Understanding patient preferences for HIV medications using adaptive conjoint analysis: feasibility assessment

Abstract

Objective: Choosing among HIV medications involve making trade-offs among various efficacy, convenience, resistance, and side-effect attributes. This study tested the feasibility of using adaptive conjoint analysis (ACA) to assess preferences (utilities) for HIV medication attributes.

Methods: HIV individuals were recruited through newspaper advertisements. Participants completed a computerized ACA survey that assessed 12 attributes, including side effects, regimen convenience, resistance, and efficacy. Literature on third-agent HIV drugs was used to identify percentage risk and severity level descriptions for each attribute. Based on the ACA-derived utilities, we assessed the relative importance of the attributes by averaging individually calculated importance and estimated the percentages that would prefer selected HIV medications over others. To check validity of the ACA utilities, the survey also had respondents choose among medications with different attribute profiles.

Results: The 35 respondents were primarily African Americans (94%) and unemployed (54%). Of these, 28 (80%) provided consistent responses and were analyzed. Of the 12 medication attributes evaluated, the risk of developing resistance, regimen convenience, and the risk of sleep disturbance had the greatest impact on preferences; each accounting for more than 8.5% of the variation in preferences. These were followed by risk of drug failure (8.2%), cholesterol elevation (7.1%), diarrhea (7.1%) and nausea (6.9%). The ACA utilities accurately predicted patients' actual medication choices 75% of the time.

Conclusions: Adaptive conjoint analysis was successful in predicting HIV treatment preferences under different medication scenarios. Resistance, regimen convenience, and sleep disturbance would likely make the most difference in the perceived value of a third-agent HIV medication.