Keywords: safety, domain shift detection, subgroups, hypothesis testing, kernel methods
TL;DR: We demonstrate the limitations of OOD detection for subgroup shifts, i.e. shifts within the support of the original distribution. We show how such shifts can be detected on a population level instead and establish a baseline on histopathology images.
Abstract: The safe application of machine learning systems in healthcare relies on valid performance claims. Such claims are typically established in a clinical validation setting designed to be as close as possible to the intended use, but inadvertent domain or population shifts remain a fundamental problem. In particular, subgroups may be differently represented in the data distribution in the validation compared to the application setting. For example, algorithms trained on population cohort data spanning all age groups may be predominantly applied in elderly people. While these data are not ``out-of distribution'', changes in the prevalence of different subgroups may have considerable impact on algorithm performance or will at least render original performance claims invalid. Both are serious problems for safely deploying machine learning systems. In this paper, we demonstrate the fundamental limitations of individual example out-of-distribution detection for such scenarios, and show that subgroup shifts can be detected on a population-level instead. We formulate population-level shift detection in the framework of statistical hypothesis testing and show that recent state-of-the-art statistical tests can be effectively applied to subgroup shift detection in a synthetic scenario as well as real histopathology images.
Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
Paper Type: validation/application paper
Primary Subject Area: Transfer Learning and Domain Adaptation
Secondary Subject Area: Detection and Diagnosis
Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.
Code And Data: Code: https://github.com/lmkoch/subgroup-shift-detection Data: https://wilds.stanford.edu/get_started/ (Camelyon17), http://yann.lecun.com/exdb/mnist/ (MNIST)