.

AI and ML are transforming nursing practice by enhancing clinical decision-making and operational efficiency. However, these technologies present significant ethical challenges related to ensuring patient autonomy, safeguarding data privacy, mitigating algorithmic bias, and ensuring transparency in decision-making processes. Current frameworks are not sufficiently tailored to nursing-specific contexts.

A systematic review was conducted, adhering to PRISMA guidelines. Six major databases were searched for studies published between 2000 and 2024. Seventeen studies met the inclusion criteria and were included in the final analysis.

Five key themes emerged from the review: enhancement of clinical decision-making, promotion of ethical awareness, support for routine nursing tasks, challenges in algorithmic bias, and the importance of public engagement in regulatory frameworks. The review identified critical gaps in nursing-specific ethical guidelines and regulatory oversight for AI integration in practice.

AI technologies offer substantial benefits for nursing, particularly in decision-making and task efficiency. However, these advantages must be balanced against ethical concerns, including the protection of patient rights, algorithmic transparency, and bias mitigation. Current regulatory frameworks require adaptation to meet the ethical needs of nursing.

The findings emphasize the need for the development of nursing-specific ethical guidelines and robust regulatory frameworks to ensure the responsible integration of AI technologies into nursing practice. AI integration must uphold ethical principles while enhancing the quality of care.

With the increasing popularity of medical imaging and its expanding applications, posing significant challenges for radiologists. Radiologists need to spend substantial time and effort to review images and manually writing reports every day. To address these challenges and speed up the process of patient care, researchers have employed deep learning methods to automatically generate medical reports. In recent years, researchers have been increasingly focusing on this task and a large amount of related work has emerged. Although there have been some review articles summarizing the state of the art in this field, their discussions remain relatively limited. Therefore, this paper provides a comprehensive review of the latest advancements in automatic medical report generation, focusing on four key aspects: (1) describing the problem of automatic medical report generation, (2) introducing datasets of different modalities, (3) thoroughly analyzing existing evaluation metrics, (4) classifying existing studies into five categories: retrieval-based, domain knowledge-based, attention-based, reinforcement learning-based, large language models-based, and merged model. In addition, we point out the problems in this field and discuss the directions of future challenges. We hope that this review provides a thorough understanding of automatic medical report generation and encourages the continued development in this area.

Early recognition and treatment of sepsis in the emergency department (ED) is important. Traditional predictive analytics and clinical decision rules lack accuracy in identifying patients with sepsis. Artificial intelligence (AI) is increasingly prevalent in healthcare and offers application potential in the care of patients with sepsis. This review examines the evidence of AI in diagnosing, managing and prognosticating sepsis in the ED.

We performed literature search in PubMed, Embase, Google Scholar and Scopus databases for studies published between 1 January 2010 and 30 June 2024 that evaluated the use of AI in adult patients with sepsis in ED, using the following search terms: ("artificial intelligence" OR "machine learning" OR "neural networks, computer" OR "deep learning" OR "natural language processing"), AND ("sepsis" OR "septic shock", AND "emergency services" OR "emergency department"). Independent searches were conducted in duplicate with discrepancies adjudicated by a third member.

Incorporating multiple variables such as vital signs, free text input, laboratory tests and electrocardiogram was possible with AI compared to traditional models leading to improvement in diagnostic performance. Machine learning (ML) models outperformed traditional scoring tools in both diagnosis and prognosis of sepsis. ML models were able to analyze trends over time and showed utility in predicting mortality, severe sepsis and septic shock. Additionally, real-time ML-assisted alert systems are effective in improving time-to-antibiotic administration and ML algorithms can differentiate sepsis patients into distinct phenotypes to tailor management (especially fluid therapy and critical care interventions), potentially improving outcomes. Existing AI tools for sepsis currently lack generalizability and user acceptance. This is risk of automation bias with loss of clinicians' skills if over-reliance develops.

Overall, AI holds great promise in revolutionizing management of patients with sepsis in the ED as a clinical support tool. However, its application is currently still constrained by inherent limitations. Balanced integration of AI technology with clinician input is essential to harness its full potential and ensure optimal patient outcomes.

Large language models are increasingly evaluated for use in healthcare. However, concerns about their impact on disparities persist. This study reviews current research on demographic biases in large language models to identify prevalent bias types, assess measurement methods, and evaluate mitigation strategies.

We conducted a systematic review, searching publications from January 2018 to July 2024 across five databases. We included peer-reviewed studies evaluating demographic biases in large language models, focusing on gender, race, ethnicity, age, and other factors. Study quality was assessed using the Joanna Briggs Institute Critical Appraisal Tools.

Our review included 24 studies. Of these, 22 (91.7%) identified biases. Gender bias was the most prevalent, reported in 15 of 16 studies (93.7%). Racial or ethnic biases were observed in 10 of 11 studies (90.9%). Only two studies found minimal or no bias in certain contexts. Mitigation strategies mainly included prompt engineering, with varying effectiveness. However, these findings are tempered by a potential publication bias, as studies with negative results are less frequently published.

Biases are observed in large language models across various medical domains. While bias detection is improving, effective mitigation strategies are still developing. As LLMs increasingly influence critical decisions, addressing these biases and their resultant disparities is essential for ensuring fair artificial intelligence systems. Future research should focus on a wider range of demographic factors, intersectional analyses, and non-Western cultural contexts.

Applying machine learning to clinical outcome prediction is challenging due to imbalanced datasets and sensitive tasks that contain rare yet critical outcomes and where equitable treatment across diverse patient groups is essential. Despite attempts, biases in predictions persist, driven by disparities in representation and exacerbated by the scarcity of positive labels, perpetuating health inequities. This paper introduces FairPlay, a synthetic data generation approach leveraging large language models, to address these issues. FairPlay enhances algorithmic performance and reduces bias by creating realistic, anonymous synthetic patient data that improves representation and augments dataset patterns while preserving privacy. Through experiments on multiple datasets, we demonstrate that FairPlay boosts mortality prediction performance across diverse subgroups, achieving up to a 21% improvement in F1 Score without requiring additional data or altering downstream training pipelines. Furthermore, FairPlay consistently reduces subgroup performance gaps, as shown by universal improvements in performance and fairness metrics across four experimental setups.

Artificial intelligence (AI) is not merely a tool for the future of clinical medicine; it is already reshaping the landscape, challenging traditional paradigms, and expanding the horizons of what is achievable in healthcare [...].

Artificial intelligence (AI)-based systems are being rapidly integrated into the fields of health and social care. Although such systems can substantially improve the provision of care, diverse and marginalized populations are often incorrectly or insufficiently represented within these systems. This review aims to assess the influence of AI on health and social care among these populations, particularly with regard to issues related to inclusivity and regulatory concerns.

We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Six leading databases were searched, and 129 articles were selected for this review in line with predefined eligibility criteria.

This research revealed disparities in AI outcomes, accessibility, and representation among diverse groups due to biased data sources and a lack of representation in training datasets, which can potentially exacerbate inequalities in care delivery for marginalized communities.

AI development practices, legal frameworks, and policies must be reformulated to ensure that AI is applied in an equitable manner. A holistic approach must be used to address disparities, enforce effective regulations, safeguard privacy, promote inclusion and equity, and emphasize rigorous validation.