Title
Regression-Based Noninvasive Estimation Of Intracranial Pressure
Abstract
Monitoring of intracranial pressure (ICP) is indicated in patients with a variety of conditions affecting the brain and cerebrospinal fluid space. The measurement of ICP, however, is highly invasive as it requires placement of a catheter in the brain tissue or cerebral ventricular spaces. Several noninvasive techniques have been proposed to overcome this issue, and one class of approaches is based on analyzing cerebral blood flow velocity (CBFV) and arterial blood pressure (ABP) waveforms to infer ICP. Here, we analyze a physiologic model linking ICP to CBFV and ABP and present a regression-based approach to estimating ICP. We tested the model on 20 datasets recorded from three patients in intensive care. Our estimates achieve a mean error (bias) of -1.12 mmHg and a standard deviation of the error of 5.56 mmHg, for a root-mean-square error of 5.68 mmHg, when compared against the invasive ICP measurement. Since transcranial Doppler ultrasound based CBFV measurements depend on the Doppler angle phi between the direction of the ultrasound beam and the (main) direction of blood flow velocity, we investigated the robustness of our ICP estimates against variations in phi. Our results show a change in the estimated ICP that is < 1 mmHg if we assume phi similar to N (mu; sigma(2)), with mu = 0 and sigma = 10 degrees.
Year
DOI
Venue
2017
10.1109/EMBC.2017.8037733
2017 39TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)
Field
DocType
Volume
Biomedical engineering,Computer science,Transcranial Doppler,Anesthesia,Blood pressure,Artificial intelligence,Doppler effect,Computer vision,Blood flow,Intracranial pressure,Cerebral blood flow,Intensive care,Ultrasound
Conference
2017
ISSN
Citations 
PageRank 
1094-687X
0
0.34
References 
Authors
0
6