Prediction of Heart Disease Using Ensemble Machine Learning Techniques
TL;DR
The proposed XGBoost model was developed for heart disease risk assessment and evaluated using accuracy, precision, recall, and F1-score, demonstrating its effectiveness and reliability for accurate heart disease prediction.
Abstract
In this current world, keep hearing about heart disease problems every day and about the deaths due to them, making heart disease a major contributor to the crucial mortality rate worldwide. According to the World Health Organization (WHO), an estimated 17.9 million individuals die from cardiovascular diseases (CVDs) each year. The identification of cardiovascular disease states, including cardiac arrhythmia and coronary heart disease, based on traditional clinical data analysis is still a big challenge. The early diagnosis of cardiac disease can enable timely medical treatment and save many lives. The use of machine learning (ML) algorithms enables intelligent decision-making and accurate disease prediction by identifying complex patterns in healthcare data. This study adopted the following preprocessing methods for the UCI Heart Disease dataset: missing-value treatment, duplicate removal, noise reduction, one-hot encoding, Z-score normalization, and SMOTE data balancing. The proposed XGBoost model was developed for heart disease risk assessment and evaluated using accuracy, precision, recall, and F1-score. The proposed model achieved 99.8% accuracy, 99.7% precision, 99.9% recall, and 99.6% F1-score, demonstrating its effectiveness and reliability for accurate heart disease prediction.