Computational models can predict response to HIV therapy without a genotype and may reduce treatment failure in different resource-limited settings.

OBJECTIVES Genotypic HIV drug-resistance testing is typically 60%-65% predictive of response to combination antiretroviral therapy (ART) and is valuable for guiding treatment changes. Genotyping is unavailable in many resource-limited settings (RLSs). We aimed to develop models that can predict response to ART without a genotype and evaluated their potential as a treatment support tool in RLSs. METHODS Random forest models were trained to predict the probability of response to ART (≤400 copies HIV RNA/mL) using the following data from 14 891 treatment change episodes (TCEs) after virological failure, from well-resourced countries: viral load and CD4 count prior to treatment change, treatment history, drugs in the new regimen, time to follow-up and follow-up viral load. Models were assessed by cross-validation during development, with an independent set of 800 cases from well-resourced countries, plus 231 cases from Southern Africa, 206 from India and 375 from Romania. The area under the receiver operating characteristic curve (AUC) was the main outcome measure. RESULTS The models achieved an AUC of 0.74-0.81 during cross-validation and 0.76-0.77 with the 800 test TCEs. They achieved AUCs of 0.58-0.65 (Southern Africa), 0.63 (India) and 0.70 (Romania). Models were more accurate for data from the well-resourced countries than for cases from Southern Africa and India (P < 0.001), but not Romania. The models identified alternative, available drug regimens predicted to result in virological response for 94% of virological failures in Southern Africa, 99% of those in India and 93% of those in Romania. CONCLUSIONS We developed computational models that predict virological response to ART without a genotype with comparable accuracy to genotyping with rule-based interpretation. These models have the potential to help optimize antiretroviral therapy for patients in RLSs where genotyping is not generally available.

[1]  Douglas D. Richman,et al.  Antiretroviral Treatment of Adult HIV Infection , 2008 .

[2]  Brendan Larder,et al.  A Comparison of Three Computational Modelling Methods for the Prediction of Virological Response to Combination Hiv Therapy Author's Personal Copy , 2022 .

[3]  A. Breckenridge,et al.  Routine versus clinically driven laboratory monitoring of HIV antiretroviral therapy in Africa (DART): a randomised non-inferiority trial , 2010, The Lancet.

[4]  Lynn Morris,et al.  Impact of HIV-1 Subtype and Antiretroviral Therapy on Protease and Reverse Transcriptase Genotype: Results of a Global Collaboration , 2005, PLoS medicine.

[5]  Michael Rayment,et al.  Prevention of HIV-1 infection with early antiretroviral therapy , 2012, Journal of Family Planning and Reproductive Health Care.

[6]  N. McGrath,et al.  Population-level effect of HIV on adult mortality and early evidence of reversal after introduction of antiretroviral therapy in Malawi , 2008, The Lancet.

[7]  J. A. Robinson.  Clinics , 1883, The Dental register.

[8]  B. Chi,et al.  Outcomes of antiretroviral treatment in programmes with and without routine viral load monitoring in southern Africa , 2011, AIDS.

[9]  Peter M. A. Sloot,et al.  Comparison of HIV-1 Genotypic Resistance Test Interpretation Systems in Predicting Virological Outcomes Over Time , 2010, PloS one.

[10]  Brendan Larder,et al.  The Development of Artificial Neural Networks to Predict Virological response to Combination HIV Therapy , 2007, Antiviral therapy.

[11]  Lesley E Scott,et al.  Quantifying HIV for monitoring antiretroviral therapy in resource-poor settings. , 2010, The Journal of infectious diseases.

[12]  A. Wensing,et al.  Modelling response to HIV therapy without a genotype: an argument for viral load monitoring in resource-limited settings. , 2010, The Journal of antimicrobial chemotherapy.

[13]  N. Parkin,et al.  The public health approach to identify antiretroviral therapy failure: high-level nucleoside reverse transcriptase inhibitor resistance among Malawians failing first-line antiretroviral therapy , 2009, AIDS.

[14]  A. Wensing,et al.  Accumulation of Drug Resistance and Loss of Therapeutic Options Precede Commonly Used Criteria for Treatment Failure in HIV-1 Subtype-C-Infected Patients , 2012, Antiviral therapy.

[15]  G. Alvarez-Uria,et al.  Gender differences, routes of transmission, socio-demographic characteristics and prevalence of HIV related infections of adults and children in an HIV cohort from a rural district of India , 2012, Infectious disease reports.

[16]  T. F. Rinke de Wit,et al.  COHORT PROFILE Cohort Profile: The PharmAccess African , 2022 .

[17]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[18]  B. Gazzard,et al.  Clinical evaluation of the potential utility of computational modeling as an HIV treatment selection tool by physicians with considerable HIV experience. , 2011, AIDS patient care and STDs.

[19]  Amalio Telenti,et al.  Antiretroviral Treatment of Adult HIV Infection2010 Recommendations of the International AIDS Society–USA Panel , 2010 .

[20]  S. Hammer,et al.  Antiretroviral therapy for HIV infection in 1998: updated recommendations of the International AIDS Society-USA Panel. , 1997, JAMA.

[21]  Sabine Yerly,et al.  Virological monitoring and resistance to first-line highly active antiretroviral therapy in adults infected with HIV-1 treated under WHO guidelines: a systematic review and meta-analysis. , 2009, The Lancet. Infectious diseases.

[22]  J. Kestle.  Clinical Trials , 2014, World Journal of Surgery.

[23]  P. Phanuphak,et al.  Deferred modification of antiretroviral regimen following documented treatment failure in Asia: results from the TREAT Asia HIV Observational Database (TAHOD) , 2009, HIV medicine.

[24]  B. Larder,et al.  The development of an expert system to predict virological response to HIV therapy as part of an online treatment support tool , 2011, AIDS.

[25]  Thomas Lengauer,et al.  Prediction of response to antiretroviral therapy by human experts and by the EuResist data‐driven expert system (the EVE study) , 2010, HIV medicine.

[26]  Tommy F. Liu,et al.  Web resources for HIV type 1 genotypic-resistance test interpretation. , 2006, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[27]  References , 1971 .

[28]  T. F. Rinke de Wit,et al.  Unnecessary Antiretroviral Treatment Switches and Accumulation of HIV Resistance Mutations; Two Arguments for Viral Load Monitoring in Africa , 2011, Journal of acquired immune deficiency syndromes.

[29]  Rolf Kaiser,et al.  Correction: Antiretroviral Therapy Optimisation without Genotype Resistance Testing: A Perspective on Treatment History Based Models , 2011, PLoS ONE.