Accounting for Underspecification in Statistical Claims of Model Superiority

Thomas Sanchez, Pedro M Gordaliza, Meritxell Bach Cuadra

Keywords: underspecification; validation; statistical comparison

TL;DR: Underspecification increases the probabilities of false outperformance claims in machine learning for medical imaging

Abstract: Machine learning methods are increasingly applied in medical imaging, yet many reported improvements lack statistical robustness: recent works have highlighted that small but significant performance gains are highly likely to be false positives. However, these analyses do not take *underspecification* into account: the fact that models achieving similar validation scores may behave differently on unseen data due to random initialization or training dynamics. Here, we extend a recent statistical framework modeling false outperformance claims to include underspecification as an additional variance component. Our simulations demonstrate that even modest seed variability ($\sim1$%) substantially increases the evidence required to support superiority claims. Our findings underscore the need for explicit modeling of training variance when validating medical imaging systems.

Submission Number: 19