Machine learning mortality classification in clinical documentation with increased accuracy in visual‐based analyses

Aim The role of machine learning on clinical documentation for predictive outcomes remains undefined. We aimed to compare three neural networks on inpatient providers’ notes to predict mortality in neonatal hypoxic‐ischaemic encephalopathy (HIE). Methods Using Children's Hospitals Neonatal Data...

Full description

Saved in:
Bibliographic Details
Published in:Acta Paediatrica 2020-07, Vol.109 (7), p.1346-1353
Main Authors: Slattery, Susan M., Knight, Daniel C., Weese‐Mayer, Debra E., Grobman, William A., Downey, Doug C., Murthy, Karna
Format: Article
Language:English
Subjects:
Accuracy
Child
clinical documentation
deep learning
Documentation
electronic health records
Encephalopathy
Humans
Hypothermia
Hypothermia, Induced
Hypoxia
Hypoxia-Ischemia, Brain - therapy
Infant
Infant, Newborn
Infants
Learning algorithms
Machine Learning
Mortality
Neonates
Neural networks
Neural Networks, Computer
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Aim The role of machine learning on clinical documentation for predictive outcomes remains undefined. We aimed to compare three neural networks on inpatient providers’ notes to predict mortality in neonatal hypoxic‐ischaemic encephalopathy (HIE). Methods Using Children's Hospitals Neonatal Database, non‐anomalous neonates with HIE treated with therapeutic hypothermia were identified at a single‐centre. Data were linked with the initial seven days of documentation. Exposures were derived using the databases and applying convolutional and two recurrent neural networks. The primary outcome was mortality. The predictive accuracy and performance measures for models were determined. Results The cohort included 52 eligible infants. Most infants survived (n = 36, 69%) and 23 had severe HIE (44%). Neural networks performed above baseline and differed in their median accuracy for predicting mortality (P = .0001): recurrent models with long short‐term memory 69% (25th, 75th percentile 65, 73%) and gated‐recurrent model units 65% (62, 69%) and convolutional 72% (64, 96%). Convolutional networks’ median specificity was 81% (72, 97%). Conclusion The neural network models demonstrated fundamental validity in predicting mortality using inpatient provider documentation. Convolutional models had high specificity for (excluding) mortality in neonatal HIE. These findings provide a platform for future model training and ultimately tool development to assist clinicians in patient assessments and risk stratifications.
ISSN:0803-5253
1651-2227
DOI:10.1111/apa.15109