INFERENTIAL STATISTICS DRIVEN LOGISTIC REGRESSION MODEL FOR CARDIOVASCULAR DISEASE PREDICTION

Cardiovascular diseases (CVDs) are widely recognisedas primary contributors to global mortality, necessitatingthe development of precise predictive models that provideclear explanations for early detection and facilitate effectiveinterventions. A logistic regression model incorporating inferential statistical methods into the analysis offers a solution for enhanced reliability and interpretability in predicting cardiovascular diseases using clinical data. The analysis employed correlation tests, combined with chi-squaretests and independent t-statistics, to identify key factors,including patient age, blood pressure, cholesterol levels, glucose measures, exercise activity, smoking habits, and alcohol intake. The model generalisation improved significantlyby using the Synthetic Minority Over-sampling Technique(SMOTE) to manage class imbalance problems. The implemented model attained exceptional scores with a 95.2% accuracy rate, 94.8% precision, 96.1% recall, 95.4% F1-score,and 97.2% AUC-ROC. Real-time Medical applications andreliability assessments rely on confusion matrix analysis,ROC curve examination, calibration plots, and feature importance assessment. The training loss curves verified thatconvergence occurred during the training process. The analytical results demonstrate that logistic regression performswell, generating computations that are both clinically usefuland statistically comprehensive, while promoting preventivecardiovascular healthcare