Missing data matter: an empirical evaluation of the impacts of missing EHR data in comparative effectiveness research.

Yizhao ZhouJiasheng ShiRonen SteinXiaokang LiuRobert N BaldassanoChristopher B ForrestYong ChenJing Huang

Published in: Journal of the American Medical Informatics Association : JAMIA (2023)

Missing data in EHRs could lead to biased estimates of treatment effects and false negative findings in CER even after missing data were imputed. It is important to leverage the temporal information of disease trajectory to impute missing values when using EHRs as a data resource for CER and to consider the missing rate and the effect size when choosing an imputation method.

Keyphrases

electronic health record
big data
healthcare
machine learning
artificial intelligence
data analysis