Automated Machine Learning Model for the Heart Disease Prediction System

Abstract

Early and accurate prediction methods are necessary to improve patient outcomes due to the fact that heart disease is still a significant cause of mortality globally. In this study, we introduce the Heart Disease Prediction System (HDPS), an AI-powered tool that uses clinical variables including age, gender, cholesterol, blood pressure, and heart rate to aid doctors in making accurate diagnoses of cardiac diseases. The medical datasets were analysed using a variety of machine learning methods, including Decision Tree, Random Forest, Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbours, and Random Forest. Out of all the algorithms, Random Forest achieved the best accuracy, reaching 90.5%. The system leverages automated model selection, performance evaluation, and feature optimization to reduce manual effort and enhance efficiency. Through rigorous experimentation and epoch-based analysis, the model demonstrated high reliability and consistency in prediction. The system’s user-friendly interface further promotes ease of use in clinical settings. Early diagnosis, personalised treatment planning, and enhanced patient care are all possible outcomes of incorporating AutoML into healthcare, as this study highlights. To further boost clinical value, future study will examine integration with explainable AI and real-time wearable data.

Ähnliche Arbeiten