Automated Extraction of Stroke Severity from Unstructured Electronic Health Records using Natural Language Processing.

Marta FernandesM Brandon WestoverAneesh Bhim SinghalSahar F Zafar

Published in: medRxiv : the preprint server for health sciences (2024)

The automatic NLP-based model can enable large-scale stroke severity phenotyping from EHR and therefore support real-world quality improvement and comparative effectiveness studies in stroke.

Keyphrases

electronic health record
atrial fibrillation
quality improvement
deep learning
high throughput
machine learning
clinical decision support
autism spectrum disorder
adverse drug