False alerts in AI colonoscopy tools distract doctors for seconds
Gaze responses to false-positive computer-aided detection prompts during colonoscopy: a paired-video and real-time eye-tracking study
Artificial Intelligence
Summary
During colonoscopies, computer tools highlight spots that might be problems, but sometimes these alerts are wrong. The authors studied how often doctors’ eyes move to these wrong alerts and for how long they stay focused there. They found that doctors look at false alerts almost half to two-thirds of the time, and their attention lingers even after the alert disappears. This could slow down doctors or distract them during exams. The study suggests AI design should consider this distraction to make tools more helpful.
What this means in practice
- •For medical device designers: Improve AI colonoscopy systems by reducing distracting false-positive alerts to minimize doctor attention shifts during exams.
- •For human factors engineers: Assess and redesign clinical alert interfaces to limit attention burden from false-positive prompts in medical procedures.
Authors
Te Luo, Yan Zhu, Peiyao Fu, Ruijie Yang, Xian Yang, Quanlin Li, Pinghong Zhou, Shuo Wang
Abstract
False-positive computer-aided detection (CADe) prompts may divert endoscopists' attention during colonoscopy, yet the attentional impact of individual prompts remains unclear. We used event-locked eye tracking to quantify gaze attraction and attention occupation in complementary retrospective and prospective studies. In a retrospective paired-video experiment, 3 senior and 2 novice endoscopists viewed 60 colonoscopy videos with and without CADe. The prospective study recorded gaze during 42 real-time CADe-assisted colonoscopies performed by 9 senior endoscopists. Screened CADe prompts outside expert-annotated lesion windows were classified as false-positive artifact events. False-positive prompts attracted gaze in 48.6% (68/140) of retrospective observations and 65.2% (533/817) of prospective events. Among attraction events with complete recovery, median attention occupation lasted 1000 ms in the retrospective study and 1100 ms in the prospective study. Corresponding median prompt durations were 33 ms and 267 ms, with median time amplifications of 17.55-fold and 5.15-fold, respectively. In paired retrospective comparisons, visible artifact prompts drew gaze closer to the prompted region than did the same-coordinate unassisted reference. Secondary retrospective analyses showed high lesion gaze recognition without and with CADe (98.0% versus 99.0%). First gaze entry into lesion regions occurred 147.8 ms earlier with CADe. Across controlled and real-time clinical settings, false-positive CADe prompts frequently captured gaze, with attention persisting beyond prompt visibility. These findings support considering prompt-related attentional burden in CADe evaluation and design.