Dementia-Agents: A Multi-Modal Multi-Agent System for Dementia Staging and Phenotyping

2026-06-19

AI Summary

This study addresses the limitations of existing AI approaches, which are typically confined to binary or three-stage modeling of Alzheimer’s disease and thus struggle with the complex, syndrome-level diagnostic challenges posed by dementia in real-world clinical settings—characterized by multiple stages, diverse phenotypes, and heterogeneous etiologies. To overcome this, the authors propose a clinically aligned multi-agent system that integrates semantic transformation of structured clinical records, a fine-tuned domain-specific large language model, and a probabilistic aggregation mechanism through a collaborative workflow among data agents, domain-expert agents, and a coordinating agent. Evaluated on a real-world cohort of 1,066 patients, the method substantially outperforms both monolithic multimodal large models and current medical multi-agent systems, achieving higher accuracy in staging and phenotype identification while preserving interpretability.

Abstract

Dementia diagnosis requires integrating multi-modal clinical assessments from diverse informants and clinicians under incomplete and heterogeneous data conditions. Yet most AI-driven approaches remain Alzheimer's disease (AD)-centric, framing the problem as binary AD detection or three-stage AD progression modeling within well-curated research settings. This pathology-driven paradigm overlooks the broader, syndrome-level nature of dementia, which spans multiple stages, phenotypes, and etiologies. In this paper, we propose Dementia-Agents, a clinically aligned multi-agent framework for real-world dementia staging and phenotyping. The framework follows a three-step workflow: (1) a data agent translates structured clinical records into semantically faithful textual representations that preserve missing-data signals and routes them to domain-aligned experts; (2) five fine-tuned expert agents generate domain-level predictions; and (3) a coordinator agent performs probabilistic aggregation to produce final staging and phenotyping decisions. We develop and evaluate Dementia-Agents on a real-world clinical cohort of 1,066 patients from two cognitive neurology services. Compared with monolithic multi-modal large language models (MLLMs) and prior medical multi-agent systems, our approach achieves consistent improvements in diagnostic performance for real-world syndrome-level dementia staging and phenotyping, while preserving domain-level interpretability.

Problem

• dementia staging
• dementia phenotyping
• multi-modal data
• heterogeneous clinical data
• syndrome-level diagnosis

Innovation

• multi-agent system
• dementia phenotyping
• multi-modal clinical data
• probabilistic aggregation
• real-world clinical AI