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/

Zendy Plus

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

Zendy Tools

Zendy Open

We present a neural network framework for learning a survival model topredict a time-to-event outcome while simultaneously learning a topic modelthat reveals feature relationships. In particular, we model each subject as adistribution over "topics", where a topic could, for instance, correspond to anage group, a disorder, or a disease. The presence of a topic in a subject meansthat specific clinical features are more likely to appear for the subject.Topics encode information about related features and are learned in asupervised manner to predict a time-to-event outcome. Our framework supportscombining many different topic and survival models; training the resultingjoint survival-topic model readily scales to large datasets using standardneural net optimizers with minibatch gradient descent. For example, a specialcase is to combine LDA with a Cox model, in which case a subject's distributionover topics serves as the input feature vector to the Cox model. We explain howto address practical implementation issues that arise when applying theseneural survival-supervised topic models to clinical data, including how tovisualize results to assist clinical interpretation. We study the effectivenessof our proposed framework on seven clinical datasets on predicting time untildeath as well as hospital ICU length of stay, where we find that neuralsurvival-supervised topic models achieve competitive accuracy with existingapproaches while yielding interpretable clinical topics that explain featurerelationships. Our code is available at:https://github.com/georgehc/survival-topics

Neural Topic Models with Survival Supervision: Jointly Predicting Time-to-Event Outcomes and Learning How Clinical Features Relate