Format

Send to

Choose Destination
J Acquir Immune Defic Syndr. 2015 May 1;69(1):109-18. doi: 10.1097/QAI.0000000000000548.

Super Learner Analysis of Electronic Adherence Data Improves Viral Prediction and May Provide Strategies for Selective HIV RNA Monitoring.

Author information

1
*Division of Biostatistics, School of Public Health, University of California, Berkeley, Berkeley, CA; †Departments of Medicine (Infectious Disease) and Epidemiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA; ‡School of Nursing, Yale University, New Haven, CT; §Massachusetts General Hospital, Center for Global Health, Harvard Medical School, Boston, MA; ‖Health Services and Outcomes Research, Children's Mercy Hospitals and Clinics, University of Missouri-Kansas City Schools of Medicine and Pharmacy, Kansas City, MO; ¶Departments of Health Behavior and Medicine, School of Medicine and Gillings School of Global Public Health, University of North Carolina at Chapel Hill, Chapel Hill, NC; #Department of Medicine, Albert Einstein College of Medicine and Montefiore Medical Center, Bronx, NY; **Department of Psychiatry, School of Medicine, Yale University, New Haven, CT; ††HIV Center for Clinical and Behavioral Studies, NY State Psychiatric Institute and Department of Psychiatry, Columbia University, New York, NY; ‡‡Department of Health Services, Policy & Practice, Brown University School of Public Health, Providence, RI; §§Department of Psychology, University of Washington, Seattle, WA; ‖‖Department of Health and Community Systems, University of Pittsburgh, School of Nursing, Pittsburgh, PA; ¶¶School of Dentistry, University of California, Los Angeles, Los Angeles, CA; and ##Massachusetts General Hospital, Center for Global Health, Department of Global Health and Population, Harvard School of Public Health, Boston, MA.

Abstract

OBJECTIVE:

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.

DESIGN:

Multisite prospective cohort consortium.

METHODS:

We evaluated longitudinal data on 1478 adult patients treated with ART and monitored using the Medication Event Monitoring System (MEMS) in 16 US cohorts contributing to the MACH14 consortium. Because 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.

RESULTS:

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 receiver operating characteristic curve, evaluated on data not used in model fitting, was 0.78 (95% confidence interval: 0.75 to 0.80) and 0.79 (95% confidence interval: 0.76 to 0.81) for failure defined as single HIV RNA level >1000 copies per milliliter or >400 copies per milliliter, respectively. Our results suggest that 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.

CONCLUSIONS:

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.

PMID:
25942462
PMCID:
PMC4421909
DOI:
10.1097/QAI.0000000000000548
[Indexed for MEDLINE]
Free PMC Article

Publication types, MeSH terms, Substances, Grant support

Publication types

MeSH terms

Substances

Grant support

Supplemental Content

Full text links

Icon for Wolters Kluwer Icon for PubMed Central
Loading ...
Support Center