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.

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

The Society of Critical Care Medicine (SCCM) Podcast features in-depth interviews with leaders in critical care. Experts discuss hot topics in intensive care with perspectives from all members of the critical care team. Guests include authors from SCCM’s peer-reviewed journals, Critical Care Medicine, Pediatric Critical Care Medicine, and Critical Care Explorations, as well as thought leaders within the field. This is a new and updated channel, formerly known as the iCritical Care Podcast All Audio Channel.

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

Sign up to save your podcasts

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

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