Mitigating Cognitive Biases in Clinical Decision-Making Through Multi-Agent Conversations Using Large Language Models: Simulation Study
The multi-agent framework demonstrated an ability to re-evaluate and correct misconceptions, even in scenarios with misleading initial investigations. In addition, the LLM-driven, multi-agent conversation framework shows promise in enhancing diagnostic accuracy in diagnostically challenging medical scenarios.
Authors
- Hairil Rizal Abdullah (ORCID: https://orcid.org/0000-0003-1916-0832)
- Daniel Shu Wei Ting (ORCID: https://orcid.org/0000-0003-2264-7174)
- Yilin Ning (ORCID: https://orcid.org/0000-0002-6758-4472)
- Sui An Lie (ORCID: https://orcid.org/0000-0001-8565-1934)
- Nan Liu (ORCID: https://orcid.org/0000-0003-3610-4883)
- Irene Li (ORCID: https://orcid.org/0000-0002-1851-5390)
- Rui Yang (ORCID: https://orcid.org/0009-0006-0597-7197)
- Yuhe Ke (ORCID: https://orcid.org/0000-0001-7193-4749)
- Taylor Xin Yi Lim (ORCID: https://orcid.org/0000-0001-7047-3418)
Institutions
- National University of Singapore (SG)
- Singapore General Hospital (SG)
- Singapore National Eye Center (SG)
- Singapore Eye Research Institute (SG)
- Duke-NUS Medical School (SG)
- The University of Tokyo (JP)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2024-11-19
- DOI
- https://doi.org/10.2196/59439
- Citations
- 38
- Primary Topic
- Clinical Reasoning and Diagnostic Skills
- Type
- article
- Field-Weighted Citation Impact
- 19.12