Gaube, Susanne and Suresh, Harini and Raue, Martina and Lermer, Eva and Koch, Timo K. and Hudecek, Matthias F. C. and Ackery, Alun D. and Grover, Samir C. and Coughlin, Joseph F. and Frey, Dieter and Kitamura, Felipe C. and Ghassemi, Marzyeh and Colak, Errol (2023) Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays. SCIENTIFIC REPORTS, 13 (1): 1383. ISSN 2045-2322,
Full text not available from this repository. (Request a copy)Abstract
Artificial intelligence (AI)-generated clinical advice is becoming more prevalent in healthcare. However, the impact of AI-generated advice on physicians' decision-making is underexplored. In this study, physicians received X-rays with correct diagnostic advice and were asked to make a diagnosis, rate the advice's quality, and judge their own confidence. We manipulated whether the advice came with or without a visual annotation on the X-rays, and whether it was labeled as coming from an AI or a human radiologist. Overall, receiving annotated advice from an AI resulted in the highest diagnostic accuracy. Physicians rated the quality of AI advice higher than human advice. We did not find a strong effect of either manipulation on participants' confidence. The magnitude of the effects varied between task experts and non-task experts, with the latter benefiting considerably from correct explainable AI advice. These findings raise important considerations for the deployment of diagnostic advice in healthcare.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | ALGORITHM; |
| Subjects: | 600 Technology > 610 Medical sciences Medicine |
| Divisions: | Medicine > Abteilung für Krankenhaushygiene und Infektiologie Human Sciences > Institut für Psychologie > Lehrstuhl für Psychologie V (Sozial-, Arbeits- und Organisationspsychologie) - Prof. Dr. Peter Fischer |
| Depositing User: | Dr. Gernot Deinzer |
| Date Deposited: | 16 Mar 2024 13:38 |
| Last Modified: | 16 Mar 2024 13:38 |
| URI: | https://pred.uni-regensburg.de/id/eprint/60203 |
Actions (login required)
 |
View Item |
