New AI model assesses depression and anxiety from clinical dialogue
Researchers have developed ADAPTS, an AI model based on LLM architecture, which can automatically assess the severity of depression and anxiety from clinical interviews. The model achieved better results than initial human assessments.
What happened?
ADAPTS (Agentic Decomposition for Automated Protocol-agnostic Tracking of Symptoms) utilises a 'mixture-of-agents' LLM architecture to analyse long clinical interviews. The model breaks down the interviews into symptom-specific reasoning tasks, generating traceable justifications. During testing on two independent datasets ($N=204$), the ADAPTS model showed a mean absolute error of 22, compared to an error of 26 for the original human assessments in high-variance interviews. The model achieves greater stability with an extended protocol that includes qualitative clinical conventions.
Key facts
| Modell | ADAPTS |
|---|---|
| Absolut felmarginal (ADAPTS) | 22 |
| Absolut felmarginal (mänsklig bedömning) | 26 |
| Antal dataset | 2 |
| Antal deltagare (N) | 204 |
”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 se”
”On high-discrepancy interviews, automated ratings approximated expert benchmarks (absolute error=22) more closely than original human ratings (absolute error=26).”
Why it matters
The new AI model offers a systematised method for objectively evaluating mental health. By reducing variance in assessments, ADAPTS can contribute to more consistent and reliable diagnoses. In the long term, this could free up healthcare resources and facilitate faster, more standardised assessment processes within psychiatry.
Who is affected?
Developers of AI models, researchers in affective computing, clinicians, and psychiatrists assessing mental health, as well as patients suffering from depression and anxiety, are affected. The model is designed to assist professional staff rather than replace them.
What else you should know
ADAPTS has been tested on two independent datasets with distinct interview structures, indicating broad applicability. The research results are published as a new arXiv preprint, meaning it has not yet undergone traditional peer review.
Quick answers about this story
Vad har hänt?
När hände det?
Varför spelar det roll?
Vilka bolag berörs?
Påverkar det EU?
The link opens in a new window and leads to the publisher's own site.
Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.
AI-verktyg i artikeln
Topics
Get similar news straight to your inbox
The reader's room
Send in a question or an addition. The newsroom reads everything before it's published and replies when relevant. No AI-generated text – just people.
Sign in to submit a comment or question.
Read the article through your role
- Decide whether this affects strategy over 6–12 months or is just noise.
- Discuss with leadership: do we own the right question or does ownership need to move?
- Ask: what risk are we taking by NOT acting on this this quarter?
Generated angle — not editorial analysis of "New AI model assesses depression and anxiety from clinical d"