Using near-infrared spectroscopy and a random forest regressor to estimate intracranial pressure

Filip A. J. Relander; Alexander Ruesch; Jason Yang; Deepshikha Acharya; Bradley Scammon; Samantha Schmitt; Emily C. Crane; Matthew A. Smith; Jana M. Kainerstorfer

doi:10.1117/1.NPh.9.4.045001

11 October 2022 Using near-infrared spectroscopy and a random forest regressor to estimate intracranial pressure

Filip A. J. Relander, Alexander Ruesch, Jason Yang, Deepshikha Acharya, Bradley Scammon, Samantha Schmitt, Emily C. Crane, Matthew A. Smith, Jana M. Kainerstorfer

Author Affiliations +

Neurophotonics, Vol. 9, Issue 4, 045001 (October 2022). https://doi.org/10.1117/1.NPh.9.4.045001

Abstract

Significance

Intracranial pressure (ICP) measurements are important for patient treatment but are invasive and prone to complications. Noninvasive ICP monitoring methods exist, but they suffer from poor accuracy, lack of generalizability, or high cost.

Aim

We previously showed that cerebral blood flow (CBF) cardiac waveforms measured with diffuse correlation spectroscopy can be used for noninvasive ICP monitoring. Here we extend the approach to cardiac waveforms measured with near-infrared spectroscopy (NIRS).

Approach

Changes in hemoglobin concentrations were measured in eight nonhuman primates, in addition to invasive ICP, arterial blood pressure, and CBF changes. Features of average cardiac waveforms in hemoglobin and CBF signals were used to train a random forest (RF) regressor.

Results

The RF regressor achieves a cross-validated ICP estimation of 0.937r², 2.703-mmHg² mean squared error (MSE), and 95% confidence interval (CI) of [ − 3.064 3.160 ] mmHg on oxyhemoglobin concentration changes; 0.946r², 2.301-mmHg² MSE, and 95% CI of [ − 2.841 2.866 ] mmHg on total hemoglobin concentration changes; and 0.963r², 1.688 mmHg² MSE, and 95% CI of [ − 2.450 2.397 ] mmHg on CBF changes.

Conclusions

This study provides a proof of concept for the use of NIRS in noninvasive ICP estimation.

CC BY: © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

Citation Download Citation

Filip A. J. Relander, Alexander Ruesch, Jason Yang, Deepshikha Acharya, Bradley Scammon, Samantha Schmitt, Emily C. Crane, Matthew A. Smith, and Jana M. Kainerstorfer "Using near-infrared spectroscopy and a random forest regressor to estimate intracranial pressure," Neurophotonics 9(4), 045001 (11 October 2022). https://doi.org/10.1117/1.NPh.9.4.045001

Received: 16 June 2022; Accepted: 23 September 2022; Published: 11 October 2022

ACCESS THE FULL ARTICLE

JOURNAL ARTICLE
16 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY