Utilizing timestamps of longitudinal electronic health record data to classify clinical deterioration events.

Li-Heng FuChris KnaplundKenrick CatoAdler PerotteMin-Jeoung KangPatricia C DykesDavid J Albers Sarah Collins Rossetti

Published in: Journal of the American Medical Informatics Association : JAMIA (2021)

This study demonstrates that our recurrent neural network models using only timestamps of longitudinal electronic health record data that reflect healthcare processes achieve well-performing discriminative power.

Keyphrases

electronic health record
neural network
healthcare
clinical decision support
adverse drug
cross sectional
machine learning
big data