A Deep Learning Framework for Deriving Noninvasive Intracranial Pressure Waveforms from Transcranial Doppler

Increased intracranial pressure (ICP) causes disability and mortality in the neurointensive care population. Current methods for monitoring ICP are invasive. We designed a deep learning framework using a domain adversarial neural network to estimate noninvasive ICP, from blood pressure, electrocardi...

Full description

Saved in:
Bibliographic Details
Published in:Annals of neurology 2023-07, Vol.94 (1), p.196-202
Main Authors: Megjhani, Murad, Terilli, Kalijah, Weinerman, Bennett, Nametz, Daniel, Kwon, Soon Bin, Velazquez, Angela, Ghoshal, Shivani, Roh, David J., Agarwal, Sachin, Connolly, E. Sander, Claassen, Jan, Park, Soojin
Format: Article
Language:English
Subjects:
Blood flow
Blood pressure
Blood Pressure - physiology
Cerebral blood flow
Cerebrovascular Circulation - physiology
Deep Learning
EKG
Electrocardiography
Flow velocity
Humans
Intracranial Hypertension - etiology
Intracranial pressure
Intracranial Pressure - physiology
Machine learning
Monitoring methods
Neural networks
Support vector machines
Ultrasonography, Doppler, Transcranial - adverse effects
Ultrasound
Waveforms
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:Increased intracranial pressure (ICP) causes disability and mortality in the neurointensive care population. Current methods for monitoring ICP are invasive. We designed a deep learning framework using a domain adversarial neural network to estimate noninvasive ICP, from blood pressure, electrocardiogram, and cerebral blood flow velocity. Our model had a mean of median absolute error of 3.88 ± 3.26 mmHg for the domain adversarial neural network, and 3.94 ± 1.71 mmHg for the domain adversarial transformers. Compared with nonlinear approaches, such as support vector regression, this was 26.7% and 25.7% lower. Our proposed framework provides more accurate noninvasive ICP estimates than currently available. ANN NEUROL 2023;94:196–202
ISSN:0364-5134
1531-8249
1531-8249
DOI:10.1002/ana.26682