An update to the HIV-TRePS system: The development of new computational models that do not require a genotype to predict HIV treatment outcomes

Andrew D. Revell*, Dechao Wang, Robin Wood, Carl Morrow, Hugo Tempelman, Raph Hamers, Gerardo Alvarez-Uria, Adrian Streinu-Cercel, Luminita Ene, Annemarie Wensing, Peter Reiss, Ard I. Van Sighem, Mark Nelson, Sean Emery, Julio S.G. Montaner, H. Clifford Lane, Brendan A. Larder, Ard Van sighem, Richard Harrigan, Tobias Rinke de WitKim Sigaloff, Brian Agan, Vincent Marconi, Scott Wegner, Wataru Sugiura, Maurizio Zazzi, Jose Gatell, Elisa Lazzari, Brian Gazzard, Anton Pozniak, Sundhiya Mandalia, Lidia Ruiz, Bonaventura Clotet, Schlomo Staszewski, Carlo Torti, Julie Metcalf, Maria Jesus Perez-Elias, Andrew Carr, Richard Norris, Karl Hesse, Emanuel Vlahakis, Roos Barth, Gordana Dragovic

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

10 Scopus citations


Objectives: The optimal individualized selection of antiretroviral drugs in resource-limited settings is challenging because of the limited availability of drugs and genotyping. Here we describe the development of the latest computational models to predict the response to combination antiretroviral therapy without a genotype, for potential use in such settings. Methods: Random forest models were trained to predict the probability of a virological response to therapy (<50 copies HIV RNA/mL) following virological failure using the following data from 22 567 treatment-change episodes including 1090 from southern Africa: baseline viral load and CD4 cell count, treatment history, drugs in the new regimen, time to follow-up and follow-up viral load. The models were assessed during cross-validation and with an independent global test set of 1000 cases including 100 from southern Africa. The models' accuracy [area under the receiver-operating characteristic curve (AUC)] was evaluated and compared with genotyping using rules-based interpretation systems for those cases with genotypes available. Results: The models achieved AUCs of 0.79-0.84 (mean 0.82) during cross-validation, 0.80 with the global test set and 0.78 with the southern African subset. The AUCs were significantly lower (0.56-0.57) for genotyping. Conclusions: The models predicted virological response to HIV therapy without a genotype as accurately as previous models that included a genotype. They were accurate for cases from southern Africa and significantly more accurate than genotyping. These models will be accessible via the online treatment support tool HIV-TRePS and have the potential to help optimize antiretroviral therapy in resource-limited settings where genotyping is not generally available.

Original languageEnglish
Article numberdkt447
Pages (from-to)1104-1110
Number of pages7
JournalJournal of Antimicrobial Chemotherapy
Issue number4
StatePublished - Apr 2014


  • Antiretroviral therapy
  • Genotyping
  • Resource-limited settings


Dive into the research topics of 'An update to the HIV-TRePS system: The development of new computational models that do not require a genotype to predict HIV treatment outcomes'. Together they form a unique fingerprint.

Cite this