Heart Disease Prediction: An End-to-End ML Pipeline

Engineered an end-to-end ML pipeline to predict heart disease with 92.2% recall—critical for minimizing missed diagnoses in clinical settings. Processed 918 patient records using KNN imputation and scikit-learn pipelines. Trained and validated 7 classifiers via 5-fold cross-validation; selected Logistic Regression for its high recall, interpretability, and clinical reliability. Achieved 89.7% accuracy and 0.933 ROC AUC. Delivered a production-ready model (joblib), fully documented and reproducible in Jupyter.