Development of a Classification Model for CD4 Count of HIV Patients Using Supervised Machine Learning Algorithms: A Comparative Analysis

Development of a Classification Model for CD4 Count of HIV Patients Using Supervised Machine Learning Algorithms: A Comparative Analysis

Peter Adebayo Idowu, Jeremiah Ademola Balogun
ISBN13: 9781522574675|ISBN10: 1522574670|EISBN13: 9781522574682
DOI: 10.4018/978-1-5225-7467-5.ch006
Cite Chapter Cite Chapter

MLA

Idowu, Peter Adebayo, and Jeremiah Ademola Balogun. "Development of a Classification Model for CD4 Count of HIV Patients Using Supervised Machine Learning Algorithms: A Comparative Analysis." Computational Models for Biomedical Reasoning and Problem Solving, edited by Chung-Hao Chen and Sen-Ching Samson Cheung, IGI Global, 2019, pp. 149-176. https://doi.org/10.4018/978-1-5225-7467-5.ch006

APA

Idowu, P. A. & Balogun, J. A. (2019). Development of a Classification Model for CD4 Count of HIV Patients Using Supervised Machine Learning Algorithms: A Comparative Analysis. In C. Chen & S. Cheung (Eds.), Computational Models for Biomedical Reasoning and Problem Solving (pp. 149-176). IGI Global. https://doi.org/10.4018/978-1-5225-7467-5.ch006

Chicago

Idowu, Peter Adebayo, and Jeremiah Ademola Balogun. "Development of a Classification Model for CD4 Count of HIV Patients Using Supervised Machine Learning Algorithms: A Comparative Analysis." In Computational Models for Biomedical Reasoning and Problem Solving, edited by Chung-Hao Chen and Sen-Ching Samson Cheung, 149-176. Hershey, PA: IGI Global, 2019. https://doi.org/10.4018/978-1-5225-7467-5.ch006

Export Reference

Mendeley
Favorite

Abstract

This chapter was developed with a view to present a predictive model for the classification of the level of CD4 count of HIV patients receiving ART/HAART treatment in Nigeria. Following the review of literature, the pre-determining factors for determining CD4 count were identified and validated by experts while historical data explaining the relationship between the factors and CD4 count level was collected. The predictive model for CD4 count level was formulated using C4.5 decision trees (DT), support vector machines (SVM), and the multi-layer perceptron (MLP) classifiers based on the identified factors which were formulated using WEKA software and validated. The results showed that decision trees algorithm revealed five (5) important variables, namely age group, white blood cell count, viral load, time of diagnosing HIV, and age of the patient. The MLP had the best performance with a value of 100% followed by the SVM with an accuracy of 91.1%, and both were observed to outperform the DT algorithm used.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.