MES: A Multi-Agent Evidence Synthesis System for Medical Decision-Making

Abstract

Medical evidence synthesis increasingly requires published studies, real-world clinical data and structured biomedical knowledge, yet most automated systems remain centered on literature retrieval and summarization. Here we present MES, a multi-agent framework for source-grounded medical evidence synthesis. MES coordinates six specialized agents to decompose clinical questions, retrieve literature and trial evidence, generate question-specific RWE by constructing and analyzing real-world cohorts, query biomedical knowledge graphs, integrate quantitative findings and screen generated claims against their cited evidence. The framework uses evidence-based medicine taxonomies to clarify underspecified questions, adapts evidence use when sources are absent or discordant and reports unresolved gaps rather than forcing consensus. MES also provides claim-level provenance tracking and cross-agent consistency checking, allowing final reports to distinguish trial evidence, real-world associations and knowledge-graph support. We evaluated MES in two clinical use cases and across 144 clinical queries spanning six evidence-based medicine categories. MES generated structured reports that preserved source traceability, identified cross-source disagreement and communicated uncertainty across diverse clinical question types. MES provides an auditable framework for organizing, testing and contextualizing heterogeneous clinical evidence while keeping the evidentiary basis of each conclusion explicit.

Medical Decision‐Making Capacity in Early‐Stage Alzheimer Patients: Comparison With Healthy Controls and Benefit of Assistive Information
Dilara Aylin Felice Vossberg, Vasilija Rolfes, Heiner Fangerau +1
Psychogeriatrics : the official journal of the Japanese Psychogeriatric Society14 Oct 2026Peer-reviewedCC BYFull textGeneral medicineEurope PMC
Post In-Hospital Cardiac Arrest Simulation to Improve Medical Decision Making and Communication in Internal Medicine Residents
Emily Harris, Alexandra Collis, David Carlbom +3
MedEdPORTAL : the journal of teaching and learning resources19 Oct 2026Peer-reviewedCC BYFull textGeneral medicineEurope PMC
Procalcitonin-Guided Antimicrobial Therapy: Current Evidence for Clinical Decision-Making and Practical Limitations
Sumayyah Alshammari, Basmah Alrawaili, Roaa Alshammari +4
Cureus19 Oct 2026Peer-reviewedCC BYFull textGeneral medicineEurope PMC
Combination of Technologies in Body Contouring: Evidence Mapping and a Decision-Making Algorithm
Igo Reichmann Losso, Luiz Augusto Sousa Oliveira, Camila Araújo Gomes +5
Cureus19 Oct 2026Peer-reviewedCC BYFull textGeneral medicineEurope PMC
Multi-label auxiliary decision-making model for pharmacotherapy of ischemic stroke based on BR-SA-LightGBM using real-world electronic medical records
Yueqi Chen, Chen Rui, Chen Rui +3
Frontiers in Medicine27 Oct 2026Peer-reviewedCC BYFull textGeneral medicineDOAJ

Cite

BibTeX RIS

BibTeX

@misc{li2026multiagent,
  title = {{MES: A Multi-Agent Evidence Synthesis System for Medical Decision-Making}},
  author = {H. Li and W. Pan and S. Rajendran and C. Zang and J. Gabeskiria and V. Liu and V. Feng and M. Penmetsa and L. Lin and A. B. Jayakar and A. Boucher and E. J. Schenck and H. S. Yang and F. Wang},
  howpublished = {medRxiv},
  year = {2026},
  month = sep,
  doi = {10.64898/2026.09.15.26362921},
  url = {https://www.medrxiv.org/content/10.64898/2026.09.15.26362921v1},
  note = {CC BY-NC-ND},
}

RIS

TY  - UNPB
TI  - MES: A Multi-Agent Evidence Synthesis System for Medical Decision-Making
AU  - H. Li
AU  - W. Pan
AU  - S. Rajendran
AU  - C. Zang
AU  - J. Gabeskiria
AU  - V. Liu
AU  - V. Feng
AU  - M. Penmetsa
AU  - L. Lin
AU  - A. B. Jayakar
AU  - A. Boucher
AU  - E. J. Schenck
AU  - H. S. Yang
AU  - F. Wang
PY  - 2026
DA  - 2026/09/15
PB  - medRxiv
DO  - 10.64898/2026.09.15.26362921
UR  - https://www.medrxiv.org/content/10.64898/2026.09.15.26362921v1
AB  - Medical evidence synthesis increasingly requires published studies, real-world clinical data and structured biomedical knowledge, yet most automated systems remain centered on literature retrieval and summarization. Here we present MES, a multi-agent framework for source-grounded medical evidence synthesis. MES coordinates six specialized agents to decompose clinical questions, retrieve literature and trial evidence, generate question-specific RWE by constructing and analyzing real-world cohorts, query biomedical knowledge graphs, integrate quantitative findings and screen generated claims against their cited evidence. The framework uses evidence-based medicine taxonomies to clarify underspecified questions, adapts evidence use when sources are absent or discordant and reports unresolved gaps rather than forcing consensus. MES also provides claim-level provenance tracking and cross-agent consistency checking, allowing final reports to distinguish trial evidence, real-world associations and knowledge-graph support. We evaluated MES in two clinical use cases and across 144 clinical queries spanning six evidence-based medicine categories. MES generated structured reports that preserved source traceability, identified cross-source disagreement and communicated uncertainty across diverse clinical question types. MES provides an auditable framework for organizing, testing and contextualizing heterogeneous clinical evidence while keeping the evidentiary basis of each conclusion explicit.
ER  -

Abstract

Related

Cite