D2MDT: Department-aware Multidisciplinary Team Consultation with Deliberation for Efficient Clinical Prediction
2026-06-02 • Multiagent Systems
Multiagent Systems
AI summaryⓘ
The authors developed a new system called D2MDT to improve how computers use electronic health records (EHRs) to predict patient outcomes, like mortality. Instead of using one big AI model, they created a multi-agent team where each 'doctor' agent focuses on a different medical specialty and shares unique information. Their method also speeds up discussions by only addressing unresolved issues rather than repeating everything. Tests showed their approach makes predictions more accurate and consultations more efficient.
Electronic Health RecordsClinical PredictionMulti-Agent SystemsLarge Language ModelsMulti-disciplinary TeamsDeliberationMortality PredictionStructured DataConsultation Efficiency
Authors
Yongqi Liang, Qidong Liu, Chunze Yang, Lei Wu, Jiusong Ge, Ni Zhang, Chen Li
Abstract
Electronic health records (EHRs) are central to clinical prediction, but existing methods either rely on correlation-driven deep models or use single large language models (LLMs), making it difficult to support multidisciplinary clinical reasoning. Recent multi-agent systems (MAS) provide a promising alternative, yet current EHR-grounded MAS methods still suffer from weak evidence differentiation across agents and redundant multi-round interaction. We propose D2MDT, a Department-aware MultiDisciplinary Team Consultation with Deliberation for Efficient clinical prediction. D2MDT first constructs structured EHR evidence and consultation-ready semantic evidence for multi-agent consultation. It then assigns patient-specific department perspectives to doctor agents and retrieves complementary evidence for collaborative consultation. To improve efficiency, D2MDT further introduces residual deliberation, which updates only unresolved consensus rather than replaying the full discussion history. Finally, D2MDT fuses the refined consensus report with structured EHR representations for prediction. Experiments on mortality prediction show that D2MDT improves both predictive performance and consultation efficiency. We release the code online to ease the reproducibility of this paper.