A Deep Learning Framework for Deriving Noninvasive Intracranial Pressure Waveforms from Transcranial Doppler-Reference-Cited by-同舟云学术

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

Published:2023-06 Issue:1 Volume:94 Page:196-202
ISSN:0364-5134
Container-title:Annals of Neurology
language:en
Short-container-title:Annals of Neurology

Author:

Megjhani Murad¹²^ORCID,Terilli Kalijah¹²^ORCID,Weinerman Bennett²³,Nametz Daniel¹²,Kwon Soon Bin¹²,Velazquez Angela¹,Ghoshal Shivani¹⁴,Roh David J.¹⁴,Agarwal Sachin¹⁴,Connolly E. Sander⁴⁵,Claassen Jan¹⁴^ORCID,Park Soojin¹²⁴⁶

Affiliation:

1. Department of Neurology Columbia University New York NY USA

2. Program for Hospital and Intensive Care Informatics, Department of Neurology Columbia University New York NY USA

3. Division of Critical Care and Hospital Medicine, Department of Pediatrics Columbia University New York NY USA

4. NewYork‐Presbyterian Hospital at Columbia University Irving Medical Center New York NY USA

5. Department of Neurosurgery Columbia University New York NY USA

6. Department of Biomedical Informatics Columbia University New York NY USA

Abstract

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

Funder

American Heart Association

National Institute of Neurological Disorders and Stroke

Publisher

Wiley

Subject

Neurology (clinical),Neurology

Link

https://onlinelibrary.wiley.com/doi/pdf/10.1002/ana.26682

Reference18 articles.

1. Consensus summary statement of the International Multidisciplinary Consensus Conference on Multimodality Monitoring in Neurocritical Care

2. External Ventricular Drain Infections: Risk Factors and Outcome

3. Model-Based Noninvasive Estimation of Intracranial Pressure from Cerebral Blood Flow Velocity and Arterial Pressure

4. Noninvasive Prediction of Intracranial Pressure Curves Using Transcranial Doppler Ultrasonography and Blood Pressure Curves

5. A review of non‐invasive methods of monitoring intracranial pressure;Asiedu DP;J Neurol Res,2014

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Derivation, External Validation and Clinical Implications of a deep learning approach for intracranial pressure estimation using non-cranial waveform measurements;2024-01-30

2. A Real-Time Deep Learning Approach for Inferring Intracranial Pressure from Routinely Measured Extracranial Waveforms in the Intensive Care Unit;2023-05-18