Lotta Meijerink

Dennis Ulmer, Lotta Meijerink, Giovanni Cinà

When deploying machine learning models in high-stakes real-world environments such as health care, it is crucial to accurately assess the uncertainty concerning a model's prediction on abnormal inputs. However, there is a scarcity of literature analyzing this problem on medical data, especially on mixed-type tabular data such as Electronic Health Records. We close this gap by presenting a series of tests including a large variety of contemporary uncertainty estimation techniques, in order to determine whether they are able to identify out-of-distribution (OOD) patients. In contrast to previous work, we design tests on realistic and clinically relevant OOD groups, and run experiments on real-world medical data. We find that almost all techniques fail to achieve convincing results, partly disagreeing with earlier findings.

Lotta Meijerink, Giovanni Cinà, Michele Tonutti

In a data-scarce field such as healthcare, where models often deliver predictions on patients with rare conditions, the ability to measure the uncertainty of a model's prediction could potentially lead to improved effectiveness of decision support tools and increased user trust. This work advances the understanding of uncertainty estimation for classification and risk prediction on medical tabular data, in a two-fold way. First, we expand and refine the set of heuristics to select an uncertainty estimation technique, introducing tests for clinically-relevant scenarios such as generalization to uncommon pathologies, changes in clinical protocol and simulations of corrupted data. We furthermore differentiate these heuristics depending on the clinical use-case. Second, we observe that ensembles and related techniques perform poorly when it comes to detecting out-of-domain examples, a critical task which is carried out more successfully by auto-encoders. These remarks are enriched by considerations of the interplay of uncertainty estimation with class imbalance, post-modeling calibration and other modeling procedures. Our findings are supported by an array of experiments on toy and real-world data.