van der Zander QEW, Roumans R, Kusters CHJ, Dehghani N, Masclee AAM, de With PHN, van der Sommen F, Snijders CCP, Schoon EJ. Appropriate trust in artificial intelligence for the optical diagnosis of colorectal polyps: the role of human/artificial intelligence interaction.
Gastrointest Endosc 2024;
100:1070-1078.e10. [PMID:
38942330 DOI:
10.1016/j.gie.2024.06.029]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/12/2023] [Revised: 03/26/2024] [Accepted: 06/19/2024] [Indexed: 06/30/2024]
Abstract
BACKGROUND AND AIMS
Computer-aided diagnosis (CADx) for the optical diagnosis of colorectal polyps is thoroughly investigated. However, studies on human-artificial intelligence interaction are lacking. Our aim was to investigate endoscopists' trust in CADx by evaluating whether communicating a calibrated algorithm confidence score improved trust.
METHODS
Endoscopists optically diagnosed 60 colorectal polyps. Initially, endoscopists diagnosed the polyps without CADx assistance (initial diagnosis). Immediately afterward, the same polyp was again shown with a CADx prediction: either only a prediction (benign or premalignant) or a prediction accompanied by a calibrated confidence score (0-100). A confidence score of 0 indicated a benign prediction, 100 a (pre)malignant prediction. In half of the polyps, CADx was mandatory, and for the other half, CADx was optional. After reviewing the CADx prediction, endoscopists made a final diagnosis. Histopathology was used as the reference standard. Endoscopists' trust in CADx was measured as CADx prediction utilization: the willingness to follow CADx predictions when the endoscopists initially disagreed with the CADx prediction.
RESULTS
Twenty-three endoscopists participated. Presenting CADx predictions increased the endoscopists' diagnostic accuracy (69.3% initial vs 76.6% final diagnosis, P < .001). The CADx prediction was used in 36.5% (n = 183 of 501) of disagreements. Adding a confidence score led to lower CADx prediction utilization, except when the confidence score surpassed 60. Mandatory CADx decreased CADx prediction utilization compared to optional CADx. Appropriate trust-using correct or disregarding incorrect CADx predictions-was 48.7% (n = 244 of 501).
CONCLUSIONS
Appropriate trust was common, and CADx prediction utilization was highest for the optional CADx without confidence scores. These results express the importance of a better understanding of human-artificial intelligence interaction.
Collapse