AI-Enabled Smartwatch for Medication Adherence in Outpatient Psychiatry

This was a single-center, prospective, exploratory randomized controlled trial conducted in an outpatient psychiatric clinic. Participants aged 12 years or older were randomized 1:1 to an AI-enabled smartwatch medication-monitoring system or waitlist usual care for four weeks. Participants in both groups continued their usual psychiatric care, and no additional medication-adherence counseling was provided as part of the intervention.

Medication adherence was assessed at baseline and at Week 4 using the clinician-rated Korean Brief Adherence Rating Scale (K-BARS). The primary analysis compared the change in K-BARS score between the randomized groups. Control participants were offered the smartwatch for an additional four weeks after completing the randomized comparison period. Analyses of responder thresholds, device engagement, and the optional post-waitlist smartwatch period were exploratory.

The study was registered retrospectively after enrollment and study completion.

Inclusion criteria

• Age 12 years or older
• Receiving outpatient psychiatric care at Wonkwang University Hospital
• Receiving at least one regularly prescribed psychotropic medication
• Willing and able to wear the study smartwatch and complete the study assessments
• Able to provide written informed consent; for minors, written assent and written consent from a parent or legal guardian were required

Exclusion criteria

• Diagnosed congenital genetic disorder
• Clear history of acquired brain injury
• Seizure disorder or another neurological condition that could interfere with study participation
• Psychotic symptoms, aggression, or behavioral instability severe enough to prevent safe and stable smartwatch use or create a substantial risk of device damage