English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

One major impediment to the wider use of deep learning for clinical decisionmaking is the difficulty of assigning a level of confidence to modelpredictions. Currently, deep Bayesian neural networks and sparse Gaussianprocesses are the main two scalable uncertainty estimation methods. However,deep Bayesian neural network suffers from lack of expressiveness, and moreexpressive models such as deep kernel learning, which is an extension of sparseGaussian process, captures only the uncertainty from the higher level latentspace. Therefore, the deep learning model under it lacks interpretability andignores uncertainty from the raw data. In this paper, we merge features of thedeep Bayesian learning framework with deep kernel learning to leverage thestrengths of both methods for more comprehensive uncertainty estimation.Through a series of experiments on predicting the first incidence of heartfailure, diabetes and depression applied to large-scale electronic medicalrecords, we demonstrate that our method is better at capturing uncertainty thanboth Gaussian processes and deep Bayesian neural networks in terms ofindicating data insufficiency and distinguishing true positive and falsepositive predictions, with a comparable generalisation performance.Furthermore, by assessing the accuracy and area under the receiver operatingcharacteristic curve over the predictive probability, we show that our methodis less susceptible to making overconfident predictions, especially for theminority class in imbalanced datasets. Finally, we demonstrate how uncertaintyinformation derived by the model can inform risk factor analysis towards modelinterpretability.

Deep Bayesian Gaussian Processes for Uncertainty Estimation in Electronic Health Records