How to account for early overly small risk sets in the analysis of pregnancy outcome data?-Comparison of different methods for stabilizing the Aalen-Johansen estimator.

Regina StegherrAnne-Katrin FietzMaria Hoeltzenbein Katarina DatheJan Beyersmann

Published in: Pharmacoepidemiology and drug safety (2023)

In the analyses of pregnancy data with rare events, the postpone approach is favorable as no events are excluded. However, the approach that ignores early events has the narrowest confidence interval.

Keyphrases

electronic health record
preterm birth
big data
pregnancy outcomes
artificial intelligence