Researchers have developed ADAPTS, a novel framework utilizing a mixture-of-agents Large Language Model architecture to automatically assess depression and anxiety severity from clinical interviews. This system decomposes interviews into symptom-specific tasks, providing auditable justifications and maintaining temporal and speaker alignment. In evaluations across two datasets, ADAPTS demonstrated promising results, with automated ratings closely approximating expert benchmarks and outperforming original human ratings on high-discrepancy interviews. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT This framework could enable more objective and scalable psychiatric assessments, particularly in resource-limited settings.
RANK_REASON This is a research paper detailing a new framework for automated symptom tracking.