Published Paper Details:

: Heart disease remains one of the leading causes of mortality globally, necessitating the development of early and accurate diagnostic tools. This project focuses on predicting the likelihood of heart attacks using various machine learning (ML) algorithms. A publicly available clinical dataset, including features such as age, gender, chest pain type, blood pressure, cholesterol, and ECG results, is used for training and evaluation. The dataset undergoes preprocessing steps including data cleaning, normalization, and feature encoding. Supervised learning algorithms including Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Decision Tree, and Random Forest are implemented and compared based on performance metrics such as accuracy, precision, recall, F1-score, and ROC-AUC. The Random Forest algorithm outperformed others in terms of accuracy and generalization ability. The system is integrated into an Android application using Firebase as a backend service, enabling real-time user interaction and prediction delivery. The study demonstrates that ensemble learning methods offer robust and interpretable solutions for heart disease prediction, which can support clinical decision-making and preventive care. Future enhancements may include integration with wearable devices and deployment in real-time hospital environments.