Dynamic Mortality Risk Predictions in Pediatric Critical Care Using Recurrent Neural Networks

TL;DR

This paper presents a recurrent neural network model that dynamically predicts ICU mortality in pediatric patients by analyzing time-series data from electronic medical records, outperforming traditional scoring systems.

Contribution

The study introduces a novel RNN approach for real-time mortality prediction in PICU patients, leveraging extensive EMR data over a decade.

Findings

RNN significantly outperforms existing clinical scores.

Dynamic predictions improve over static models.

Model effectively incorporates diverse patient data.

Abstract

Viewing the trajectory of a patient as a dynamical system, a recurrent neural network was developed to learn the course of patient encounters in the Pediatric Intensive Care Unit (PICU) of a major tertiary care center. Data extracted from Electronic Medical Records (EMR) of about 12000 patients who were admitted to the PICU over a period of more than 10 years were leveraged. The RNN model ingests a sequence of measurements which include physiologic observations, laboratory results, administered drugs and interventions, and generates temporally dynamic predictions for in-ICU mortality at user-specified times. The RNN's ICU mortality predictions offer significant improvements over those from two clinically-used scores and static machine learning algorithms.