The Average Patient Fallacy
This addresses a critical bias in medical AI that can lead to missed diagnoses and ethical issues, though it is incremental in proposing specific fixes rather than a new paradigm.
The paper tackles the problem of machine learning in medicine being optimized for population averages, which marginalizes rare but critical cases, and proposes operational fixes like new metrics and weighted objectives to address this bias.
Machine learning in medicine is typically optimized for population averages. This frequency weighted training privileges common presentations and marginalizes rare yet clinically critical cases, a bias we call the average patient fallacy. In mixture models, gradients from rare cases are suppressed by prevalence, creating a direct conflict with precision medicine. Clinical vignettes in oncology, cardiology, and ophthalmology show how this yields missed rare responders, delayed recognition of atypical emergencies, and underperformance on vision-threatening variants. We propose operational fixes: Rare Case Performance Gap, Rare Case Calibration Error, a prevalence utility definition of rarity, and clinically weighted objectives that surface ethical priorities. Weight selection should follow structured deliberation. AI in medicine must detect exceptional cases because of their significance.