An Investigation of Classification Algorithms for Predicting HIV Drug Resistance without Genotype Resistance Testing. Lecture Notes in Computer Science (LNCS), 8315: 236-253 (2013).

Publication Latest Publications

Title: An Investigation of Classification Algorithms for Predicting HIV Drug Resistance without Genotype Resistance Testing
Authors: Brandt P, Moodley D, Pillay AW, Seebregts CJ, de Oliveira T.
Journal: Lecture Notes in Computer Science (LNCS),8315:236-253 (2013)

Journal Impact Factor (I.F.): 1.2
Number of citations (Google Scholar): 1

Abstract

The development of drug resistance is a major factor impeding the efficacy of antiretroviral treatment of South Africa?s HIV infected population. While genotype resistance testing is the standard method to determine resistance, access to these tests is limited in low-resource settings.

In this paper we investigate machine learning techniques for drug resistance prediction from routine treatment and laboratory data to help clinicians select patients for confirmatory genotype testing. The techniques, including binary relevance, HOMER, MLkNN, predictive clustering trees (PCT), RAkEL and ensemble of classifier chains were tested on a dataset of 252 medical records of patients enrolled in an HIV treatment failure clinic in rural KwaZulu-Natal in South Africa.

The PCT method performed best with a discriminant power of 1.56 for two drugs, above 1.0 for three others and a mean true positive rate of 0.68. These methods show potential for application where access to genotyping is limited.

Download: Full text paper

Citation: Brandt P, Moodley D, Pillay AW, Seebregts CJ, de Oliveira T. An Investigation of Classification Algorithms for Predicting HIV Drug Resistance without Genotype Resistance Testing Lecture Notes in Computer Science (LNCS),8315:236-253 (2013).


Sexual partnership age pairings and risk of HIV acquisition in rural South Africa
Journal: AIDS (2017)

Incidence rate estimation, periodic testing and the limitations of the mid-point imputation approach
Journal: International Journal of Epidemiology (2017)

Mutational Correlates of Virological Failure in Individuals Receiving a WHO-Recommended Tenofovir-Containing First-Line Regimen: An International Collaboration
Journal: EBioMedicine (2017)
All publications...


KwaZulu-Natal Research Innovation and Sequencing Platform (KRISP), K-RITH Tower Building, Nelson R Mandela School of Medicine, UKZN

Contact: Prof. Tulio de Oliveira, Tel: +27 31 260 4898, Email: tuliodna@gmail.com & deoliveira@ukzn.ac.za

Page design updated 2013. Many of the pages were previously hosted at bioafrica.net.