An autonomous bronchoscopy robot controlled by artificial intelligence (BronchoBot) outperforms experienced bronchoscopists in a simulated setting

Background Performance in flexible bronchoscopy varies even among experienced bronchoscopists. This study aimed to compare an autonomous bronchoscopy robot (BronchoBot) to human bronchoscopists in a standardized simulation-based setting. Methods We compared 30 bronchoscopies performed by humans (10 novices, 10 intermediates, 10 experienced) to 10 bronchoscopies performed by BronchoBot on a realistic phantom. The primary outcomes were anatomy rating (0–12 points) and dexterity rating (0–6 points) assessed by two blinded expert raters. Secondary outcomes were: Diagnostic Completeness (DC; 0–18 segments), Structured Progress (SP; 0–18 progressions), Procedure Time (PT; seconds), and Mean Intersegmental Time (MIT, seconds/segment), assessed by an AI. Tertiary outcomes included five targeted navigations by BronchoBot to RB4→RB5→RB6 and LB8→LB9→LB10, following the bronchoscopy skills and task assessment (BSTAT) tool, rated by an AI. Results BronchoBot significantly outperformed all three human groups for all outcome measures. Anatomy-rating (novice, intermediate, experienced vs. BronchoBot): 4.8, 10.3, 10.3 versus 11.8 points, p-values<.001. Dexterity-rating: 2.0, 3.0, 4.5 versus 5.3 points, p-values<.001. DC: 9, 15, 16 versus 18 segments, p<.001, p=.001, p=0.003. SP: 2, 7, 8 versus 18 progressions, p-values<.001. PT: 281, 251, 190 versus 124 s, p-values<.001. MIT: 32, 16, 13 versus 7 s/segment, p-values<.001. BronchoBot successfully completed targeted navigation in all attempts for RB4→RB5→RB6: median±interquartile range: 26±2 s, and LB8→LB9→LB10 30±2 s. Conclusions BronchoBot outperformed experienced human bronchoscopists using validated assessment tools based on expert human and AI ratings. BronchoBot can serve a role as benchmarking expert performance in a simulated setting, but further development and evaluation are required for use in patients.