AI-Driven Diagnostic Assistance in Medical Inquiry: Reinforcement Learning Algorithm Development and Validation
This retrospective analysis of predominantly respiratory pediatric presentations in emergency and pediatrics departments demonstrated that an AI-driven diagnostic assistant had high diagnostic performance both in stand-alone use and in simulated collaboration with clinicians. Its investigation process was found to be consistent with the clinicians' medical investigation logic. These findings highlight the diagnostic assistant's promise in assisting the decision-making processes of health care professionals.
Authors
- Yefeng Zheng (ORCID: https://orcid.org/0000-0003-2195-2847)
- Xuyan Chen (ORCID: https://orcid.org/0000-0001-6468-3611)
- Sheng Wu (ORCID: https://orcid.org/0000-0003-0362-9894)
- Weijie He (ORCID: https://orcid.org/0000-0002-5523-1039)
- Ting Chen (ORCID: https://orcid.org/0000-0002-3228-9166)
- Rui Jiang (ORCID: https://orcid.org/0000-0002-7533-3753)
- Xuan Zou
- Yu Huang (ORCID: https://orcid.org/0000-0002-5465-4574)
- Yi Ouyang (ORCID: https://orcid.org/0000-0001-5987-451X)
- Yu Wu (ORCID: https://orcid.org/0000-0003-0453-5662)
- Lili Feng (ORCID: https://orcid.org/0000-0002-7166-2867)
- Zhen Zhang (ORCID: https://orcid.org/0009-0007-6716-9053)
- Yongsheng Wu (ORCID: https://orcid.org/0009-0007-1564-4043)
- Mengqi Yang (ORCID: https://orcid.org/0009-0005-8228-4565)
Institutions
- Tencent (China) (CN)
- Beijing Academy of Artificial Intelligence (CN)
- Tencent Healthcare (China) (CN)
- Shenzhen Center for Disease Control and Prevention (CN)
- Beijing Tsinghua Chang Gung Hospital (CN)
- Tsinghua University (CN)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2024-08-23
- DOI
- https://doi.org/10.2196/54616
- Citations
- 15
- Primary Topic
- Clinical Reasoning and Diagnostic Skills
- Type
- article
- Field-Weighted Citation Impact
- 7.55