Classification of Coronary Heart Disease Based on Community Health Centre Medical Record Data Using SVM Algorithm

Abstract

Coronary heart disease (CHD) is one of the leading causes of death worldwide and demands a fast and accurate diagnostic system, especially in community health centres (Puskesmas) where medical resources are limited. This study aims to develop a classification system for CHD using the Support Vector Machine (SVM) algorithm based on numerical medical record data. It also addresses the gap in previous studies that rarely applied SVM to tabular data from primary healthcare facilities. The methodology includes variable weighting, min-max normalization, model training with a linear kernel, and performance evaluation using a confusion matrix. The dataset consists of 100 patient records with variables such as age, blood pressure, heart rate, respiratory rate, and chest pain. The results show that the SVM model achieved an accuracy of 95%, a precision of 100%, recall of 88.9%, and an F1-score of 94.1%. The model was further integrated into a web-based application using Flask to support automated early diagnosis. This study demonstrates that SVM is effective in classifying heart disease based on medical records and offers a practical solution to improve healthcare service quality in Puskesmas.