Heart Disease Prediction using Machine Learning
Aadib Malim, Kaif Kalokhe, Nouman Kupe, Aquib Mulla, Kirti Karande
Department of Artificial inntelligence and Machine Learning
Anjuman I Islam Abdul Razzaq Kalsekar Polytechnique,
Panvel, India – 410206
Abstract
Machine Learning (ML) is increasingly applied in various sectors globally, and the healthcare sector is no exception. In particular, ML can significantly contribute to the early detection of locomotor disorders and heart diseases. Timely predictions can offer valuable insights to physicians, enabling them to tailor their diagnostic and treatment strategies for individual patients. This project focuses on the use of ML algorithms to predict the likelihood of heart disease in individuals. It involves a comparative analysis of several classifiers, including decision trees, Naïve Bayes, Logistic Regression, SVM, and Random Forest. Furthermore, the project introduces an ensemble classifier that combines the strengths of both robust and less robust classifiers. This approach allows for the utilization of numerous samples for training and validation purposes. We analyze both existing classifiers and proposed classifiers like AdaBoost and XGBoost, aiming to enhance accuracy and predictive capabilities.Heart disease remains a significant concern worldwide, and early detection is crucial for preventing severe outcomes and enhancing patient care. Machine learning techniques have shown promise in increasing the accuracy of heart disease predictions. This paper discusses the use of ML in predicting heart disease, emphasizing its potential advantages and the challenges encountered. The main goal of this research is to assess the performance of various ML algorithms in predicting heart disease risk based on patient data. The dataset comprises a wide array of variables, including age, gender, blood pressure, cholesterol levels, exercise patterns, and medical history. After preprocessing these variables, we train and test several ML models, such as Logistic Regression, Random Forest, and Support Vector Machines (SVM), to evaluate their effectiveness.
