atlas

Research map / Large language models / AI and society

Knowledge-Infused Learning for Developing a Mental Health Diagnostic Copilot in Healthcare Systems

AAAI 2025 · Large language models › AI and society · approach: AI for health and public decisions · 1 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a knowledge-infused, multi-turn AI diagnostic copilot for mental health that works alongside clinicians, with a planned (not yet implemented) evaluation design.

Problem

Mental health diagnosis and treatment disparities for underserved communities such as African Americans, where static AI diagnostic systems lack real-time multi-turn patient interaction and clinical grounding.

Approach

Combine Knowledge-Infused Learning (clinical ontologies SNOMED CT and UMLS embedded into decision trees and ensembles via modified splitting criteria) with multi-turn conversational feedback and clinician instructability via DPO or KTO.

Key results

Limitations

Experimental setup

Datasets: ESCON IHMI SMHD Primate SNOMED CT UMLS

Metrics: clinical entity overlap score NLI-based logical coherence cosine similarity BERTScore

Builds on: Knowledge-Infused Learning Direct Preference Optimization Kahneman-Tversky Optimization

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy