Flight rules for clinical AI: lessons from aviation for human-AI collaboration in medicine

The parallels between medicine and aviation are well-recognised. The aviation industry's early experience with automation improved safety and efficiency, but simultaneously introduced new vulnerabilities and occasionally created misplaced trust in complex systems. Aviation has developed a robust safety framework in response to these costly lessons. In this Perspective, which draws from the experiences of clinicians and aviation experts, we argue that it is now time for the medical community to consider how we can learn from these lessons as artificial intelligence (AI) becomes increasingly integrated into clinical care. We propose that this requires a shift in perspective from AI as "autopilot" to collaboration with a "digital copilot", as well as considerations of practicalities such as scenario-based training, clinician benchmarking, and minimum unaided practice, with the ultimate aim of optimising human-AI collaboration to improve patient care.