A Retrospective Assessment of Machine Learning Models in Heart Rate Prediction

Using Random Forest and Logistic Regression

Abstract

Applications of data mining are wide and diverse. Among this health care is a major application of data mining. Heart Disease is the most dangerous life-threatening chronic disease globally. Coronary artery diseases specifically heart-related incidents, persist as prominent contributors to global mortality rates. Timely identification and precise prediction of such incidents hold paramount importance for proactive intervention and minimizing unfavorable consequences. Leveraging a dataset sourced from Kaggle, comprising 303 patient samples and 13 features, our research explores the comparative performance of these machine learning algorithms. Surprisingly, both Random Forest and Logistic Regression models demonstrate identical accuracy rates of 86% in predicting heart rates. This parity in performance prompts further investigation into the underlying factors influencing model convergence. Finally, we stress the significance of thorough model evaluation that goes beyond accuracy, especially when dealing with imbalanced datasets.