Jul 2026· International Journal of Research in Medical Sciences· 0 citations· 30 references
TL;DR
It was demonstrated that machine learning (ML) and deep learning (DL) models consistently outperformed conventional cardiovascular risk prediction tools, achieving area under the receiver operating characteristic curve (AUC) values ranging from 0.80-0.99 across various cardiovascular conditions.
Abstract
Cardiovascular disease (CVD) remains the leading cause of morbidity and mortality worldwide, necessitating improved approaches for early detection and risk stratification. Traditional cardiovascular risk assessment models often demonstrate limited predictive accuracy because they rely on a restricted number of clinical variables and linear statistical relationships. Artificial intelligence (AI)-driven predictive analytics has emerged as a promising solution capable of processing large, complex, and multidimensional healthcare datasets to improve cardiovascular risk prediction and clinical decision-making. This systematic review aimed to evaluate the effectiveness of AI-based predictive models for the early detection and risk stratification of CVD. A comprehensive literature search was conducted across PubMed/MEDLINE, Scopus, Web of Science, Embase, CINAHL, IEEE Xplore, and the Cochrane Library for studies published between January 2015 and December 2025. A total of 130 studies involving approximately 12.8 million participants met the eligibility criteria and were included in the review. The findings demonstrated that machine learning (ML) and deep learning (DL) models consistently outperformed conventional cardiovascular risk prediction tools, achieving area under the receiver operating characteristic curve (AUC) values ranging from 0.80-0.99 across various cardiovascular conditions. The strongest evidence was observed in the prediction of coronary artery disease, heart failure, atrial fibrillation, stroke, and major adverse cardiovascular events. Electronic health records, electrocardiography, medical imaging, wearable devices, and multimodal datasets were the most commonly utilized data sources. Despite their promising performance, challenges related to external validation, interpretability, algorithmic bias, and clinical implementation remain.
Evidence is provided that ensemble-based frameworks currently offer the most effective balance between predictive accuracy, robustness, and clinical feasibility, and future research should emphasize multi-center external validation and explainable AI frameworks.
Marium Shaikh, Hanmant Fadewar· International Journal For Mu...· 0 citations
Cardiovascular disease is a main cause of mortality worldwide that need the development of reliable and data-driven prediction models for timely diagnosis and intervention. Conventional risk assessment methods depend on statistical scoring and handcrafted clinical features fail to capture complex nonlinear features in several cardiovascular existing data. This systematic literature review investigates recent advances in artificial intelligence-based CVD prediction that include machine learning, deep learning, hybrid, and ensemble learning models. The PRISMA-2020 strategy and Kitchenham guidelines, 110 studies published between 2013 and 2025 were systematically analyzed across diverse data modalities such as electronic health records, electrocardiograms, medical images, wearable sensors, and multimodal datasets. The findings indicate that tree-based ML models such as Random Forest, XGBoost, and Gradient Boosting shows the strong performance on structured clinical datasets. The DL-based models such as convolutional neural networks, long short-term memory networks, and transformer-based models effectively capture the high-dimensional physiological and imaging features. Hybrid model combined deep representations with clinical parameters to achieve predictive performance up to 98.00%, and ensemble learning models shows the superior performance and generalization capabilities across several distinct datasets. The challenges in cardiovascular disease detection such as limited multimodal datasets, very few external validation, insufficient explainability, and the absence of standardized benchmark evaluation parameters continue to show down the clinical translation. This review synthesizes current algorithmic developments, identifies critical research gaps, and highlights the potential of multimodal learning, explainable AI, federated learning, and clinically validated model for advancing next-generation cardiovascular risk prediction systems.
Anuja Gaikwad, Nilima Kulkarnir· Journal of Intelligent Decis...· 0 citations
There is an urgent need for explainable, clinically validated and standardised ML frameworks to translate predictive models into routine healthcare practice and improve early detection of cardiovascular disease.
Hanna Rasheed, Arya.K.R Arya.K.R, Ashida.K.A Ashida.K.A· International Journal of Tec...· 0 citations
Cardiovascular diseases (CVDs) remain a major cause of morbidity and mortality worldwide, emphasizing the need for reliable methods that can identify high-risk individuals at an early stage. Although machine learning and deep learning approaches have demonstrated considerable potential for cardiovascular risk prediction, their limited interpretability often restricts their acceptance in clinical decision-making. This study proposes an Explainable AI-Driven Decision Support System (XAI-DSS) for the early prediction of cardiovascular diseases by integrating intelligent clinical data preprocessing, feature selection, an ensemble learning-based prediction model, and explainable artificial intelligence. The framework processes heterogeneous cardiovascular risk factors, including demographic characteristics, blood pressure, cholesterol, glucose levels, electrocardiographic attributes, lifestyle factors, and other relevant clinical indicators. A hybrid feature-selection strategy is employed to identify the most informative risk variables, while an optimized ensemble classifier generates patient-specific CVD risk predictions. Explainability is incorporated using SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) to provide both global and patient-level interpretations of model decisions. Experimental evaluation demonstrated an accuracy of 96.42%, sensitivity of 95.81%, specificity of 96.87%, precision of 96.15%, F1-score of 95.98%, and area under the ROC curve (AUC) of 0.982. Compared with the selected baseline machine-learning model, the proposed XAI-DSS achieved an approximately 4.7% improvement in prediction accuracy and 5.3% improvement in F1-score. Explainability analysis further identified age, systolic blood pressure, cholesterol, maximum heart rate, fasting blood glucose, and chest-pain characteristics as influential factors contributing to cardiovascular risk predictions. The proposed framework therefore combines high predictive performance with transparent clinical reasoning, enabling healthcare professionals to understand the factors influencing individual risk assessments. The developed XAI-DSS can serve as a supportive screening framework for early cardiovascular risk stratification and informed clinical decision-making, subject to external clinical validation.
K. Sridhar, S. Swathi, S. Saranya et al.· International journal of com...· 0 citations
This systematic review analyses the effectiveness of integrated AI‐based hypertension prediction and management systems those integrate real‐time oversight, interpretable risk prediction, customized lifestyle intervention, clinical decision support, and early warning procedure.
Overall, AI outlines the transition from a reactive cardiology model toward a predictive, proactive, and precision-based approach in cardiovascular prevention, with a specific focus on risk stratification, early detection of subclinical disease, and identification of patients most likely to benefit from targeted interventions.
Simona Giubilato, L. Granata, S. Petrina· Giornale italiano di cardiol...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
