Analyzing the role of model uncertainty for electronic health records

Published

Conference Paper

© 2020 Owner/Author. In medicine, both ethical and monetary costs of incorrect predictions can be significant, and the complexity of the problems often necessitates increasingly complex models. Recent work has shown that changing just the random seed is enough for otherwise well-tuned deep neural networks to vary in their individual predicted probabilities. In light of this, we investigate the role of model uncertainty methods in the medical domain. Using RNN ensembles and various Bayesian RNNs, we show that population-level metrics, such as AUC-PR, AUC-ROC, log-likelihood, and calibration error, do not capture model uncertainty. Meanwhile, the presence of significant variability in patient-specific predictions and optimal decisions motivates the need for capturing model uncertainty. Understanding the uncertainty for individual patients is an area with clear clinical impact, such as determining when a model decision is likely to be brittle. We further show that RNNs with only Bayesian embeddings can be a more efficient way to capture model uncertainty compared to ensembles, and we analyze how model uncertainty is impacted across individual input features and patient subgroups.

Full Text

Duke Authors

Cited Authors

  • Dusenberry, MW; Tran, D; Choi, E; Kemp, J; Nixon, J; Jerfel, G; Heller, K; Dai, AM

Published Date

  • February 4, 2020

Published In

  • Acm Chil 2020 Proceedings of the 2020 Acm Conference on Health, Inference, and Learning

Start / End Page

  • 204 - 213

International Standard Book Number 13 (ISBN-13)

  • 9781450370462

Digital Object Identifier (DOI)

  • 10.1145/3368555.3384457

Citation Source

  • Scopus