Heart Disease Prediction Using Machine Learning Techniques

• Author(s): Baisani Indraja ; Sai Shreya Pola ; Nitish Jain ; Ullas Reddy CH ; Umesh Kumar M
• Paper ID: 1703297
• Page: 386-392
• Published Date: 25-03-2022
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 5 Issue 9 March-2022

Abstract

Heart related diseases are one of the dominant causes of death in emerging, developing, and even wealthy countries, with millions of people dying each year. Heart Disease refers to the state when the blood supply to the body's organs is cut off, resulting in a blood clot. Usually, this disease affects elderly people but with the drastic changes in the environment and their lifestyles, we can observe minor heart attack occurrences in middle-aged persons as well. This is a situation of major concern. In most cases, heart disease diagnosis relies on a complicated combination of clinical and pathological data. Consequently, clinical professionals and researchers are interested in how to accurately and efficiently predict what is happening in the heart. Some of the most common types of heart diseases are Heart Valve Disease, Coronary Artery Disease (CAD), Pericardial Disease, Heart Arrhythmias etc. The data contains factors such as age, gender, BP, cholesterol and many more that need to be considered and analyzed. This process can consume a lot of time and delays the treatment procedure. To achieve brisk results of the data examination, technology can be used. This project aims to predict heart disease both accurately and quickly by applying machine learning algorithms. The dataset we have used is from two online sources named Kaggle and UCI Machine learning Repository. The proposed model uses the dataset from above mentioned sources. The Correlation-based feature selection method determines the best features that correlate with the target class significantly. And also, check for features that do not contribute to determining the target and thus remove them. By using the parameter tuning method, the best tuning parameters are applied and then machine learning algorithms are implemented to train the model. The Stacked Ensemble method algorithm is used to obtain precise results.

Keywords

Data examination, Heart disease, technology, machine learning, Stacked Ensemble Method

Citations

IRE Journals:
Baisani Indraja , Sai Shreya Pola , Nitish Jain , Ullas Reddy CH , Umesh Kumar M "Heart Disease Prediction Using Machine Learning Techniques" Iconic Research And Engineering Journals Volume 5 Issue 9 2022 Page 386-392

IEEE:
Baisani Indraja , Sai Shreya Pola , Nitish Jain , Ullas Reddy CH , Umesh Kumar M "Heart Disease Prediction Using Machine Learning Techniques" Iconic Research And Engineering Journals, 5(9)