Out-of-Distribution Detection for Medical Applications: Guidelines for Practical Evaluation

TL;DR

This paper provides practical guidelines and tests for selecting effective Out-of-Distribution detection methods in medical applications, demonstrated on Electronic Health Records to enhance safety and reliability.

Contribution

It introduces a set of evaluation guidelines for OOD detection methods tailored to medical datasets, addressing a gap in practical implementation strategies.

Findings

Guidelines help select suitable OOD detectors for medical data

Illustrated with a real-life Electronic Health Records case

Aims to improve safety in clinical machine learning applications

Abstract

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.