Assessment of Natural Language Processing Methods for Ascertaining the Expanded Disability Status Scale Score From the Electronic Health Records of Patients With Multiple Sclerosis: Algorithm Development and Validation Study.

Zhen Yang Chloe Pou-Prom Ashley Jones Michaelia Banning David Dai Muhammad M Mamdani Jiwon Oh Tony Antoniou

Published in: JMIR medical informatics (2022)

A combined keyword-CNN natural language processing model can extract and accurately predict EDSS scores from patient records. This approach can be automated for efficient information extraction in clinical and research settings.

Keyphrases

electronic health record
deep learning
machine learning
autism spectrum disorder
clinical decision support
multiple sclerosis
convolutional neural network
case report
oxidative stress
adverse drug
high throughput
healthcare
neural network