Artificial intelligence improves bronchoscopy performance – a randomized cross-over trial.

<bold>Background:</bold> Bronchoscopy is a technical challenging procedure, and segments can be missed even for experienced bronchoscopists. <bold>Aim:</bold> To evaluate if an automatic bronchial identification system based on artificial intelligence (AI) could help bronchoscopists to perform more complete and structured procedures through automatic guidance. <bold>Methods:</bold> 101 participants were included from six different continents at the European Respiratory Society annual conference in Milan, 9-13th September 2023. Participants were split into three groups based on experience: Novices (0 bronchoscopies), Intermediates (1-249 bronchoscopies), and Experienced (≥250 bronchoscopies). The participants performed two bronchoscopies on a realistic physical phantom, one with AI (AmbuBPStrainingGUIDEv.0.0.1, Prototype version, Ambu) and one Standard procedure. The F1-group received AI-guidance for their first procedure, the F2-group for their second. A cross-over randomization controlled for learning by testing. All procedures were automatically rated according to the outcome measures: Inspected segments, Structured Progressions, and Procedure Time. <bold>Results:</bold> AI guidance caused the participants to inspect more segments, (mean difference, paired t-test: +6.0 segments, P<.001), perform more Structured Progressions (+5.2 progressions, P<.001), and spend more time on the procedure (+72 seconds, P<.001) compared to their standard procedures. <bold>Conclusions:</bold> AI-guidance helped bronchoscopists of all experience levels to inspect more segments in a more structured order. Clinical implementation of AI guidance could help ensure and document more complete bronchoscopy procedures in the future.