CHANGES IN EXAMINER BEHAVIOR CAUSED BY A COMPUTER-AIDED SYSTEM FOR POLYP DETECTION

Endoscopy, vol. 54, pp. S91

Abstract

Aims Multiple computer-aided systems for polyp detection (CADe) are currently introduced into clinical practice, with an unclear effect on examiner behavior. In particular, false positive detections could lead to prolonged examination time due to frequent misinterpretations of normal mucosa. In this work, we aimed to measure the influence of a CADe system on reaction time, mucosa misinterpretations, and changes in visual gaze pattern. Methods Participants with different levels of colonoscopy experience were assigned to examine short video sequences while eye movement was tracked. Videos comprised 17 sequences containing polyps and 12 sequences containing false positive activations of different lengths. Using a crossover design, videos were presented in two assessments with and without CADe (GI Genius, Medtronic) support. Reaction time for polyp detection, misinterpretation of normal mucosal surfaces, and eye-tracking metrics were evaluated. Results 21 participants performed a total of 1218 experiments. The CADe system was significantly faster in detecting polyps (1.16 sec) compared to the users (p<0.001). However, the reaction time of the user with or without the CADe system was similar (2.90 sec. vs 2.97 sec, p=0.678). Participants falsely identified a polyp in a median of 4 cases without CADe and 6 cases with CADe support. Eye traveling distance was significantly reduced with the use of the CADe system. Conclusions This work confirms that CADe systems detect polyps faster than humans. In addition, the CADe system led to increased misinterpretations of normal mucosa and decreased eye travel distance. Possible consequences of these findings are prolonged examination time and deskilling. Publication History Article published online: 14 April 2022 © 2022. European Society of Gastrointestinal Endoscopy. All rights reserved. Georg Thieme Verlag KG Rüdigerstraße 14, 70469 Stuttgart, Germany

Authors 6

1. Joel Troya

   Universitätsklinikum Würzburg

   Affiliation as printed

   University Hospital Würzburg, Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, Würzburg, Germany

2. Daniel Fitting

   Universitätsklinikum Würzburg

   Affiliation as printed

   University Hospital Würzburg, Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, Würzburg, Germany

3. Markus Brand

   Universitätsklinikum Würzburg

   Affiliation as printed

   University Hospital Würzburg, Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, Würzburg, Germany

4. Boban Sudarevic

   Universitätsklinikum Würzburg

   Affiliation as printed

   University Hospital Würzburg, Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, Würzburg, Germany

5. Jakob Nikolas Kather Aachen Department of Medicine III

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   University Hospital RWTH Aachen, Department of Medicine III, Aachen, Germany

6. Alexander G. Meining

   Universitätsklinikum Würzburg

   Affiliation as printed

   University Hospital Würzburg, Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, Würzburg, Germany