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

Deep learning (DL) has recently drawn much attention in image analysis,natural language process, and high-dimensional medical data analysis. Under thecausal direct acyclic graph (DAG) interpretation, the input variables withoutincoming edges from parent nodes in the DL architecture maybe assumed to berandomized and independent of each other. As in a regression setting, includingthe input variables in the DL algorithm would reduce the bias from thepotential confounders. However, failing to include a potential latent causalstructure among the input variables affecting both treatment assignment and theoutput variable could be additional significant source of bias. The primarygoal of this study is to develop new DL algorithms to estimate causalindividual event times for time-to-event data, equivalently to estimate thecausal time-to-event distribution with or without right censoring, accountingfor the potential latent structure among the input variables. Once the causalindividual event times are estimated, it would be straightforward to estimatethe causal average treatment effects as the differences in the averages of theestimated causal individual event times. A connection is made between theproposed method and the targeted maximum likelihood estimation (TMLE).Simulation studies are performed to assess improvement in prediction abilitiesof the proposed methods by using the mean square error (MSE)-based method andrank-based $C$-Index metric. The simulation results indicate that improvementon the prediction accuracy could be substantial particularly when there is acollider among the input variables. The proposed method is illustrated with apublicly available and influential breast cancer data set. The proposed methodhas been implemented by using PyTorch and uploaded athttps://github.com/yicjia/CausalDeepCENT.

CausalDeepCENT: Deep Learning for Causal Prediction of Individual Event Times