Development and Validation of a Risk Score for Predicting Non-Adherence to Antiretroviral Therapy

Abstract

Several patient-related factors that influence adherence to antiretroviral therapy (ART) have been described. However, studies that propose a practical and simple tool to predict nonadherence after ART initiation are still scarce. In this study, we develop and validate a score to predict the risk of nonadherence in people starting ART. The model/score was developed and validated using a cohort of people living with HIV starting ART at the Hospital del Mar, Barcelona, between 2012 and 2015 (derivation cohort) and between 2016 and 2018 (validation cohort),. Adherence was evaluated every 2 months using both pharmacy refills and patient self-reports. Nonadherence was defined as taking <90% of the prescribed dose and/or ART interruption for more than 1 week. Predictive factors for nonadherence were identified by logistic regression. Beta coefficients were used to develop a predictive score. Optimal cutoffs were identified using the bootstrapping methodology, and performance was evaluated with the C statistic. Our study is based on 574 patients: 349 in the derivation cohort and 225 in the validation cohort. A total of 104 patients (29.8%) of the derivation cohort were nonadherent. Nonadherence predictors were patient prejudgment; previous medical appointment failures; cultural and/or idiomatic barriers; heavy alcohol use; substance abuse; unstable housing; and severe mental illness. The cutoff point (receiver operating characteristic curve) for nonadherence was 26.3 (sensitivity 0.87 and specificity 0.86). The C statistic (95% confidence interval) was 0.91 (0.87-0.94). These results were consistent with those predicted by the score in the validation cohort. This easy-to-use, highly sensitive, and specific tool could be easily used to identify patients at highest risk for nonadherence, thus allowing resource optimization and achieving optimal treatment goals.

Keywords: adherence; antiretroviral therapy; risk factors; score; validation.

FIG. 1.

ROC curve of the best cutoff point according to the maximum likelihood criterion: 26.3. ROC, receiver operating characteristic.

FIG. 2.

Calibration plot containing 95% confidence intervals of the observed (Y-axis) and model-based (X-axis) nonadherence risk computed for the validation cohort.