Super learner analysis of electronic adherence data improves viral prediction and may provide strategies for selective HIV RNA monitoring
Published Date:May 1 2015
Source:J Acquir Immune Defic Syndr. 69(1):109-118.
Decision Support Techniques
HIV RNA Monitoring
Medication Event Monitoring System
Pubmed Central ID:PMC4421909
Funding:AI069419/AI/NIAID NIH HHS/United States
AI38858/AI/NIAID NIH HHS/United States
CC02-SD-003/CC/ODCDC CDC HHS/United States
CC99-SD003/CC/ODCDC CDC HHS/United States
K02DA017277/DA/NIDA NIH HHS/United States
K08 MH01584/MH/NIMH NIH HHS/United States
K23 MH087228/MH/NIMH NIH HHS/United States
K23MH01862/MH/NIMH NIH HHS/United States
K23MH087228/MH/NIMH NIH HHS/United States
P01MH49548/MH/NIMH NIH HHS/United States
P30 AI050410/AI/NIAID NIH HHS/United States
P30 MH043520/MH/NIMH NIH HHS/United States
P30 MH062294/MH/NIMH NIH HHS/United States
P30-AI50410/AI/NIAID NIH HHS/United States
R01 AI074345/AI/NIAID NIH HHS/United States
R01 MH068197/MH/NIMH NIH HHS/United States
R01 MH078773/MH/NIMH NIH HHS/United States
R01AI41413/AI/NIAID NIH HHS/United States
R01DA015679/DA/NIDA NIH HHS/United States
R01DA11869/DA/NIDA NIH HHS/United States
R01DA13826/DA/NIDA NIH HHS/United States
R01DA15215/DA/NIDA NIH HHS/United States
R01MH068197/MH/NIMH NIH HHS/United States
R01MH078773/MH/NIMH NIH HHS/United States
R01MH54907/MH/NIMH NIH HHS/United States
R01MH58986/MH/NIMH NIH HHS/United States
R01MH61173/MH/NIMH NIH HHS/United States
R01MH61695/MH/NIMH NIH HHS/United States
R01NR04749/NR/NINR NIH HHS/United States
Regular HIV RNA testing for all HIV positive patients on antiretroviral therapy (ART) is expensive and has low yield since most tests are undetectable. Selective testing of those at higher risk of failure may improve efficiency. We investigated whether a novel analysis of adherence data could correctly classify virological failure and potentially inform a selective testing strategy.
Multisite prospective cohort consortium.
We evaluated longitudinal data on 1478 adult patients treated with ART and monitored using the Medication Event Monitoring System (MEMS) in 16 United States cohorts contributing to the MACH14 consortium. Since the relationship between adherence and virological failure is complex and heterogeneous, we applied a machine-learning algorithm (Super Learner) to build a model for classifying failure and evaluated its performance using cross-validation.
Application of the Super Learner algorithm to MEMS data, combined with data on CD4+ T cell counts and ART regimen, significantly improved classification of virological failure over a single MEMS adherence measure. Area under the ROC curve, evaluated on data not used in model fitting, was 0.78 (95% CI: 0.75, 0.80) and 0.79 (95% CI: 0.76, 0.81) for failure defined as single HIV RNA level >1000 copies/ml or >400 copies/ml, respectively. Our results suggest 25–31% of viral load tests could be avoided while maintaining sensitivity for failure detection at or above 95%, for a cost savings of $16–$29 per person-month.
Our findings provide initial proof-of-concept for the potential use of electronic medication adherence data to reduce costs through behavior-driven HIV RNA testing.
application/octet-stream image/gif image/jpeg image/gif image/jpeg image/gif image/jpeg image/gif image/jpeg image/gif image/jpeg image/gif image/jpeg
You May Also Like: