Development and external validation of deep learning clinical prediction models using variable-length time series data.

Fereshteh S BashiriKyle A CareyJennie MartinJay L KoynerDana P EdelsonEmily R GilbertAnoop MayampurathMajid AfsharMatthew M Churpek

Published in: Journal of the American Medical Informatics Association : JAMIA (2024)

The LSTM architecture performs as well or better than some newer architectures, and PLE-DT may enhance the AUPRC in variable-length time series data for predicting clinical outcomes during external validation.

Keyphrases

deep learning
electronic health record
big data
artificial intelligence
data analysis
convolutional neural network