Assessing heart disease severeness via machine learning techniques

Xinwei Wang

doi:10.1117/12.2692725

23 August 2023 Assessing heart disease severeness via machine learning techniques

Xinwei Wang

Proceedings Volume 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023); 1278430 (2023) https://doi.org/10.1117/12.2692725
Event: 2023 2nd International Conference on Applied Statistics, Computational Mathematics and Software Engineering (ASCMSE 2023), 2023, Kaifeng, China

Abstract

The aim of this study was to discover the correlation between the risk and severeness of heart disease with a variety of risk factors by fitting the most appropriate model in python. Regarding the models in this paper, logistic regression model, multinomial regression model, decision tree, neural network model and gradient boosting classifier model were applied. The merits and drawbacks were discussed in this paper using appropriate statistics. During the section of model fitting, imbalances in the data were identified and SMOTE instruments were used to deal with the uneven data across categories. The gradient boosting classifier model was therefore used as a combined random forest and booster synthesis model to fit this data to the final model. The accuracy of the final model was 82%, which proved to be reliable for summarizing the characteristics in the data. The study found that age had the greatest association with heart disease, with the risk of heart disease increasing or the severity of heart disease tending to worsen with age. In addition, men were found to have a slightly higher risk of heart disease than women. And elevated cholesterol levels are associated with an increased risk of heart disease.

Citation Download Citation

Xinwei Wang "Assessing heart disease severeness via machine learning techniques", Proc. SPIE 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023), 1278430 (23 August 2023); https://doi.org/10.1117/12.2692725

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