Grounded in Consensus, In Step With Emerging Science: A Consensus-Anchored Multi-Corpus Clinical Chatbot for Long COVID

2026-07-27

AI Summary

This study addresses the challenge of fragmented and asynchronously updated evidence in clinical decision-making for long COVID. The authors propose a retrieval-augmented generation (RAG) chatbot tailored for clinicians, which uniquely anchors on expert consensus guidelines while dynamically integrating three evolving evidence sources: PubMed literature, registered clinical trials, and living systematic reviews. This design ensures clinical stability without sacrificing access to cutting-edge findings. In automated evaluations across 50 clinical questions, the system demonstrated performance comparable to OpenEvidence, yet achieved higher and more consistent scores under assessment by large language models.

Abstract

Long COVID (LC) poses a challenge for clinical decision support because relevant evidence is distributed across sources with different update cycles, evidentiary roles, and levels of clinical maturity. We present a clinician-facing chatbot that organizes four sources within a retrieval-augmented workflow: expert-curated consensus guidance, current PubMed literature, registered interventional trials, and evidence from living systematic reviews. Consensus guidance is always included to frame responses, while the remaining sources are retrieved in parallel when selected by the user. In an exploratory automated evaluation on 50 clinician-facing questions, our chatbot showed comparable mean ratings to OpenEvidence, with numerically higher scores and lower score variability in an LLM-judged comparison.

Problem

• Long COVID
• clinical decision support
• evidence integration
• multi-source information
• consensus guidance

Innovation

• consensus-anchored
• retrieval-augmented generation
• multi-corpus integration
• clinical decision support
• Long COVID