Detection of Out-of-Distribution (OOD) samples in real time is a crucial safety check for deployment of machine learning models in the medical field. Despite a growing number of uncertainty quantification techniques, there is a lack of evaluation guidelines on how to select OOD detection methods in practice. This gap impedes implementation of OOD detection methods for real-world applications. Here, we propose a series of practical considerations and tests to choose the best OOD detector for a specific medical dataset. These guidelines are illustrated on a real-life use case of Electronic Health Records (EHR). Our results can serve as a guide for implementation of OOD detection methods in clinical practice, mitigating risks associated with the use of machine learning models in healthcare.
@article{arxiv.2109.14885,
title = {Out-of-Distribution Detection for Medical Applications: Guidelines for Practical Evaluation},
author = {Karina Zadorozhny and Patrick Thoral and Paul Elbers and Giovanni Cinà},
journal= {arXiv preprint arXiv:2109.14885},
year = {2022}
}