# The Average Patient Fallacy

arXiv: https://arxiv.org/abs/2509.26474 · HTML: https://mlsanity.com/paper/2509.26474/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 26 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 4 of 4)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Learning Models with Uniform Performance via Distributionally Robust Optimization](https://mlsanity.com/paper/1810.08750/) (2018)
- [Principles alone cannot guarantee ethical AI](https://mlsanity.com/paper/1906.06668/) (2019)

## Built on by (most cited first, 1 of 1)

- [An N-of-1 Artificial Intelligence Ecosystem for Precision Medicine](https://mlsanity.com/paper/2510.24359/) (2025)

## Abstract (arXiv)

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.