Impact of AI recommendation correctness on diagnostic accuracy in clinical decision-making
AI recommendations can exert a stronger influence on diagnostic decisions than healthcare provider-related factors. While AI support improved accuracy when correct, it reduced accuracy when incorrect, indicating overreliance on the system and posing a substantial safety risk. These findings highlight the dual nature of AI in clinical decision support and underscore the imperative for systems with consistently high quality in clinical practice. Equally important, clinicians must receive training and support to critically assess AI recommendations when making clinical decisions.
Authors
- Ursula Hübner (ORCID: https://orcid.org/0000-0001-5372-2339)
- Niels Hannemann
- Jan-Oliver Kutza
- Dorothee Busch (ORCID: https://orcid.org/0000-0001-5176-8157)
- Birgit Babitsch (ORCID: https://orcid.org/0000-0002-8722-3332)
- Jens Hüsers (ORCID: https://orcid.org/0000-0003-3324-9155)
- Mareike Przysucha
- Florian Kücking (ORCID: https://orcid.org/0009-0005-0808-6552)
Institutions
- Osnabrück University (DE)
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- Hochschule Osnabrück (DE)
Publication Details
- Journal
- International Journal of Medical Informatics
- Published
- 2025-12-13
- DOI
- https://doi.org/10.1016/j.ijmedinf.2025.106223
- Citations
- 5
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 3.27