LearnICU is a comprehensive library housing thousands of online educational materials, many available only to SCCM members. ​
Search the library or explore resources sorted by Knowledge Line (Category) or Content Type.

SCCM Pod-442 Continuous Prediction of Mortality in the PICU: A Recurrent Neural Network Model in a Single-Center Dataset

As a proof of concept, a recurrent neural network (RNN) model was developed using electronic medical record (EMR) data capable of continuously assessing a child’s risk of mortality throughout an ICU stay as a proxy measure of illness severity. Host Margaret M. Parker, MD, MCCM, is joined by Melissa D. Aczon, PhD, to discuss how the RNN model can process hundreds of input variables contained in a patient’s EMR and integrate them dynamically as measurements become available. The RNN’s high discrimination suggests its potential to provide an accurate, continuous, and real-time assessment of a child in the PICU. (Aczon M, et al. Ped Crit Care Med. 2021;22:519-529) Dr. Aczon is a principal data scientist at Children’s Hospital Los Angeles. Melissa D. Aczon, PhD is a Principal Data Scientist at Children’s Hospital Los Angeles. 

Published: 9/2/2021


Estimated Time: 30:50 min

Categories: Pediatrics, Neurology,
Content Type: Podcasts,