Artificial Intelligence-Guided Bronchoscopy is Superior to Human Expert Instruction for the Performance of Critical-Care Physicians: A Randomized Controlled Trial
Primary result · MITResult — go to the resultMedian difference −7.9 sAuthors' conclusion
Training using an AI system resulted in faster and more efficient bronchoscopy performance by critical-care physicians when compared to expert human tutor instruction.
Study context
- Population
- Critical-care physicians, simulated setting
- Participants
- 40 physicians
- Comparison
- Artificial intelligence (AI)-guided bronchoscopy training vs expert tutor feedback
- AIGn = 19
- ETGn = 21reference
- Primary endpoint
- MIT, a measure of bronchoscopic performance efficiency
Methodological detailsnonblinded, parallel group, simulated setting, single academic university hospital
- Nonblinded
- Parallel group
- Simulated setting
- Single academic university hospital
Primary result
MIT
Median difference
−7.9 s
0.027
As reported in the abstract
Secondary outcomes
| Outcome | Estimate | P value |
|---|---|---|
| Procedure time (PT)Moderate effect size (0.36) | median difference −77 s | 0.022 |
| Segments revisited (SR)Moderate effect size (0.37) | median difference −7 segments | 0.019 |
Diagnostic completeness (DC), structured progress (SP)
- No significant difference between the groups for all other final test measures
Original publication
Artificial Intelligence-Guided Bronchoscopy is Superior to Human Expert Instruction for the Performance of Critical-Care Physicians: A Randomized Controlled Trial. Crit Care Med. Published 20 March 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →