TY - JOUR
T1 - An update to the HIV-TRePS system: the development of new computational models that do not require a genotype to predict HIV treatment outcomes
T2 - The development of new computational models that do not require a genotype to predict HIV treatment outcomes
AU - Revell, Andrew D.
AU - Wang, Dechao
AU - Wood, Robin
AU - Morrow, Carl
AU - Tempelman, Hugo
AU - Hamers, Raph
AU - Alvarez-Uria, Gerardo
AU - Streinu-Cercel, Adrian
AU - Ene, Luminita
AU - Wensing, Annemarie
AU - Reiss, Peter
AU - van Sighem, Ard I.
AU - Nelson, Mark
AU - Emery, Sean
AU - Montaner, Julio S. G.
AU - Lane, H. Clifford
AU - Larder, Brendan A.
AU - AUTHOR GROUP
AU - van Sighem, Ard
AU - Montaner, Julio
AU - Harrigan, Richard
AU - Rinke de Wit, Tobias
AU - Sigaloff, Kim
AU - Agan, Brian
AU - Marconi, Vincent
AU - Wegner, Scott
AU - Sugiura, Wataru
AU - Zazzi, Maurizio
AU - Gatell, Jose
AU - Lazzari, Elisa
AU - Gazzard, Brian
AU - Pozniak, Anton
AU - Mandalia, Sundhiya
AU - Ruiz, Lidia
AU - Clotet, Bonaventura
AU - Staszewski, Schlomo
AU - Torti, Carlo
AU - Lane, Cliff
AU - Metcalf, Julie
AU - Perez-Elias, Maria-Jesus
AU - Carr, Andrew
AU - Norris, Richard
AU - Hesse, Karl
AU - Vlahakis, Emanuel
AU - Barth, Roos
AU - Dragovic, Gordana
AU - Cooper, David
AU - Baxter, John
AU - Monno, Laura
AU - Clotet, Bonventura
AU - Picchio, Gaston
PY - 2014/1/1
Y1 - 2014/1/1
N2 - 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. 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. 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. 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
AB - 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. 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. 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. 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
KW - Antiretroviral therapy
KW - Genotyping
KW - Resource-limited settings
UR - http://www.scopus.com/inward/record.url?scp=84896477071&partnerID=8YFLogxK
U2 - https://doi.org/10.1093/jac/dkt447
DO - https://doi.org/10.1093/jac/dkt447
M3 - Article
C2 - 24275116
SN - 0305-7453
VL - 69
SP - 1104
EP - 1110
JO - Journal of antimicrobial chemotherapy
JF - Journal of antimicrobial chemotherapy
IS - 4
M1 - dkt447
ER -