@conference{97,
  author = {Pascal Brandt and Deshen Moodley and Anban Pillay and Chris Seebregts and T. de Oliveira},
  title = {An Investigation of Classification Algorithms for Predicting HIV Drug Resistance Without Genotype Resistance Testing},
  abstract = {The development of drug resistance is a major factor imped- ing the efficacy of antiretroviral treatment of South Africa{\textquoteright}s HIV infected population. While genotype resistance testing is the standard method to determine resistance, access to these tests is limited in low-resource set- tings. 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 tech- niques, including binary relevance, HOMER, MLkNN, predictive clus- tering trees (PCT), RAkEL and ensemble of classifier chains were tested on a dataset of 252 medical records of patients enrolled in an HIV treat- ment 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.},
  year = {2014},
  journal = {Third International Symposium on Foundations of Health Information Engineering and Systems},
  chapter = {236-253},
  month = {21/08-23/08},
  isbn = {978-3-642-53955-8},
  url = {http://link.springer.com/chapter/10.1007/978-3-642-53956-5_16},
}