Evaluation of Use of Artificial Intelligence (AI) and Machine Learning to Practice and Master Colonoscopic Skills.

Abstract

Abstract Objective The abstract concisely summarizes the research project "Evaluation of Use of Artificial Intelligence (AI) and Machine Learning to Practice and Master Colonoscopic Skills." It outlines the background of flexible colonoscopy, highlighting its importance in diagnosing and treating colorectal diseases. The study emphasizes the potential of VR simulators to provide a safe, controlled training environment. It identifies the need for quantitative data defining the number of procedures required to achieve competence in VR training. The research aims to demonstrate the effect of the use of AI and machine learning in colonoscopy traning.by conducting experiments with novice subjects and collecting and analyzing data. The expected outcome is to provide quantified evidence supporting the use of VR and AI in colonoscopy training, ultimately improving training methods and enhancing patient safety. Methods The methodology of this study involves a mixed approach where novice subjects undergo hands-on training on VR colonoscopy systems. Participants are selected based on specific criteria, and consent is obtained before involvement. The study utilises a VR simulator alongside physical phantom models to ensure comprehensive training. Detailed experimental procedures are followed, including simulation-based training sessions and performance assessments. Data is collected systematically through observation, performance metrics, and feedback and analysed using statistical methods such as SPSS to quantify the proficiency-gain curve and evaluate the effectiveness of VR training in mastering colonoscopic skills. Results This study included colonoscopy examinations performed on eight volunteers four times and compared with four experts who were examined 500 times. The results indicated that the average time taken to complete the procedure varied between (5:03 to 13:10 minutes) and the time to reach the cecum (4:58 to 10:10 minutes), with statistically significant differences between volunteers (P = 0.03) in the time to reach the cecum. The comparison between the expert group and volunteers also showed statistically significant differences between experts and volunteers in some aspects, such as the time taken to reach the cecum (2:22 minutes for experts versus 7:37 minutes for volunteers). Although the percentage of time in which a clear vision was maintained was higher among experts (96.75%) compared to volunteers (92.62%), this percentage among volunteers was also statistically significant, reflecting the importance of training and practice in improving this skill. Conclusion The conclusion of this study indicates that using VR simulators and AI in colonoscopy training significantly enhances skill acquisition, reduces the proficiency-gain curve, and ensures a safer training environment. The data analysis shows a marked improvement in performance among novice subjects trained with VR, validating the effectiveness of this approach. The study provides quantified evidence supporting the integration of VR and AI technologies in medical training programs, suggesting that such methods effective.