Deep Bayesian Gaussian Processes for Uncertainty Estimation in Electronic Health Records

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 network suffers 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 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 distinguishing true positive and false positive predictions, with a comparable generalisation 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.

arXiv comment21 pages

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)
• A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference
• When Gaussian Process Meets Big Data: A Review of Scalable GPs
• Quality of Uncertainty Quantification for Bayesian Neural Network Inference
• Rates of Convergence for Sparse Variational Gaussian Process Regression
• Improving Clinical Predictions through Unsupervised Time Series Representation Learning

Cited by in corpus (5)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients
• Hi-BEHRT: Hierarchical Transformer-based model for accurate prediction of clinical events using multimodal longitudinal electronic health records
• UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced Data
• Risk factor identification for incident heart failure using neural network distillation and variable selection