Combining Multiple Large Language Models Improves Diagnostic Accuracy
Open accessAbstract
diagnoses. We found that aggregating responses from multiple LLMs leads to more accurate differential diagnoses (average TOP-5 accuracy for three LLMs: 75.3%±1.6 percentage points) compared with the differential diagnoses produced by single LLMs (average TOP-5 accuracy for single LLMs: 59.0%±6.1 percentage points). We also found that aggregating smaller and less capable models (TOP-5 accuracy for three smaller LLMs, not including GPT-4: 70.0%) can rival the accuracy of the top-performing model (TOP-5 accuracy for GPT-4: 72.0%). The use of collective intelligence methods to synthesize differential diagnoses, combining the responses of different LLMs, achieves three of the necessary steps toward advancing LLMs as a diagnostic support tool: demonstrating sufficiently high diagnostic accuracy, reducing the risk of misdiagnoses, and eliminating the dependence on a single commercial vendor. (Funded by the European Union's Horizon Europe research and innovation program.).
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Existing mixed-vendor approaches in medicine mostly rely on independent model runs, combining models from different providers via voting or simple aggregation.
“However, existing mixed-vendor approaches in medicine mostly rely on independent model runs, combining models from different providers via voting or simple aggregation (Barabucci et al., 2024;Sorich et al., 2024).”
From Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis? (2026) · cites this paper as Barabucci et al., 2024
Combining outputs from cross-vendor models via majority voting or collective intelligence algorithms can outperform individual baselines.
“For example, recent studies demonstrate that combining outputs from cross-vendor models via majority voting or collective intelligence algorithms can outperform individual baselines (Barabucci et al., 2024;Sorich et al., 2024).”
From Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis? (2026) · cites this paper as Barabucci et al., 2024
Cites
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.05232 · Cited by 2,516 · see citing works
Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine
Lee, P., Bubeck, S., & Petro, J. (2023) · New England Journal of Medicine · doi:10.1056/nejmsr2214184 · Cited by 1,738 · see citing works
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
Liang, T., He, Z., Jiao, W., Wang, X., Wang, Y., Wang, R., Yang, Y., Shi, S., & Tu, Z. (2023) · arXiv · doi:10.48550/arxiv.2305.19118 · Cited by 320 · see citing works
Towards Accurate Differential Diagnosis with Large Language Models
McDuff, D., Schaekermann, M., Tu, T., Palepu, A., Wang, A., Garrison, J., Singhal, K., Sharma, Y., Azizi, S., Kulkarni, K., et al. (2023) · arXiv · doi:10.48550/arxiv.2312.00164 · Cited by 311 · see citing works
Towards accurate differential diagnosis with large language models
McDuff, D., Schaekermann, M., Tu, T., Palepu, A., Wang, A., Garrison, J., Singhal, K., Sharma, Y., Azizi, S., Kulkarni, K., et al. (2025) · Nature · doi:10.1038/s41586-025-08869-4 · Cited by 311 · see citing works
Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine
Nori, H., Lee, Y. T., Zhang, S., Carignan, D., Edgar, R., Fusi, N., King, N., Larson, J., Li, Y., Liu, W., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.16452 · Cited by 178 · see citing works
Barnett, M. L., Boddupalli, D., Nundy, S., & Bates, D. W. (2019) · JAMA Network Open · doi:10.1001/jamanetworkopen.2019.0096 · Cited by 154 · cited 7× · see citing works
“The degree of increase in accuracy achieved by the method employed in this study is in line with similar results in the field of collective intelligence, both in the medical field [11, 12] and outside [10, 13].”
BackgroundMethodResultInfluentialChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
Chan, C.-M., Chen, W., Su, Y., Yu, J., Xue, W., Zhang, S., Fu, J., & Liu, Z. (2023) · arXiv · doi:10.48550/arxiv.2308.07201 · Cited by 55 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?
Yuan, G. C., Zhang, X., Kim, S. E., & Rajpurkar, P. (2026) · Proceedings of the 1st Workshop on Linguistic Analysis for Health (HeaLing 2026) · doi:10.18653/v1/2026.healing-1.1 · Cited by 1 · see citing works
“However, existing mixed-vendor approaches in medicine mostly rely on independent model runs, combining models from different providers via voting or simple aggregation (Barabucci et al., 2024; Sorich et al., 2024).”
- Authors
- Barabucci, G., Shia, V., Chu, E., Harack, B., Laskowski, K., & Fu, N.
- Affiliations
- University of Cologne (DE)
- Harvey Mudd College (US)
- Kaiser Permanente (US)
- University of Oxford (GB)
- The Human Diagnosis Project (US)
- Venue
- NEJM AI
- Publisher
- Massachusetts Medical Society
- Published
- 2024-10-24
- Volume
- 1
- Issue
- 11
- Pages
- AIcs2400502-AIcs2400502
- ISSN
- 2836-9386 (ISSN-L)
- OpenAlex
- W4403486851
- Cited by
- 24
- References
- 8
- Citations by year
- 2026: 7 · 2025: 17
- FWCI
- 2.24
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- NEJM AI (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- European Commission (101070588)
- HORIZON EUROPE Framework Programme
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- large language models, diagnostic accuracy, clinical decision support, diagnosis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
