Correcting hazard ratio estimates for outcome misclassification using multiple imputation with internal validation data.

Jiayi Ni Aaron Leong Kaberi Dasgupta Elham Rahme

Published in: Pharmacoepidemiology and drug safety (2017)

Multiple imputation is useful to correct for outcome misclassification in time-to-event analyses if complementary validation data are available from subsamples. Copyright © 2017 John Wiley & Sons, Ltd.

Keyphrases

electronic health record
big data
deep learning
clinical evaluation