Human–AI collectives most accurately diagnose clinical vignettes

AI systems, particularly large language models (LLMs), are increasingly being employed in high-stakes decisions that impact both individuals and society at large, often without adequate safeguards to ensure safety, quality, and equity. Yet LLMs hallucinate, lack common sense, and are biased-shortcomings that may reflect LLMs' inherent limitations and thus may not be remedied by more sophisticated architectures, more data, or more human feedback. Relying solely on LLMs for complex, high-stakes decisions is therefore problematic. Here, we present a hybrid collective intelligence system that mitigates these risks by leveraging the complementary strengths of human experience and the vast information processed by LLMs. We apply our method to open-ended medical diagnostics, combining 40,762 differential diagnoses made by physicians with the diagnoses of five state-of-the art LLMs across 2,133 text-based medical case vignettes. We show that hybrid collectives of physicians and LLMs outperform both single physicians and physician collectives, as well as single LLMs and LLM ensembles. This result holds across a range of medical specialties and professional experience and can be attributed to humans' and LLMs' complementary contributions that lead to different kinds of errors. Our approach highlights the potential for collective human and machine intelligence to improve accuracy in complex, open-ended domains like medical diagnostics.

Authors

Institutions

Publication Details

Journal
Proceedings of the National Academy of Sciences
Published
2025-06-13
DOI
https://doi.org/10.1073/pnas.2426153122
Citations
15
Primary Topic
Clinical Reasoning and Diagnostic Skills
Type
article
Field-Weighted Citation Impact
22.74

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Human–AI collectives most accurately diagnose clinical vignettes

Nikolas Zöller, Stefan Michael Herzog, Benjamin Harack, Kornel Laskowski et al.
15 citations
Proceedings of the National Academy of Sciences
Clinical Reasoning and Diagnostic Skills
22.74
article

Human–AI collectives most accurately diagnose clinical vignettes

Nikolas Zöller, Stefan Michael Herzog, Benjamin Harack, Kornel Laskowski, Gioele Barabucci, Victor Shia, Vito Trianni, Ralf H. J. M. Kurvers, Nathan Fu, Jayanth Komarneni, I-Chun Lin, Eugene Chu, Julian Berger
article en
15 citations

Abstract

AI systems, particularly large language models (LLMs), are increasingly being employed in high-stakes decisions that impact both individuals and society at large, often without adequate safeguards to ensure safety, quality, and equity. Yet LLMs hallucinate, lack common sense, and are biased-shortcomings that may reflect LLMs' inherent limitations and thus may not be remedied by more sophisticated architectures, more data, or more human feedback. Relying solely on LLMs for complex, high-stakes decisions is therefore problematic. Here, we present a hybrid collective intelligence system that mitigates these risks by leveraging the complementary strengths of human experience and the vast information processed by LLMs. We apply our method to open-ended medical diagnostics, combining 40,762 differential diagnoses made by physicians with the diagnoses of five state-of-the art LLMs across 2,133 text-based medical case vignettes. We show that hybrid collectives of physicians and LLMs outperform both single physicians and physician collectives, as well as single LLMs and LLM ensembles. This result holds across a range of medical specialties and professional experience and can be attributed to humans' and LLMs' complementary contributions that lead to different kinds of errors. Our approach highlights the potential for collective human and machine intelligence to improve accuracy in complex, open-ended domains like medical diagnostics.

Proceedings of the National Academy of SciencesVol. 122(24)
Harvey Mudd College (US), Kaiser Permanente (US), University of California, San Francisco (US), University of Cologne (DE), University of Oxford (GB), Max Planck Institute for Human Development (DE), Centre for Artificial Intelligence and Robotics (IN), Rational (Germany) (DE), Innovation Cluster (Canada) (CA), National Research Council (RO), Human Immunome Project (US), Institute of Cognitive Sciences and Technologies (IT), The Human Diagnosis Project, Technische Universität Berlin (DE)
Kaiser Permanente, Harvey Mudd College, University of Oxford, European Commission, Deutsche Forschungsgemeinschaft, Max-Planck-Gesellschaft, Universität zu Köln, Max-Planck-Institut für Bildungsforschung, HORIZON EUROPE Framework Programme, HORIZON EUROPE European Research Council
Openalex Percentile: Top 1%
Clinical Reasoning and Diagnostic Skills
22.74
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.