Results From a Pilot Study of an Automated Directly Observed Therapy Intervention Using Artificial Intelligence With...

Area of Science:

• Digital health interventions
• HIV/AIDS research
• Artificial intelligence in medicine

Background:

• Suboptimal adherence to antiretroviral therapy (ART) is a significant challenge for youth with HIV (YWH), leading to drug resistance and poor health outcomes.
• Mobile health (mHealth) interventions offer a promising avenue to improve medication adherence and clinical outcomes in this population.

Purpose of the Study:

• To evaluate the feasibility and acceptability of a novel mobile app-based intervention utilizing automated directly observed therapy (aDOT) with artificial intelligence and conditional economic incentives (CEIs).
• To assess the potential of the aDOT-CEI intervention to improve ART adherence and viral suppression among virally unsuppressed YWH.

Main Methods:

• A pilot study was conducted with 28 virally unsuppressed YWH (aged 18-29) in California and Florida.
• Participants used the aDOT platform for 3 months, with outcomes including feasibility, acceptability, self-reported ART adherence, and HIV viral load.
• The intervention was informed by the operant framework of Key Principles in Contingency Management Implementation.

Main Results:

• High participant satisfaction with the app (91%) and reported medication adherence assistance (82%).
• Moderate comfort with app privacy and security (55%), with 59% finding incentives helpful for daily adherence.
• The intervention demonstrated high acceptability and feasibility, with potential for improving viral suppression.

Conclusions:

• The aDOT-CEI intervention shows promise for improving ART adherence and viral suppression in YWH.
• Refinements such as increased incentives and enhanced privacy assurances may improve intervention outcomes.
• Further research with larger sample sizes is recommended to confirm the efficacy of the aDOT-CEI intervention.