Diabetes mellitus (DM) is a chronic metabolic disorder that poses significant challenges to public health. Among its various complications, diabetic nephropathy (DN) emerges as a critical microvascular complication associated with high mortality rates. Despite the development of diverse therapeutic strategies targeting metabolic improvement, hemodynamic regulation, and fibrosis mitigation, the precise mechanisms responsible for glomerular injury in DN are not yet fully elucidated. To explore these mechanisms, public DN datasets (GSE30528, GSE104948, and GSE96804) were obtained from the GEO database. We merged the GSE30528 and GSE104948 datasets to identify differentially expressed genes (DEGs) between DN and control groups using R software. Weighted gene co-expression network analysis (WGCNA) was subsequently employed to discern genes associated with DN in key modules. We utilized Venny software to pinpoint co-expressed genes shared between DEGs and key module genes. These co-expressed genes underwent gene ontology (GO) and Kyoto encyclopedia of genes and genomes (KEGG) enrichment analyses. Through LASSO, SVM, and RF methods, we isolated five significant genes: FN1, C1orf21, CD36, CD48, and SRPX2. These genes were further validated using a logistic model and 10-fold cross-validation. The external dataset GSE96804 served to validate the identified biomarkers, while receiver operating characteristic (ROC) curve analysis assessed their diagnostic efficacy for DN. Additionally, GSE104948 facilitated comparison of biomarker expression levels between DN and five other kidney diseases, highlighting their specificity for DN. These biomarkers also enabled the identification and validation of two molecular subtypes characterized by distinct immune profiles. The Nephroseq v5 database corroborated the correlation between biomarkers and clinical data. Furthermore, the GSigDB database was employed to predict protein-drug interactions, with molecular docking confirming the therapeutic potential of these drug targets. Finally, a diabetic mouse model (BKS-db) was constructed, and RT-qPCR experiments validated the reliability of the identified biomarkers. The study identified five biomarkers with robust diagnostic predictive power for DN. Subtype classification based on these biomarkers revealed distinct enrichment pathways and immune cell infiltration profiles, underscoring the close relationship between these genes and immune functions in DN. Drug prediction and molecular docking analyses demonstrated excellent binding affinities of candidate drugs to target proteins. Differential expression analysis between DN and five other kidney diseases indicated that all biomarkers, except C1orf21, were highly expressed in DN. Notably, as the mouse model lacks the C1orf21 gene, RT-qPCR confirmed the upregulated expression of FN1, CD36, CD48, and SRPX2. This study successfully identified five biomarkers with potential diagnostic and therapeutic value for DN. These biomarkers not only offer insights into the regulatory mechanisms underlying glomerular injury but also provide a theoretical foundation for the development of diagnostic biomarkers and therapeutic targets related to DN-associated glomerular injury.

Pulmonary hypertension (PH) often leads to poor survival outcomes and encompasses diverse subtypes with distinct underlying causes. Specifically, PH resulting from fibrosing mediastinitis (FM-PH) presents significant diagnostic challenges due to nonspecific symptoms and overlap of clinical characterization with other PH subtypes, leading to frequent misdiagnosis and delayed treatment. Moreover, the complex diagnostic procedures impose a significant burden on FM-PH patients, many of whom already experience mobility difficulties. This study represents a single test-based diagnosis of FM-PH, using the plasma metabolites obtained through ferric particle-enhanced laser desorption/ionization mass spectrometry analysis. Distinct metabolic alterations in FM-PH are identified compared to healthy controls and other PH subtypes, achieving an area under the curve (AUC) of 0.987 for FM-PH diagnosis and 0.728 for differentiating FM-PH from other subtypes. By addressing existing gaps in diagnostic strategies, this research highlights the potential of metabolic analysis in elucidating the metabolic landscape of PH.

Heart failure (HF) is associated with a large socioeconomic burden. The growth of cardiac computed tomography (CT) has allowed for investigation of new applications in predicting risk of cardiovascular disease.

To determine if cardiac CT imaging biomarkers could predict new-onset HF and improve discrimination in a current HF prediction model.

Participants of the Multi-Ethnic Study of Atherosclerosis (MESA) were included to evaluate new-onset HF during a median follow-up period of 17.7 years. Cardiac CT imaging biomarkers measured include left ventricular size indexed (LVSi) and calcification of the coronary arteries (CAC), aortic valve (AVC), mitral annulus (MAC), and thoracic aorta (TAC). We evaluated if cardiac CT variables improved the 10-year risk prediction of new-onset HF by the Pooled Cohort equations to Prevent HF (PCP-HF) score.

Among 6,667 MESA participants (52.7 ​% female), 426 events of new-onset HF occurred. Cox model analysis revealed log transformed CAC (HR 1.11; 95 ​% CI 1.06-1.16; p ​< ​0.001), log transformed AVC (HR 1.06; 95 ​% CI 1.01-1.12; p ​= ​0.014), and LVSi (HR 1.17; 95 ​% CI 1.12-1.21; p ​< ​0.001) were significantly associated with new-onset HF. Area under the curve (AUC) discrimination of new-onset HF by the PCP-HF score was improved with incorporation of cardiac CT imaging biomarkers.

Cardiac CT imaging biomarkers provide anatomic risk factors that improve the prediction of new-onset HF. Coronary and valvular calcifications may signal comorbidities associated with HF. LVSi may reflect left ventricular remodeling associated with HF.

Artificial intelligence (AI) has captured the attention of everyone, including cardiovascular (CV) clinicians and scientists. Moving beyond philosophical debates, modern cardiology cannot overlook AI's growing influence but must actively explore its potential applications in clinical practice and research methodology.

AI offers exciting possibilities for advancing CV medicine by uncovering disease heterogeneity, integrating complex multimodal data, and enhancing treatment strategies. In this review, we discuss the innovative applications of AI in cardiac electrophysiology, imaging, angiography, biomarkers, and genomic data, as well as emerging tools like face recognition and speech analysis. Furthermore, we focus on the expanding role of machine learning (ML) in predicting CV risk and outcomes, outlining a roadmap for the implementation of AI in CV care delivery. While the future of AI holds great promise, technical limitations and ethical challenges remain significant barriers to its widespread clinical adoption.

Addressing these issues through the development of high-quality standards and involving key stakeholders will be essential for AI to transform cardiovascular care safely and effectively.

Cardiovascular diseases remain the leading cause of global morbidity and mortality. Validated risk scores are the basis of guideline-recommended care, but most scores lack the capacity to integrate complex and multidimensional data. Limitations inherent to traditional risk prediction models and the growing burden of residual cardiovascular risk highlight the need for refined strategies that go beyond conventional paradigms. Artificial intelligence and machine learning (ML) provide unique opportunities to refine cardiovascular risk assessment and surveillance through the integration of diverse data types and sources, including clinical, electrocardiographic, imaging and multi-omics derived data. In fact, ML models, such as deep neural networks, can handle high-dimensional data through which phenotyping and cardiovascular risk assessment across diverse patient populations become much more precise, fostering a paradigm shift towards more personalized care. Here, we review the role of ML in advancing cardiovascular risk assessment and discuss its potential to identify novel therapeutic targets and to improve prevention strategies. We also discuss key challenges inherent to ML, such as data quality, standardized reporting, model transparency and validation, and discuss barriers in its clinical translation. We highlight the transformative potential of ML in precision cardiology and advocate for more personalized cardiovascular prevention strategies that go beyond previous notions.

Per- and polyfluoroalkyl substances (PFAS) have been associated with an increased risk of acute coronary syndromes (ACS), but the influence on the degree of coronary stenosis and prognosis is unclear. This study enrolled 571 newly diagnosed ACS cases and investigated the association of 12 PFAS with coronary stenosis severity and prognosis. Coronary stenosis was assessed via Gensini score (GS) and number of lesioned vessels (LVN). Prognosis was estimated by tracking major adverse cardiovascular events (MACE). Statistical analyses included ordered logistic regression, Cox regression, threshold effect models, Bayesian kernel machine regression, and quantile g-computation models. The adverse outcome pathway (AOP) framework was applied to reveal the underlying mechanism. The results showed positive association between perfluorooctanesulfonic acid (PFOS) and coronary stenosis, with an odds ratio (95% confidence interval, CI) of 1.33 (1.06, 1.67) for GS and 1.36 (1.08, 1.71) for LVN. PFOS significantly increased the incidence of poor prognosis, with hazard ratios (95% CI) of 1.96 (1.34, 2.89) for MACE. Threshold effects were observed for PFAS on coronary stenosis and prognosis, with PFOS thresholds of 4.65 ng/mL for GS, 4.54 ng/mL for LVN, and 5.14 ng/mL for MACE, and 5.03 ng/mL for nonfatal myocardial infarction. PFAS mixture exposure increased the occurrence of MACE and nonfatal myocardial infarction. The AOP framework shows that PFAS may impact protein binding, the cytoskeleton, multicellular biological processes, and heart function. In summary, our study revealed the adverse effects of PFAS on the degree of coronary stenosis and prognosis in ACS and identified potentially relevant molecular loci.

Background: Recent studies have analyzed some cytokines in patients with papillary thyroid carcinoma (PTC), but simultaneous analysis of multiple cytokines remains rare. Nonetheless, the simultaneous assessment of multiple cytokines is increasingly recognized as crucial for understanding the cytokine characteristics and developmental mechanisms in PTC. In addition, studies applying artificial intelligence (AI) to discriminate patients with PTC based on serum multiple cytokine data have been performed rarely. Here, we measured and compared 46 cytokines in patients with PTC and healthy individuals, applying AI algorithms to classify the two groups. Methods: Blood serum was isolated from 63 patients with PTC and 63 control individuals. Forty-six cytokines were analyzed simultaneously using Luminex assay Human XL Cytokine Panel. Several laboratory findings were identified from electronic medical records. Student's t-test or the Mann-Whitney U test were performed to analyze the difference between the two groups. As AI classification algorithms to categorize patients with PTC, K-nearest neighbor function, Naïve Bayes classifier, logistic regression, support vector machine, and eXtreme Gradient Boosting (XGBoost) were employed. The SHAP analysis assessed how individual parameters influence the classification of patients with PTC. Results: Cytokine levels, including GM-CSF, IFN-γ, IL-1ra, IL-7, IL-10, IL-12p40, IL-15, CCL20/MIP-α, CCL5/RANTES, and TNF-α, were significantly higher in PTC than in controls. Conversely, CD40 Ligand, EGF, IL-1β, PDGF-AA, and TGF-α exhibited significantly lower concentrations in PTC compared to controls. Among the five classification algorithms evaluated, XGBoost demonstrated superior performance in terms of accuracy, precision, sensitivity (recall), specificity, F1-score, and ROC-AUC score. Notably, EGF and IL-10 were identified as critical cytokines that significantly contributed to the differentiation of patients with PTC. Conclusions: A total of 5 cytokines showed lower levels in the PTC group than in the control, while 10 cytokines showed higher levels. While XGBoost demonstrated the best performance in discriminating between the PTC group and the control group, EGF and IL-10 were considered to be closely associated with PTC.

Uric acid (UA), fibrinogen (FIB), and homocysteine (Hcy) are the main contributors to cardiovascular and cerebrovascular diseases, and are related to hypertension. Hypertension plays a role in atherosclerosis (CAS). We hence explored the correlations of UA, FIB, and Hcy levels with CAS in hypertensive patients.

Totally 170 hypertensive patients were retrospectively included and assigned into the Non-sclerosis, Thickened, and Plaque groups based on carotid intima-media thickness (cIMT), with serum UA, FIB, and Hcy compared. Correlations of UA, FIB, and Hcy with cIMT and carotid atherosclerotic plaque (CAP) were assessed using Spearman's correlation analysis. The risk factors of CAS were evaluated by logistic multivariate regression analysis. The predictive value of UA, FIB, and Hcy for CAS was estimated by the receiver operating characteristic (ROC) curve.

UA, FIB, and Hcy were up-regulated in the Plaque group vs. other two groups. Serum UA, FIB, and Hcy were positively linked to cIMT and CAP, and were independent risk factors for CAS. The area under ROC curve of UA, FIB, Hcy levels and their combination for predicting CAS were 0.889, 0.855, 0.902, and 0.958, respectively. Hypertensive patients with high levels of UA, FIB, or Hcy were more likely to develop CAS.

Serum UA, FIB, and Hcy are positively correlated with cIMT and CAP, and are independent risk factors for CAS in hypertensive patients. High UA, FIB and Hcy expression could assist in predicting CAS in patients with hypertension, and the combination of the three was more valuable than all three alone.

Artificial intelligence (AI) has profoundly influenced the field of cardiovascular interventions and coronary artery procedures in particular. AI has enhanced diagnostic accuracy in coronary artery disease through advanced invasive and noninvasive imaging modalities, facilitating more precise diagnosis and personalized interventional strategies. AI integration in coronary interventions has streamlined diagnostic and procedural workflows, improved procedural accuracy, increased clinician efficiency, and enhanced patient safety and outcomes. Despite its potential, AI still faces significant challenges, including concerns regarding algorithmic biases, lack of transparency in AI-driven decision making, and ethical challenges. This review explores the latest advancements of AI applications in coronary artery interventions, focusing on preprocedural planning and real-time procedural guidance. It also addresses the major limitations and obstacles that hinder the widespread clinical adoption of AI technologies in this field.

Artificial intelligence is rapidly evolving and its possibilities are endless. Its primary applications in cardiac magnetic resonance imaging have focused on: image acquisition (in terms of acceleration and quality improvement); segmentation (in terms of saving time and reproducibility); tissue characterisation (including radiomic techniques and the non-contrast assessment of myocardial fibrosis); automatic diagnosis; and prognostic stratification. The aim of this article is to attempt to provide an overview of the current situation as preparation for the significant changes currently underway or imminent in the very near future.

Background: Prostate cancer (PCa) is a prevalent malignancy among elderly men. Biochemical recurrence (BCR), which typically occurs after radical treatments such as radical prostatectomy or radiation therapy, serves as a critical indicator of potential disease progression. However, reliable and effective methods for predicting BCR in PCa patients remain limited. Methods: In this study, we used Bayesian deconvolution combined with 10 machine learning algorithms to build a five-gene model for predicting PCa progression. The model and the five selected genes were externally validated. Various analyses such as prognosis, clinical subgroups, tumor microenvironment, immunity, genetic variants, and drug sensitivity were performed on MSMB/Epithelial_cells subgroups. Results: Our model outperformed 102 previously published prognostic features. Notably, PCa patients with a high proportion of MSMB/epithelial cells were characterized by a greater progression-free Interval (PFI), a higher proportion of early-stage tumors, a lower stromal component, and a reduced presence of tumor-associated fibroblasts (CAF). The high proportion of MSMB/epithelial cells was also associated with higher frequencies of SPOP and TP53 mutations. Drug sensitivity analysis revealed that patients with a poorer prognosis and lower MSMB/epithelial cell ratio showed increased sensitivity to cyclophosphamide, cisplatin, and dasatinib. Conclusions: The model developed in this study provides a robust and accurate tool for predicting PCa progression. It offers significant potential for enhancing risk stratification and informing personalized treatment strategies for PCa patients.

Patients with early-stage hepatocellular carcinoma (HCC) generally have good survival rates following surgical resection. However, a subset of these patients experience recurrence within five years post-surgery.

To develop predictive models utilizing machine learning (ML) methods to detect early-stage patients at a high risk of mortality.

Eight hundred and eight patients with HCC at Beijing Ditan Hospital were randomly allocated to training and validation cohorts in a 2:1 ratio. Prognostic models were generated using random survival forests and artificial neural networks (ANNs). These ML models were compared with other classic HCC scoring systems. A decision-tree model was established to validate the contribution of immune-inflammatory indicators to the long-term outlook of patients with early-stage HCC.

Immune-inflammatory markers, albumin-bilirubin scores, alpha-fetoprotein, tumor size, and International Normalized Ratio were closely associated with the 5-year survival rates. Among various predictive models, the ANN model generated using these indicators through ML algorithms exhibited superior performance, with a 5-year area under the curve (AUC) of 0.85 (95%CI: 0.82-0.88). In the validation cohort, the 5-year AUC was 0.82 (95%CI: 0.74-0.85). According to the ANN model, patients were classified into high-risk and low-risk groups, with an overall survival hazard ratio of 7.98 (95%CI: 5.85-10.93, P < 0.0001) between the two cohorts.

A non-invasive, cost-effective ML-based model was developed to assist clinicians in identifying high-risk early-stage HCC patients with poor postoperative prognosis following surgical resection.

Heart failure (HF) and atrial fibrillation (AF) frequently coexist, exacerbate each other and are associated with increased morbidity and mortality rates. However, no previous study has specifically calculated the risk of experiencing either event following the occurrence of the other and also considered competing risks. The aim of this study was to examine the bidirectional relationship of AF and HF in a multiethnic population, taking competing risks into account.

Two Fine and Gray regression models of the subdistribution functions were implemented to evaluate the bidirectional association between AF and HF and were adjusted for a common set of covariates. Competing events were defined as HF/AF and/or cardiac death vs noncardiac death. For each model, common covariates for AF and HF were pre-identified in the literature, and either HF or AF was used as a time-dependent covariate.

In the Multi-Ethnic Study of Atherosclerosis (MESA), 4016 study participants (mean age 67.2 ± 7.6 years and 48.8% male participants), free of clinically recognized cardiovascular disease at baseline, were assessed for AF and HF. After a median (IQR) follow-up of 6034 (3994-6313) days, 1044 incident AFs, 302 incident HFs and 1298 events of death occurred. Deaths were distributed as 313 cardiac deaths and 985 noncardiac deaths, and the incidence of AF was about 3.5 higher than that of HF. We found that HF was associated with a composite outcome of AF and/or cardiac death (HR 2.91, 95%CI [2.49-3.40]; P < 0.001) and that AF was associated with a composite outcome of HF and/or cardiac death (HR 2.05, 95%CI [1.79-2.35]; P < 0.001).

AF and HF exacerbate the incidence of each other and are strongly and independently associated, suggesting that their joint association should be taken into consideration in future studies. From a clinical perspective, the occurrence of either of these events greatly increases the risk for the other (ClinicalTrials.gov Identifier: NCT00005487).

Inflammatory breast cancer (IBC) is an aggressive and rare phenotype of breast cancer, which has a poor prognosis. Thus, it is necessary to establish a novel predictive model of high accuracy for the prognosis of IBC patients.

Clinical information of 1,230 IBC patients from 2010 to 2020 was extracted from the Surveillance, Epidemiology and End Results (SEER) database. Cox analysis was applied to identify clinicopathological characteristics associated with the overall survival (OS) of IBC patients. Random survival forest (RSF) algorithm was adopted to construct an accurate prognostic prediction model for IBC patients. Kaplan-Meier analysis was performed for survival analyses.

Race, N stage, M stage, molecular subtype, history of chemotherapy and surgery, and response to neoadjuvant therapy were identified as independent predictive factors for the OS of IBC patients. The top five significant variables included surgery, response to neoadjuvant therapy, chemotherapy, breast cancer molecular subtypes, and M stage. The C-index of RSF model was 0.7704 and the area under curve (AUC) values for 1, 3, 5 years in training and validation datasets were 0.879-0.955, suggesting the excellent predictive performance of RSF model. IBC patients were divided into high-risk group and low-risk group according the risk score of RSF model, and the OS of patients in the low-risk group was significantly longer than those in the high-risk group.

In this study, we constructed a prognosis prediction model for IBC patients through RSF algorithm, which may potentially serve as a useful tool during clinical decision-making.

N6-methyladenosine (m6A) is the most common and abundant internal co-transcriptional modification in eukaryotic RNAs. This modification is catalyzed by m6A methyltransferases, known as "writers", including METTL3/14 and WTAP, and removed by demethylases, or "erasers", such as FTO and ALKBH5. It is recognized by m6A-binding proteins, or "readers", such as YTHDF1/2/3, YTHDC1/2, IGF2BP1/2/3, and HNRNPA2B1. Cardiovascular diseases (CVDs) are the leading cause of morbidity and mortality worldwide. Recent studies indicate that m6A RNA modification plays a critical role in both the physiological and pathological processes involved in the initiation and progression of CVDs. In this review, we will explore how m6A RNA methylation impacts both the normal and disease states of the cardiovascular system. Our focus will be on recent advancements in understanding the biological functions, molecular mechanisms, and regulatory factors of m6A RNA methylation, along with its downstream target genes in various CVDs, such as atherosclerosis, ischemic diseases, metabolic disorders, and heart failure. We propose that the m6A RNA methylation pathway holds promise as a potential therapeutic target in cardiovascular disease.

The Hispanic Community Health Study/Study of Latinos (HCHS/SOL) is a multicenter, longitudinal cohort study designed to evaluate environmental, lifestyle, and genetic risk factors as they relate to cardiometabolic and other chronic diseases among Hispanic/Latino populations in the United States. Since the study's inception in 2008, as a result of the study's robust genetic measures, HCHS/SOL has facilitated major contributions to the field of genetic research. This 10-year retrospective review highlights the major findings for genotype-phenotype relationships and advancements in statistical methods owing to the HCHS/SOL. Furthermore, we discuss the ethical and societal challenges of genetic research, especially among Hispanic/Latino adults in the United States. Continued genetic research, ancillary study expansion, and consortia collaboration through HCHS/SOL will further drive knowledge and advancements in human genetics research.

Through a simple machine learning approach, we aimed to assess the risk of all-cause mortality after 5 years in a European population, based on electrocardiogram (ECG) parameters, age, and sex.

The study included patients between 40 and 90 years old who underwent ECG recording between January 2008 and October 2022 in the metropolitan area of Modena, Italy. Exclusion criteria established a patient cohort without severe ECG abnormalities, namely, tachyarrhythmias, bradyarrhythmias, Wolff-Parkinson-White syndrome, second- or third- degree AV block, bundle-branch blocks, more than three premature beats, poor signal quality, and presence of pacemakers and implantable cardioverter- defibrillators. Mortality was assessed using a set of logistic regression models, differentiated by age group, to which the Akaike Information Criterion was applied. Model fitting was evaluated using confusion matrix-related performance metrics, the area under the receiver operating characteristic (ROC) curve (AUC), and the predictive significance against the no-information rate (NIR).

53692 patients were enrolled, of whom 14353 (26.73 %) died within 5 years of ECG registration. The logistic regression model distinguished between those who died and those who survived based on the predicted mortality probability for all age groups, obtaining a significant difference between the predicted mortality and the NIR in 14 of the 55 age groups. Good accuracy and performance metrics were observed, resulting in an average AUC of 0.779.

The proposed model showed a good predictive performance in patients without severe ECG abnormalities. Therefore, this study highlights the potential of ECGs as prognostic rather than diagnostic tools.

Understanding early vascular ageing has become crucial for preventing adverse cardiovascular events. To this respect, recent AI-based risk clustering models offer early detection strategies focused on healthy populations, yet their complexity limits clinical use. This work introduces a novel recommendation system embedded in a web app to assess and mitigate early vascular ageing risk, leading patients towards improved cardiovascular health.

This system employs a methodology that calculates distances within multidimensional spaces and integrates cost functions to obtain personalized optimisation of recommendations. It also incorporates a classification system for determining the intensity levels of the clinical interventions.

The recommendation system showed high efficiency in identifying and visualizing individuals at high risk of early vascular ageing among healthy patients. Additionally, the system corroborated its consistency and reliability in generating personalized recommendations among different levels of granularity, emphasizing its focus on moderate or low-intensity recommendations, which could improve patient adherence to the intervention.

This tool might significantly aid healthcare professionals in their daily analysis, improving the prevention and management of cardiovascular diseases.

As a treatment for esophageal squamous cell carcinoma (ESCC), which is common and fatal, mitophagy is a conserved cellular mechanism that selectively removes damaged mitochondria and is crucial for cellular homeostasis. While tumor development and resistance to anticancer therapies are related to ESCC, their role in ESCC remains unclear. Here, we investigated the relationship between mitophagy-related genes (MRGs) and ESCC to provide novel insights into the role of mitophagy in ESCC prognosis and diagnosis prediction. First, we identified MRGs from the GeneCards database and examined them at both the single-cell and transcriptome levels. Key genes were selected and a prognostic model was constructed using least absolute shrinkage and selection operator analysis. External validation was performed using the GSE53624 dataset and Kaplan-Meier survival analysis was performed to identify PYCARD as a gene significantly associated with survival in ESCC. We then examined the effect of PYCARD on ESCC cell proliferation and migration and identified 169 MRGs at the single-cell and transcriptome levels, as well as the high-risk groups associated with cancer-related pathways. Thirteen key genes were selected for model construction via multiple machine learning algorithms. PYCARD, which is upregulated in patients with ESCC, was negatively correlated with prognosis and its knockdown inhibited ESCC cell proliferation and migration. Our ESCC prediction model based on mitophagy-related genes demonstrated promising results and provides more options for the management and clinical treatment of ESCC patients. Moreover, targeting or regulating PYCARD levels might offer new therapeutic strategies for ESCC patients in clinical settings.

Mitochondria are involved in septic shock and inflammatory response syndrome, which severely affects the life security of patients. It is necessary to recognize and explore the immune-mitochondrial genes in septic shock.

The GSE57065 dataset was acquired from the Gene Expression Omnibus (GEO) database and filtered by limma and the weighted correlation network analysis (WGCNA) to identify mitochondrial-related differentially expressed genes (MitoDEGs) in septic shock. The function of MitoDEGs was analyzed using the Gene Ontology (GO) analysis, Kyoto Encyclopedia of Genes and Genomes (KEGG), and Gene Set Enrichment Analysis (GSEA), respectively. The Protein-Protein Interaction (PPI) network composed of MitoDEGs was established using Cytoscape. Support Vector Machine Recursive Feature Elimination (SVM-RFE), Random Forest (RF), and Least Absolute Shrinkage and Selection Operator (LASSO) were used to identify diagnostic MitoDEGs, which were validated using receiver operating characteristic (ROC) analysis and Quantitative Real-time Reverse Transcription Polymerase Chain Reaction (qRT-PCR). Furthermore, the infiltration of immunocytes was analyzed using CIBERSORT, and the correlation between diagnostic MitoDEGs and immunocytes was explored using Spearman.

A total of 44 MitoDEGs were filtered, and functional enrichment analysis showed they were associated with mitochondrial function, and the PPI network had 457 nodes and 547 edges. Four diagnostic genes, MitoDEGs, PGS1, C6orf136, THEM4, and EPHX2, were identified by three machine learning algorithms, and qRT-PCR results obtained similar expression levels as bioinformatics analysis. Furthermore, the diagnostic model constructed by the diagnostic genes had fine diagnostic efficacy. Immunocyte infiltration analysis showed that activated immunocytes were abundant and correlated with hub genes, with neutrophils accounting for the largest proportion in septic shock.

In this study, we recognized four immune-mitochondrial key genes (PGS1, C6orf136, THEM4, and EPHX2) in septic shock and designed a novel gene diagnosis model that provided a new and meaningful way for the diagnosis of septic shock.

Understanding the viscoelastic properties of atherosclerotic plaques at rupture-prone scales is crucial for assessing their vulnerability. Here, we develop a Hybrid Hierarchical theory-Microrheology (HHM) approach, enabling the analysis of multiscale mechanical variations and distribution changes in regional tissue viscoelasticity within plaques across different spatial scales. We disclose a universal two-stage power-law rheology in plaques, characterized by distinct power-law exponents (αshort and αlong), which serve as mechanical indexes for plaque components and assessing mechanical gradients. We further propose a self-similar hierarchical theory that effectively delineates plaque heterogeneity from the cytoplasm, cell, to tissue levels. Moreover, our proposed multi-layer perceptron model addresses the viscoelastic heterogeneity and gradients within plaques, offering a promising diagnostic strategy for identifying unstable plaques. These findings not only advance our understanding of plaque mechanics but also pave the way for innovative diagnostic approaches in cardiovascular disease management. STATEMENT OF SIGNIFICANCE: Our study pioneers a Hybrid Hierarchical theory-Microrheology (HHM) approach to dissect the intricate viscoelasticity of atherosclerotic plaques, focusing on distinct components including cap fibrosis, lipid pools, and intimal fibrosis. We unveil a universal two-stage power-law rheology capturing mechanical variations across plaque structures. The proposed hierarchical model adeptly captures viscoelasticity changes from cytoplasm, cell to tissue levels. Based on the newly proposed markers, we further develop a machine learning (ML) diagnostic model that sets precise criteria for evaluating plaque components and heterogeneity. This work not only reveals the comprehensive mechanical heterogeneity within plaques but also introduces a mechanical marker-based ML strategy for assessing plaque conditions, offering a significant leap towards understanding and diagnosing atherosclerotic risks.

Managing patients with multiple risk factors for CVDs can present distinct challenges for healthcare providers, therefore addressing them can be paramount to optimize patient care.

This narrative review explores the burden that CVDs place on healthcare systems as well as how we can best optimize the risk management of these patients. Through a comprehensive review of literature, guidelines and clinical studies, this paper explores various approaches to risk management, lifestyle modifications and pharmacological interventions utilized in the management of CVDs. Furthermore, emerging technologies such as machine learning (ML) are discussed, highlighting potential opportunities for future research. By reviewing existing recommendations and evidence, this paper aims to provide insight into optimizing strategies and improving the outcomes for patients with multiple CVDs.

Optimizing risk factors can have a significant impact on patient outcomes, as such each patient should have a clear plan on how to manage these risk factors to minimize adverse healthcare results.

New-onset atrial fibrillation (NOAF) is the most common arrhythmia in critically ill patients admitted to intensive care and is associated with poor prognosis and disease burden. Identifying high-risk individuals early is crucial. This study aims to create and validate a NOAF prediction model for critically ill patients using machine learning (ML).

The data came from two non-overlapping datasets from the Medical Information Mart for Intensive Care (MIMIC), with MIMIC-IV used for training and subset of MIMIC-III used as external validation. LASSO regression was used for feature selection. Eight ML algorithms were employed to construct the prediction model. Model performance was evaluated based on identification, calibration, and clinical application. The SHapley Additive exPlanations (SHAP) method was used for visualizing model characteristics and individual case predictions.

Among 16,528 MIMIC-IV patients, 1520 (9.2%) developed AF post-ICU admission. A model with 23 variables was built, with XGBoost performing best, achieving an AUC of 0.891 (0.873-0.888) in validation and 0.769 (0.756-0.782) in external validation. Key predictors included age, mechanical ventilation, urine output, sepsis, blood urea nitrogen, percutaneous arterial oxygen saturation, continuous renal replacement therapy and weight. A risk probability greater than 0.6 was defined as high risk. A friendly user interface had been developed for clinician use.

We developed a ML model to predict the risk of NOAF in critically ill patients without cardiac surgery and validated its potential as a clinically reliable tool. SHAP improves the interpretability of the model, enables clinicians to better understand the causes of NOAF, helps clinicians to prevent it in advance and improves patient outcomes.

Prediction of short-term outcomes in young patients with acute ischemic stroke (AIS) may assist in making therapy decisions. Machine learning (ML) is increasingly used in healthcare due to its high accuracy. This study aims to use a ML-based predictive model for poor 3-month functional outcomes in young AIS patients and to compare the predictive performance of ML models with the logistic regression model.

We enrolled AIS patients aged between 18 and 50 years from the Third Chinese National Stroke Registry (CNSR-III), collected between 2015 and 2018. A modified Rankin Scale (mRS) ≥ 3 was a poor functional outcome at 3 months. Four ML tree models were developed: The extreme Gradient Boosting (XGBoost), Light Gradient Boosted Machine (lightGBM), Random Forest (RF), and The Gradient Boosting Decision Trees (GBDT), compared with logistic regression. We assess the model performance based on both discrimination and calibration.

A total of 2268 young patients with a mean age of 44.3 ± 5.5 years were included. Among them, (9%) had poor functional outcomes. The mRS at admission, living alone conditions, and high National Institutes of Health Stroke Scale (NIHSS) at discharge remained independent predictors of poor 3-month outcomes. The best AUC in the test group was XGBoost (AUC = 0.801), followed by GBDT, RF, and lightGBM (AUCs of 0.795, 0, 794, and 0.792, respectively). The XGBoost, RF, and lightGBM models were significantly better than logistic regression (P < 0.05).

ML outperformed logistic regression, where XGBoost the boost was the best model for predicting poor functional outcomes in young AIS patients. It is important to consider living alone conditions with high severity scores to improve stroke prognosis.

Predicting major adverse cardiovascular events (MACE) is crucial due to its high readmission rate and severe sequelae. Current risk scoring model of MACE are based on a few features of a patient status at a single time point. We developed a self-attention-based model to predict MACE within 3 years from time series data utilizing numerous features in electronic medical records (EMRs). In addition, we demonstrated transfer learning for hospitals with insufficient data through code mapping and feature selection by the calculated importance using Xgboost. We established operational definitions and categories for diagnoses, medications, and laboratory tests to streamline scattered codes, enhancing clinical interpretability across hospitals. This resulted in reduced feature size and improved data quality for transfer learning. The pre-trained model demonstrated an increase in AUROC after transfer learning, from 0.564 to 0.821. Furthermore, to validate the effectiveness of the predicted scores, we analyzed the data using traditional survival analysis, which confirmed an elevated hazard ratio for a group with high scores.

Magnetocardiography (MCG) is a novel non-invasive technique that detects subtle magnetic fields generated by cardiomyocyte electrical activity, offering sensitive detection of myocardial ischemia. This study aimed to assess the ability of MCG to predict impaired myocardial perfusion using single-photon emission computed tomography (SPECT).

A total of 112 patients with chest pain underwent SPECT and MCG scans, from which 65 MCG output parameters were analyzed. Using least absolute shrinkage and selection operator (LASSO) regression to screen for significant MCG variables, three machine learning models were established to detect impaired myocardial perfusion: random forest (RF), decision tree (DT), and support vector machine (SVM). The diagnostic performance was evaluated based on the sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC).

Five variables, the ratio of magnetic field amplitude at R-peak and positive T-peak (RoART+), R and T-peak magnetic field angle (RTA), maximum magnetic field angle (MAmax), maximum change in current angle (CCAmax), and change positive pole point area between the T-wave beginning and peak (CPPPATbp), were selected from 65 automatic output parameters. RTA emerged as the most critical variable in the RF, DT, and SVM models. All three models exhibited excellent diagnostic performance, with AUCs of 0.796, 0.780, and 0.804, respectively. While all models showed high sensitivity (RF = 0.870, DT = 0.826, SVM = 0.913), their specificity was comparatively lower (RF = 0.500, DT = 0.300, SVM = 0.100).

Machine learning models utilizing five key MCG variables successfully predicted impaired myocardial perfusion, as confirmed by SPECT. These findings underscore the potential of MCG as a promising future screening tool for detecting impaired myocardial perfusion.

ChiCTR2200066942, https://www.chictr.org.cn/showproj.html?proj=187904.

Quantification of aortic morphology plays an important role in the evaluation and follow-up assessment of patients with aortic diseases, but often requires labor-intensive and operator-dependent measurements. Automatic solutions would help enhance their quality and reproducibility.

To design a deep learning (DL)-based automated approach for aortic landmarks and lumen detection derived from three-dimensional (3D) MRI.

Retrospective.

Three hundred ninety-one individuals (female: 47%, age = 51.9 ± 18.4) from three sites, including healthy subjects and patients (hypertension, aortic dilation, Turner syndrome), randomly divided into training/validation/test datasets (N = 236/77/78). Twenty-five subjects were randomly selected and analyzed by three operators with different levels of expertise.

1.5-T and 3-T, 3D spoiled gradient-recalled or steady-state free precession sequences.

Reinforcement learning and a two-stage network trained using reference landmarks and segmentation from an existing semi-automatic software were used for aortic landmark detection and segmentation from sinotubular junction to coeliac trunk. Aortic segments were defined using the detected landmarks while the aortic centerline was extracted from the segmentation and morphological indices (length, aortic diameter, and volume) were computed for both the reference and the proposed segmentations.

Segmentation: Dice similarity coefficient (DSC), Hausdorff distance (HD), average symmetrical surface distance (ASSD); landmark detection: Euclidian distance (ED); model robustness: Spearman correlation, Bland-Altman analysis, Kruskal-Wallis test for comparisons between reference and DL-derived aortic indices; inter-observer study: Williams index (WI). A WI 95% confidence interval (CI) lower bound >1 indicates that the method is within the inter-observer variability. A P-value <0.05 was considered statistically significant.

DSC was 0.90 ± 0.05, HD was 12.11 ± 7.79 mm, and ASSD was 1.07 ± 0.63 mm. ED was 5.0 ± 6.1 mm. A good agreement was found between all DL-derived and reference aortic indices (r >0.95, mean bias <7%). Our segmentation and landmark detection performances were within the inter-observer variability except the sinotubular junction landmark (CI = 0.96;1.04).

A DL-based aortic segmentation and anatomical landmark detection approach was developed and applied to 3D MRI data for achieve aortic morphology evaluation.

3 TECHNICAL EFFICACY: Stage 2.

This article is aimed to make predictions in terms of prognostic factors and compare prediction methods by using Cox proportional hazards regression analysis (CPH), some machine learning techniques and Accelerated Failure Time (AFT) model for post-treatment survival probabilities according to clinical presentations and pathological information of early-stage breast cancer patients.

The study was carried out in three stages. In the first stage, the CPH method was applied. In the second stage, the AFT model and in the last stage, machine learning methods were applied. The data set consists of 697 breast cancer patients who applied to Marmara University Hospital oncology clinic between 01.01.1994 and 31.12.2009. The models obtained by using various parameters of the patients were compared according to the C index, 5-year survival rate and 10-year survival rate.

According to the models obtained as a result of the analyses applied, MetLN and age were obtained as a significant risk factor as a result of CPH method and AFT methods, while MetLN, age, tumor size, LV1 and extracapsular involvement were obtained as risk factors in machine learning methods. In addition, when the c-index values of the handheld models are examined, it is obtained as 69.8 for the CPH model, 70.36 for the AFT model, 72.1 for the random survival forest and 72.8 for the gradient boosting machine. In conclusion, the study highlights the potential of comparing conventional statistical methods and machine-learning algorithms to improve the precision of risk factor determination in early-stage breast cancer prognosis. Additionally, efforts should be made to enhance the interpretability of machine-learning models, ensuring that the results obtained can be effectively communicated and utilized by clinical practitioners. This would enable more informed decision-making and personalized care in the treatment and follow-up processes for early-stage breast cancer patients.

The accurate prediction of COVID-19 mortality risk, considering influencing factors, is crucial in guiding effective public policies to alleviate the strain on the healthcare system. As such, this study aimed to assess the efficacy of decision tree algorithms (CART, C5.0, and CHAID) in predicting COVID-19 mortality risk and compare their performance with that of the logistic model.

This retrospective cohort study examined 5080 cases of COVID-19 in Babol, a city in northern Iran, who tested positive for the virus via PCR from March 2020 to March 2022. In order to check the validity of the findings, the data was randomly divided into an 80% training set and a 20% testing set. The prediction models, such as Logistic regression models and decision tree algorithms, were trained on the 80% training data and tested on the 20% testing data. The accuracy of these methods for the test samples was assessed using measures like ROC curve, sensitivity, specificity, and AUC.

The findings revealed that the mortality rate for COVID-19 patients who were admitted to hospitals was 7.7%. Through cross validation, it was determined that the CHAID algorithm outperformed other decision tree and logistic regression algorithms in specificity, and precision but not sensitivity in predicting the risk of COVID-19 mortality. The CHAID algorithm demonstrated a specificity, precision, accuracy, and F-score of 0.98, 0.70, 0.95, and 0.52 respectively. All models indicated that factors such as ICU hospitalization, intubation, age, kidney disease, BUN, CRP, WBC, NLR, O2 sat, and hemoglobin were among the factors that influenced the mortality rate of COVID-19 patients.

The CART and C5.0 models had outperformed in sensitivity but CHAID demonstrates a better performance compared to other decision tree algorithms in specificity, precision, accuracy and shows a slight improvement over the logistic regression method in predicting the risk of COVID-19 mortality in the population under study.

To develop and validate a predictive model utilizing machine-learning techniques for estimating the length of hospital stay among patients who underwent coronary artery bypass grafting.

Three machine learning models (random forest, extreme gradient boosting and neural networks) and three traditional regression models (Poisson regression, linear regression, negative binomial regression) were trained in a dataset of 9,584 patients who underwent coronary artery bypass grafting between January 2017 and December 2021. The data were collected from hospital discharges from 133 centers in Brazil. Algorithms were ranked by calculating the root mean squared logarithmic error (RMSLE). The top performing algorithm was validated in a never-before-seen database of 2,627 patients. We also developed a model with the top ten variables to improve usability.

The random forest technique produced the model with the lowest error. The RMLSE was 0.412 (95%CI 0.405-0.419) on the training dataset and 0.454 (95%CI 0.441-0.468) on the validation dataset. Non-elective surgery, admission to a public hospital, heart failure, and age had the greatest impact on length of hospital stay.

The predictive model can be used to generate length of hospital stay indices that could be used as markers of efficiency and identify patients with the potential for prolonged hospitalization, helping the institution in managing beds, scheduling surgeries, and allocating resources.

Cardiovascular diseases remain the leading cause of global mortality, underscoring the critical need for accurate and timely diagnosis. This narrative review examines the current applications and future potential of artificial intelligence (AI) and machine learning (ML) in cardiovascular imaging. We discuss the integration of these technologies across various imaging modalities, including echocardiography, computed tomography, magnetic resonance imaging, and nuclear imaging techniques. The review explores AI-assisted diagnosis in key areas such as coronary artery disease detection, valve disorders assessment, cardiomyopathy classification, arrhythmia detection, and prediction of cardiovascular events. AI demonstrates promise in improving diagnostic accuracy, efficiency, and personalized care. However, significant challenges persist, including data quality standardization, model interpretability, regulatory considerations, and clinical workflow integration. We also address the limitations of current AI applications and the ethical implications of their implementation in clinical practice. Future directions point towards advanced AI architectures, multimodal imaging integration, and applications in precision medicine and population health management. The review emphasizes the need for ongoing collaboration between clinicians, data scientists, and policymakers to realize the full potential of AI in cardiovascular imaging while ensuring ethical and equitable implementation. As the field continues to evolve, addressing these challenges will be crucial for the successful integration of AI technologies into cardiovascular care, potentially revolutionizing diagnostic capabilities and improving patient outcomes.

Recent advancements in artificial intelligence (AI) applications in medicine have been significant over the past 30 years. To monitor current research developments, it is crucial to examine the latest trends in AI adoption across various medical fields. This bibliometric analysis focuses on AI applications in cardiology. Unlike existing literature reviews, this study specifically examines journal articles published in the last decade, sourced from both Scopus and Web of Science databases, to illustrate the recent trends in AI within cardiology. The bibliometric analysis involves a statistical and quantitative evaluation of the literature on AI application in cardiovascular medicine over a defined period. A comprehensive global literature review is conducted to identify key research areas, authors, and their interrelationships through published works. The leading institutions and most influential authors in research on the role of AI in cardiology were located in the United States, the United Kingdom, and China. This study also provides researchers with an overview of the evolution of research in AI and cardiology. The main contribution of this study is to highlight the prominent authors, countries, journals, institutions, keywords, and trends in the development of AI in cardiology.

New-onset atrial fibrillation (NOAF) occurs in 5% to 15% of patients who undergo transfemoral transcatheter aortic valve replacement (TAVR). Cardiac imaging has been underutilized to predict NOAF following TAVR.

The objective of this analysis was to compare and assess standard, manual echocardiographic and cardiac computed tomography (cCT) measurements as well as machine learning-derived cCT measurements of left atrial volume index and epicardial adipose tissue as risk factors for NOAF following TAVR.

The study included 1,385 patients undergoing elective, transfemoral TAVR for severe, symptomatic aortic stenosis. Each patient had standard and machine learning-derived measurements of left atrial volume and epicardial adipose tissue from cardiac computed tomography. The outcome of interest was NOAF within 30 days following TAVR. We used a 2-step statistical model including random forest for variable importance ranking, followed by multivariable logistic regression for predictors of highest importance. Model discrimination was assessed by using the C-statistic to compare the performance of the models with and without imaging.

Forty-seven (5.0%) of 935 patients without pre-existing atrial fibrillation (AF) experienced NOAF. Patients with pre-existing AF had the largest left atrial volume index at 76.3 ± 28.6 cm3/m2 followed by NOAF at 68.1 ± 26.6 cm3/m2 and then no AF at 57.0 ± 21.7 cm3/m2 (P < 0.001). Multivariable regression identified the following risk factors in association with NOAF: left atrial volume index ≥76 cm2 (OR: 2.538 [95% CI: 1.165-5.531]; P = 0.0191), body mass index <22 kg/m2 (OR: 4.064 [95% CI: 1.500-11.008]; P = 0.0058), EATv (OR: 1.007 [95% CI: 1.000-1.014]; P = 0.043), aortic annulus area ≥659 mm2 (OR: 6.621 [95% CI: 1.849-23.708]; P = 0.004), and sinotubular junction diameter ≥35 mm (OR: 3.891 [95% CI: 1.040-14.552]; P = 0.0435). The C-statistic of the model was 0.737, compared with 0.646 in a model that excluded imaging variables.

Underlying cardiac structural differences derived from cardiac imaging may be useful in predicting NOAF following transfemoral TAVR, independent of other clinical risk factors.

Exercise stress ECG is a common diagnostic test for stable coronary artery disease, but its sensitivity and specificity need to be further improved. In this paper, we construct a machine learning model for the prediction of angiographic coronary artery disease by HFQRS analysis of cycling exercise ECG.

This study prospectively included 140 inpatients and 59 healthy volunteers undergoing cycling exercise ECG. The CHD group (N=104) and non-CHD group (N=95) were determined by coronary angiography gold standard. Automated HF QRS analysis was performed by the blinded method. The coronary group was predominantly male, with a higher prevalence of age, BMI, hypertension, and diabetes than the non-coronary group ( P < 0.001 ), higher lipid levels in the coronary group ( P < 0.005 ), significantly longer QRS duration during exercise testing ( P < 0.005 ), more positive leads ( P < 0.001 ), and a greater proportion of significant changes in HFQRS ( P < 0.001 ). Age, Gender, Hypertension, Diabetes, and HF QRS Conclusions were screened by correlation analysis and multifactorial retrospective analysis to construct the machine learning models of the XGBoost Classifier, Logistic Regression, LightGBM Classifier, RandomForest Classifier, Artificial Neural Network and Support Vector Machine, respectively.

Male, elderly, with hypertension, diabetes mellitus, and positive exercise stress test HFQRS conclusions suggested a high risk of CHD. The best performance of the Logistic Regression model was compared, and a column line graph for assessing the risk of CHD was further developed and validated.

Historically, cardiovascular prevention has been predominantly focused on stress-induced ischemia, but recent trials have challenged this paradigm, highlighting the emerging role of vulnerable, non-flow-limiting coronary plaques, leading to a shift towards integrating plaque morphology with functional data into risk prediction models. Coronary computed tomography angiography (CCTA) represents a high-resolution, low-risk, and largely available non-invasive modality for the precise delineation of plaque composition, morphology, and inflammatory activity, further enhancing our ability to stratify high-risk plaque and predict adverse cardiovascular outcomes. Coronary artery calcium (CAC) scoring, derived from CCTA, has emerged as a promising tool for predicting future cardiovascular events in asymptomatic individuals, demonstrating incremental prognostic value beyond traditional cardiovascular risk factors in terms of myocardial infarction, stroke, and all-cause mortality. Additionally, CCTA-derived information on adverse plaque characteristics, geometric characteristics, and hemodynamic forces provides valuable insights into plaque vulnerability and seems promising in guiding revascularization strategies. Additionally, non-invasive assessments of epicardial and pericoronary adipose tissue (PCAT) further refine risk stratification, adding prognostic significance to coronary artery disease (CAD), correlating with plaque development, vulnerability, and rupture. Moreover, CT imaging not only aids in risk stratification but is now emerging as a screening tool able to monitor CAD progression and treatment efficacy over time. Thus, the integration of CAC scoring and PCAT evaluation into risk stratification algorithms, as well as the identification of high-risk plaque morphology and adverse geometric and hemodynamic characteristics, holds promising results for guiding personalized preventive interventions, helping physicians in identifying high-risk individuals earlier, tailoring lifestyle and pharmacological interventions, and improving clinical outcomes in their patients.

To develop and validate machine learning models for predicting coronary artery disease (CAD) within a Taiwanese cohort, with an emphasis on identifying significant predictors and comparing the performance of various models.

This study involved a comprehensive analysis of clinical, demographic, and laboratory data from 8,495 subjects in Taiwan Biobank (TWB) after propensity score matching to address potential confounding factors. Key variables included age, gender, lipid profiles (T-CHO, HDL_C, LDL_C, TG), smoking and alcohol consumption habits, and renal and liver function markers. The performance of multiple machine learning models was evaluated.

The cohort comprised 1,699 individuals with CAD identified through self-reported questionnaires. Significant differences were observed between CAD and non-CAD individuals regarding demographics and clinical features. Notably, the Gradient Boosting model emerged as the most accurate, achieving an AUC of 0.846 (95% confidence interval [CI] 0.819-0.873), sensitivity of 0.776 (95% CI, 0.732-0.820), and specificity of 0.759 (95% CI, 0.736-0.782), respectively. The accuracy was 0.762 (95% CI, 0.742-0.782). Age was identified as the most influential predictor of CAD risk within the studied dataset.

The Gradient Boosting machine learning model demonstrated superior performance in predicting CAD within the Taiwanese cohort, with age being a critical predictor. These findings underscore the potential of machine learning models in enhancing the prediction accuracy of CAD, thereby supporting early detection and targeted intervention strategies.

Not applicable.

Artificial intelligence (AI) based predictive models for early detection of cardiovascular disease (CVD) risk are increasingly being utilised. However, AI based risk prediction models that account for right-censored data have been overlooked. This systematic review (PROSPERO protocol CRD42023492655) includes 33 studies that utilised machine learning (ML) and deep learning (DL) models for survival outcome in CVD prediction. We provided details on the employed ML and DL models, eXplainable AI (XAI) techniques, and type of included variables, with a focus on social determinants of health (SDoH) and gender-stratification. Approximately half of the studies were published in 2023 with the majority from the United States. Random Survival Forest (RSF), Survival Gradient Boosting models, and Penalised Cox models were the most frequently employed ML models. DeepSurv was the most frequently employed DL model. DL models were better at predicting CVD outcomes than ML models. Permutation-based feature importance and Shapley values were the most utilised XAI methods for explaining AI models. Moreover, only one in five studies performed gender-stratification analysis and very few incorporate the wide range of SDoH factors in their prediction model. In conclusion, the evidence indicates that RSF and DeepSurv models are currently the optimal models for predicting CVD outcomes. This study also highlights the better predictive ability of DL survival models, compared to ML models. Future research should ensure the appropriate interpretation of AI models, accounting for SDoH, and gender stratification, as gender plays a significant role in CVD occurrence.