An Interpretable and Explainable Logistic Regression Based Model for Heart Disease Prediction

Cardiovascular disorders remain a dominant contributor to global mortality, emphasizing the importance of timely risk assessment and preventive intervention. The expansion of electronic medical data combined with advancements in computational intelligence has enabled the development of predictive systems that assist clinical evaluation. This work presents a clinical decision support framework that applies logistic regression to estimate the probability of heart disease using patient-specific clinical indicators. Due to its statistical foundation, low computational demand, and interpretability, logistic regression is particularly suitable for medical environments where explainability is essential. Experimental evaluation demonstrates that the model provides consistent predictive performance and identifies influential risk variables, supporting its applicability in early-stage cardiovascular risk screening.