Alcohol use and antiretroviral adherence: review and meta-analysis

Abstract

Background: Alcohol use is frequently implicated as a factor in nonadherence to highly active antiretroviral therapy (HAART). There have not been efforts to systematically evaluate findings across studies. This meta-analysis provides a quantitative evaluation of the alcohol-adherence association by aggregating findings across studies and examining potential moderators.

Methods: Literature searches identified 40 qualifying studies totaling over 25,000 participants. Studies were coded on several methodological variables.

Results: In the combined analysis, alcohol drinkers were approximately 50%-60% as likely to be classified as adherent [odds ratio (OR) = 0.548, 95% confidence interval (CI): 0.490 to 0.612] compared with abstainers (or those who drank relatively less). Effect sizes for problem drinking, defined as meeting the National Institute on Alcohol Abuse and Alcoholism criteria for at-risk drinking or criteria for an alcohol use disorder, were greater (OR = 0.474, 95% CI = 0.408 to 0.550) than those reflecting any or global drinking (OR = 0.604, 95% CI = 0.531 to 0.687). Several variables moderated the alcohol-adherence association.

Conclusions: Results support a significant and reliable association of alcohol use and medication nonadherence. Methodological variables seem to moderate this association and could contribute to inconsistent findings across studies. Future research would benefit from efforts to characterize theoretical mechanisms and mediators and moderators of the alcohol-adherence association.

Figure 1

Results of study selection process.

Figure 2

Forest plot indicating the effect size contributed by each study, using the most extreme comparison per study. Drinking intensity: 0 = global (e.g., any use vs. none), 1 = moderate drinking (that did not exceed the NIAAA definition of at-risk drinking or constitute an alcohol use disorder) vs. nonuse, 2 = problem drinking (that met the NIAAA definition for at-risk drinking or criteria for an alcohol use disorder) vs. nonproblem use/nonuse.