Bridging the Post-discharge Gap: A Traceable Multi-agent Framework for Safe and Continuous Care

2026-06-23

AI Summary

This study addresses critical challenges in post-discharge follow-up, including scarce medical resources, fragmented patient histories, and cross-departmental information silos, as well as the hallucination risks and limited longitudinal reasoning capabilities of large language models in continuous care. To overcome these issues, the authors propose Healink, a multi-agent framework that integrates triage-based routing, a relational database–enhanced memory mechanism, and a constraint-driven retrieval-augmented generation (RAG) engine. The framework innovatively employs a weighted similarity matching strategy to enable prescription-level traceability and proactive detection of cross-departmental medication conflicts. Evaluated on 400 routine and 85 complex real-world follow-up cases alongside the webMedQA benchmark, Healink demonstrated superior clinical authority and safety compared to human physician baselines under single-blind expert assessment.

Abstract

Post-discharge clinical follow-up is critical for maintaining continuity of care and mitigating long-term health risks. However, traditional follow-up paradigms suffer from shortage of health workforce, fragmented patient histories, and information silos across clinical departments. While large language models have demonstrated potential in medical question-answering, their deployment in continuous care is hindered by hallucination risks and a fundamental inability to reason over longitudinal, patient-specific constraints. Here we present Healink, a memory-enhanced multi-agent framework to support AI-assisted post-discharge follow-up by generating prescription-grounded, traceable responses that improved completeness and perceived clinical utility in retrospective and physician-blinded evaluations. The architecture seamlessly integrates a triage routing mechanism, a unified memory enhancement module utilizing a robust relational database for optimal latency, and a strict constraint-based retrieval-augmented generation engine. By vectorizing historical clinical records and employing weighted similarity functions across diverse phenotypic and intervention dimensions, Healink ensures precise inter-patient and intra-patient case matching while actively preventing cross-departmental drug conflicts. We evaluated Healink on a dataset comprising 400 continuous and 85 highly complex real-world follow-up cases, alongside the webMedQA benchmark. In a rigorous single-blind evaluation conducted by clinical experts, the framework outperformed human physician baselines in both authoritativeness and clinical safety. By generating a traceable, white-box evidence chain, Healink provides a scalable, safe, and highly effective paradigm for intelligent patient management, ultimately enhancing societal healthcare outcomes.

Problem

• post-discharge follow-up
• continuity of care
• information silos
• hallucination
• longitudinal reasoning

Innovation

• multi-agent framework
• memory-enhanced LLM
• retrieval-augmented generation
• traceable clinical reasoning
• constraint-based patient matching