An evaluation of the random forest, chi-square, and mRMR feature selection methods on binary indicators of ACL injury risk

Harshit Pottipati; Aarush Bojja

doi:10.1117/12.2660661

6 December 2022 An evaluation of the random forest, chi-square, and mRMR feature selection methods on binary indicators of ACL injury risk

Harshit Pottipati, Aarush Bojja

Author Affiliations +

Proceedings Volume 12458, International Conference on Biomedical and Intelligent Systems (IC-BIS 2022); 124583I (2022) https://doi.org/10.1117/12.2660661
Event: International Conference on Biomedical and Intelligent Systems, 2022, Chengdu, China

Abstract

Driven by the increase in applications of Machine Learning in the medical industry and in biomedical engineering, we sought to aid in the creation of predictive models within the sports medicine field. In this paper, we look at a set of binary data of extrinsic factors that contribute to anterior cruciate ligament (ACL) injuries. We use multiple algorithms to select the most relevant feature that can be used to aid in making a predictive model. A dataset of binary data was compiled from 12639 sports matches. As a result, the extent of each condition was not able to be measured. Nonetheless, the data is used and is run through the Minimum Redundancy Maximum Relevance (mRMR), Chi-Square, and Random Forest processes. We also weigh the features by using a shallow artificial neural network with an input and output layer. Based on the results, the feature that was selected the most and was highest weighted was the condition of having low rainfall before the sports match.

Citation Download Citation

Harshit Pottipati and Aarush Bojja "An evaluation of the random forest, chi-square, and mRMR feature selection methods on binary indicators of ACL injury risk", Proc. SPIE 12458, International Conference on Biomedical and Intelligent Systems (IC-BIS 2022), 124583I (6 December 2022); https://doi.org/10.1117/12.2660661

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