Deep Bayesian Gaussian processes for uncertainty estimation in electronic health records
Open Access
- 19 October 2021
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 11 (1) , 1-13
Abstract
One major impediment to the wider use of deep learning for clinical decision making is the difficulty of assigning a level of confidence to model predictions. Currently, deep Bayesian neural networks and sparse Gaussian processes are the main two scalable uncertainty estimation methods. However, deep Bayesian neural networks suffer from lack of expressiveness, and more expressive models such as deep kernel learning, which is an extension of sparse Gaussian process, captures only the uncertainty from the higher-level latent space. Therefore, the deep learning model under it lacks interpretability and ignores uncertainty from the raw data. In this paper, we merge features of the deep Bayesian learning framework with deep kernel learning to leverage the strengths of both methods for a more comprehensive uncertainty estimation. Through a series of experiments on predicting the first incidence of heart failure, diabetes and depression applied to large-scale electronic medical records, we demonstrate that our method is better at capturing uncertainty than both Gaussian processes and deep Bayesian neural networks in terms of indicating data insufficiency and identifying misclassifications, with a comparable generalization performance. Furthermore, by assessing the accuracy and area under the receiver operating characteristic curve over the predictive probability, we show that our method is less susceptible to making overconfident predictions, especially for the minority class in imbalanced datasets. Finally, we demonstrate how uncertainty information derived by the model can inform risk factor analysis towards model interpretability.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Advances in Variational InferenceIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Temporal trends and patterns in heart failure incidence: a population-based study of 4 million individualsThe Lancet, 2018
- Chronic low back pain and the risk of depression or anxiety symptoms: insights from a longitudinal twin studyThe Spine Journal, 2017
- Anxiety and Depression: Linkages with Viral DiseasesPublic Health Reviews, 2012
- Encyclopedia of Database Systems2009
- Probability distribution and entropy as a measure of uncertaintyJournal of Physics A: Mathematical and Theoretical, 2008
- Gaussian Processes in Machine Learning2004
- Bayesian classification with Gaussian processesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- The Effects of Adding Noise During Backpropagation Training on a Generalization PerformanceNeural Computation, 1996
- A CENTRAL LIMIT THEOREM AND A STRONG MIXING CONDITIONProceedings of the National Academy of Sciences, 1956