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

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.

arXiv comment18 pages (5 of which in appendix), 9 figures

References in corpus (2)

• LSTM: A Search Space Odyssey
• Personalized Risk Scoring for Critical Care Patients using Mixtures of Gaussian Process Experts

Cited by in corpus (8)

• ISeeU: Visually interpretable deep learning for mortality prediction inside the ICU
• Identification of Pediatric Respiratory Diseases Using Fine-grained Diagnosis System
• Heterogeneous Similarity Graph Neural Network on Electronic Health Records
• A Machine Learning Early Warning System: Multicenter Validation in Brazilian Hospitals
• The Impact of Extraneous Variables on the Performance of Recurrent Neural Network Models in Clinical Tasks
• Predicting Individual Responses to Vasoactive Medications in Children with Septic Shock
• A Knowledge Distillation Ensemble Framework for Predicting Short and Long-term Hospitalisation Outcomes from Electronic Health Records Data
• Modelling the Neuroanatomical Progression of Alzheimer's Disease and Posterior Cortical Atrophy