ADAPTS: Agentic Decomposition for Automated Protocol-agnostic Tracking of Symptoms

TL;DR

ADAPTS is a novel framework that uses a mixture-of-agents LLM architecture to automatically assess depression and anxiety severity from clinical interviews, providing accurate, explainable, and protocol-agnostic ratings.

Contribution

The paper introduces ADAPTS, a new method that decomposes clinical interviews into symptom-specific reasoning tasks using LLMs, improving psychiatric severity assessment.

Findings

Automated ratings closely match expert benchmarks with an absolute error of 22.

Implementation of clinical conventions stabilized ratings, achieving ICC(2,1)=0.877.

Framework is extensible to multimodal inputs beyond text.

Abstract

Modeling latent clinical constructs from unconstrained clinical interactions is a unique challenge in affective computing. We present ADAPTS (Agentic Decomposition for Automated Protocol-agnostic Tracking of Symptoms), a framework for automated rating of depression and anxiety severity using a mixture-of-agents LLM architecture. This approach decomposes long-form clinical interviews into symptom-specific reasoning tasks, producing auditable justifications while preserving temporal and speaker alignment. Generalization was evaluated across two independent datasets ($N=204$) with distinct interview structures. On high-discrepancy interviews, automated ratings approximated expert benchmarks ($\text{absolute error}=22$) more closely than original human ratings ($\text{absolute error}=26$). Implementing an ``extended'' protocol that incorporates qualitative clinical conventions significantly stabilized ratings, with absolute agreement reaching $\text{ICC(2,1)} = 0.877$. These findings suggest that the ADAPTS framework enables promising evaluations of psychiatric severity. While the current implementation is purely text-based, the underlying architecture is readily extensible to multimodal inputs, including acoustic and visual features. By approximating expert-level precision in a protocol-agnostic manner, this framework provides a foundation for objective and scalable psychiatric assessment, especially in resource-limited settings.