Psychometric Properties of Measuring Antiretroviral Therapy Adherence Among Young Latino Sexual Minority Men With HIV: Ecological Momentary Assessment and Electronic Pill Dispenser Study

Background: Increasing HIV rates among young Latino sexual minority men (YLSMM) warrant innovative and rigorous studies to assess prevention and treatment strategies. Ecological momentary assessments (EMAs) and electronic pill dispensers (EPDs) have been used to measure antiretroviral therapy (ART) adherence repeatedly in real time and in participants' natural environments, but their psychometric properties among YLSMM are unknown. Objective: The study's objective was to assess the concurrent validity, acceptability, compliance, and behavioral reactivity of EMAs and EPDs among YLSMM with HIV. Methods: A convenience sample of 56 YLSMM with HIV with suboptimal ART adherence, aged 18-34 years, was recruited into a 28-consecutive-day EMA study. Concurrent validity was analyzed by comparing median ART adherence rates and calculating Spearman correlations between ART adherence measured by EMA, EPD, and baseline retrospective validated 3-item and single-item measures. Acceptability was assessed in exit interviews asking participants to rate EMA and EPD burden. Compliance was assessed by computing the percent lost to follow-up, the percent of EMAs missed, and the percentage of days the EPD was not opened that had corresponding EMA data self-reporting adherence to ARTs. Behavioral reactivity was assessed by computing the median change in ART adherence during the study period, using generalized mixed models to assess whether the cumulative number of EMAs completed and days of EPD use predicted ART adherence over time, and by asking participants to rate perceived reactivity using a Likert scale. Results: EMA ART adherence was significantly correlated with baseline validated 3-item (r=0.41, P =.003) and single-item (r=0.52, P <.001) measures, but correlations were only significant for participants that reported EMA was not burdensome. Correlations for EPD ART adherence were weaker but significant (r=0.36, P =.009; r =0.34, P =.01, respectively). Acceptability was high for EMAs (48/54, 89%) and EPDs (52/54, 96%) per self-report. Loss to follow-up was 4% (2/56), with the remaining participants completing 88.6% (1339/1512) of study-prompted EMAs. The percentage of missed EMA surveys increased from 5.8% (22/378) in week 1 of the study to 16.7% (63/378) in week 4. Of 260 days when EPDs were not opened, 68.8% (179) had a corresponding EMA survey self-reporting ART adherence. Reactivity inferred from the median change in ART adherence over time was 8.8% for EMAs and -0.8% for EPDs. Each completed EMA was associated with 1.03 odds (95% CI 1-1.07) of EMA ART adherence over time, and each day of EPD use with 0.97 odds (95% CI 0.96-0.99) of EPD ART adherence over time. Self-reported perceived behavioral reactivity was 39% for EMAs and 35% for EPDs. Conclusions: This study provides evidence of concurrent validity with retrospective validated measures for EMA- and EPD-measured ART adherence among YLSMM, when participant burden is carefully considered, without significant behavioral reactivity. While acceptability and compliance of EMAs and EPDs were high overall, noncompliance increased