Endoscopists' Acceptance on the Implementation of Artificial Intelligence in Gastrointestinal Endoscopy: Development and Case Analysis of a Scale

Abstract

BackgroundThe purpose of this paper is to develop and validate a standardized endoscopist acceptance scale for the implementation of artificial intelligence (AI) in gastrointestinal endoscopy.MethodsAfter investigating endoscopists who have previously used AI and consulting with AI experts, we developed a provisional scale to measure the acceptance of AI as used in gastrointestinal endoscopy that was then distributed to a sample of endoscopists who have used AI. After analyzing the feedback data collected on the provisional scale, we developed a new formal scale with four factors. Cronbach's alpha, confirmatory factor analysis (CFA), content validity, and related validity were conducted to test the reliability and validity of the formal scale. We also constructed a receiver operating characteristic (ROC) curve in order to determine the scale's ability to distinguish higher acceptance and satisfaction.ResultsA total of 210 valid formal scale data points were collected. The overall Cronbach's alpha was 0.904. All the factor loadings were >0.50, of which the highest factor loading was 0.86 and the lowest was 0.54 (AVE = 0.580, CR = 0.953). The correlation coefficient between the total score of the scale and the satisfaction score was 0.876, and the area under the ROC curve was 0.949 ± 0.031. Endoscopists with a score higher than 50 tend to be accepting and satisfied with AI.ConclusionThis study yielded a viable questionnaire to measure the acceptance among endoscopists of the implementation of AI in gastroenterology.