A Multi-Class Heart Disease and Stroke Risk Classification Framework for Combined Assessment: A Machine Learning Approach

Enhancing Cardiovascular Risk Prediction with Explainable AI using Clinical Data

Diabetes is a major risk factor for the development of cardiovascular issues which contribute to cardiovascular disease (CVD) being a leading cause of mortality worldwide. However, traditional machine learning methods are not widely adopted in healthcare systems because they lack interpretability, which is important for early and accurate CVD risk prediction and for ruling out effective clinical intervention. In this research, a hybrid architecture is proposed that incorporates diabetes related datasets as well as explainable artificial intelligence (XAI) methodologies that could improve the prediction power and transparency of the models. The proposed approach combines different datasets at the level of features and includes rigorous data pre-processing to detect metabolic and cardiovascular risk factors. Some of the significant clinical parameters are age, BMI, glucose, cholesterol, and blood pressure. These are standardized to create a single dataset which may be utilized for predictive modelling. The employment of two XAI approaches, SHAP (SHapley Additive Explanations) with tree-based ensemble models and integrated gradients with transformer based topologies, ensures both performance and interpretability. The technique improves confidence and usefulness in clinical settings by offering accurate predictions and explanations for the model’s judgments that are relevant to the circumstance. It is also utilized for visual investigation of clinical correlations of diabetes and cardiovascular disease and identify crucial risk variables. The results suggest that merging explainability approaches with powerful machine learning can considerably boost early identification and risk assessment. The proposed approach contributes to enhanced healthcare decision-making, offering a scalable, interpretable and dependable solution for cardiovascular disease prediction.

MACHINE LEARNING-BASED PREDICTION OF HEART FAILURE MORTALITY USING CLINICAL BIOMARKERS AND IMBALANCED DATA STRATEGIES

It is demonstrated that machine learning models can effectively identify high-risk patients and that minority data resampling significantly improves mortality classification reliability, and the approach offers potential value for clinical decision support systems and prioritised care pathways.

Machine Learning–based Multi-Disease Prediction

This paper proposes a machine learning–based multi-disease prediction system that integrates disease-specific classifiers within a unified, real-time clinical decision-support platform. The framework employs Support Vector Machine (RBF) for diabetes prediction, Support Vector Machine (linear) for heart disease, Decision Tree for chronic kidney disease (CKD), and Logistic Regression for cancer prediction, with each classifier selected according to the statistical characteristics of its respective dataset. The system is implemented using a Streamlit-based web interface, enabling efficient real-time prediction with interpretable outputs. Experimental evaluation demonstrates strong predictive performance, achieving accuracies ranging from 85.71% to 94.30% and AUC-ROC values between 0.91 and 0.97 across the four disease modules, representing a 7.2 percentage-point improvement over comparable unified prediction systems reported in the literature. The modular architecture provides scalability, low computational complexity, and rapid inference, making it suitable for pre-diagnostic screening in clinical environments. The proposed framework offers an effective and practical solution for early chronic disease detection while supporting future expansion. Planned enhancements include the integration of deep learning models for medical imaging and electronic health records, Explainable Artificial Intelligence (XAI) techniques such as SHAP and LIME, wearable and IoT-based continuous health monitoring, federated learning for privacy-preserving distributed model training, and prospective clinical validation through hospital information system integration. These developments are expected to improve prediction accuracy, interpretability, scalability, and clinical applicability for next-generation intelligent healthcare systems.

PREDICTING HEART DISEASE RISK FROM CLINICAL VARIABLES: A GENDER-SPECIFIC MACHINE LEARNING ANALYSIS AMONG HIGH-CHOLESTEROL PATIENTS

Male sex was a statistically significant independent predictor of heart disease after controlling for other clinical variables and the findings support sex-specific screening and preventive strategies for high-cholesterol male patients and demonstrate the value of interpretable machine learning models for clinical decision support.

Explainable Ensemble Learning for Cardiovascular Risk Stratification A Multi-Hospital Stacking Approach with SHAP-Based Clinical Decision Support

Cardiovascular disease (CVD) remains the leading cause of mortality worldwide, necessitating accurate and interpretable risk stratification for clinical decision support. This paper presents an explainable stacking ensemble framework for binary heart disease classification and three-tier risk stratification using multi-hospital cardiac data. The approach integrates five heterogeneous base learners — Random Forest, XGBoost, Gradient Boosting, Extra Trees, and Support Vector Machine — with a Logistic Regression meta-learner trained via 5-fold cross-validation. A clinically motivated preprocessing pipeline incorporates eight engineered interaction features, RobustScaler normalization, threshold-optimized prediction (threshold = 0.82), and a novel Dual-Balanced SMOTE strategy that simultaneously addresses class imbalance and gender bias. Evaluated on the Cleveland UCI Heart Disease dataset (303 patients, 20% holdout, n = 61), the model achieves 96.72% accuracy, 0.9935 AUC-ROC, and zero false negatives at the optimal threshold. SHAP (SHapley Additive exPlanations) provides global and per-patient interpretability, identifying chest pain type (cp_4), the age–oldpeak interaction, and exercise-induced angina as the most influential predictors. The system is deployed as an end-to-end Flask web application (CardioRisk AI) enabling real-time clinical inference with SHAP waterfall visualizations and gender fairness evaluation confirming an F1 gap below 5% between male and female subgroups.

The heart disease prediction using machine learning algorithms