Predicting heart failure disease using machine learning

Yasser Hassan Basha; Ali Bou Nassif; Mohammad AlShabi

doi:10.1117/12.2632634

8 June 2022 Predicting heart failure disease using machine learning

Yasser Hassan Basha, Ali Bou Nassif, Mohammad AlShabi

Proceedings Volume 12123, Smart Biomedical and Physiological Sensor Technology XIX; 1212308 (2022) https://doi.org/10.1117/12.2632634
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Abstract

Heart failure (HF) is a common health condition that affects more than 600,000 Americans every year and results in their death. Luckily, machine learning classification, regression and prediction models are key approaches and techniques that can be used to detect and predict the cases of heart disease or failure. The study included in this paper based on a dataset that contains 918 instances or rows of various medical records. This research paper attempts to use these medical records to improve heart failure disease prediction accuracy. For that, multiple popular machine learning models were used to understand the data and provide a better prediction and results, based on different evaluation metrics. Furthermore, the results section in this study shows a better accuracy score compared with other related work using different machine learning algorithms and software. Finally, RStudio and Weka software are used in this paper to perform some of the algorithms and the best model results were using the random forest and logistic regression algorithms. These tools assisted us in better understanding of the data and data preprocessing.

Citation Download Citation

Yasser Hassan Basha, Ali Bou Nassif, and Mohammad AlShabi "Predicting heart failure disease using machine learning", Proc. SPIE 12123, Smart Biomedical and Physiological Sensor Technology XIX, 1212308 (8 June 2022); https://doi.org/10.1117/12.2632634

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available