Near-infrared spectroscopy may provide a cost-effective way to monitor intracranial pressure noninvasively

Near-infrared spectroscopy may provide a cost-effective way to monitor intracranial pressure noninvasively

An increase in intracranial pressure (ICP) is a dangerous condition that can be caused by cerebral hemorrhage, a brain tumor, cerebral edema, traumatic brain injury and hydrocephalus. ICP monitoring is therefore a key aspect of patient care in patients with these diseases. Furthermore, ICP measurements are relevant when estimating cerebral perfusion pressure (CPP), an indicator of cerebral autoregulation (CA).

CPP is associated with neuronal function and neurovascular coupling, and CA defines how the brain maintains constant blood flow. Given these broad implications and applications in clinical decision-making, precise ICP monitoring is an important tool for patient management. While current tools for ICP monitoring are accurate, they can cause bleeding or infection and are time-consuming.

Although noninvasive alternatives exist, they have limitations such as poor generalizability, low predictive capacity, and lack of reliability. Therefore, diffuse correlation spectroscopy (DCS) and near-infrared spectroscopy (NIRS) are emerging as promising noninvasive solutions. In particular, NIRS has several advantages over other non-invasive methods: low cost, bedside compatibility for long-term and continuous monitoring, and user independence.

In a new study published in Neurophotonics, researchers at Carnegie Mellon University (CMU) successfully used an NIRS device to continuously monitor changes in hemoglobin concentration. The team built on previous research in which they estimated ICP from cardiac waveform features measured with DCS and also identified the correlation between relative changes in oxyhemoglobin concentration and ICP. But how could they measure ICP using the NIRS data? The study's first author, Filip Relander, explains: "We developed and trained a random forest (RF) regression algorithm to correlate the morphology of the cardiac pulse waveforms obtained by NIRS with intracranial pressure."

To validate their algorithm, they conducted preliminary tests in a preclinical model. They measured fluctuations in invasive ICP and arterial blood pressure while profiling changes in hemoglobin concentrations. They then examined the performance of signals derived from hemoglobin concentration and CBF to closely examine the accuracy of their algorithm.

From a proof-of-concept perspective, the results were very promising. There was a high correlation between the ICP estimated using the RF algorithm and the actual ICP measured using invasive techniques.

We have shown, by validating the results with invasive ICP data, that the trained RF algorithm applied to NIRS-based cardiac waveforms can be used to estimate ICP with a high degree of precision.”

Jana Kainerstorfer, associate professor of biomedical engineering at CMU and senior author of the study

Furthermore, the results showed that the RF algorithm could interpret waveform features extracted from both NIRS and DCS, highlighting its usability.

The parameters used in the algorithm can be obtained from NIRS measurements, combined with electrocardiograms and mean arterial blood pressure, which are regularly used for clinical evaluation. Therefore, if this RF-based platform can provide robust ICP measurements in subsequent human studies, its potential for clinical use would be enormous. According to Neurophotonics Associate Editor Rickson C. Mesquita, Professor at the University of Campinas, "Non-invasive assessment of ICP is of great value for monitoring patients in critical condition, such as patients in intensive care. The future of NIRS in this field is exciting!"

Source:

SPIE – International Society for Optics and Photonics

Reference:

Relander, FAJ, et al. (2022) Using near-infrared spectroscopy and a random forest regressor to estimate intracranial pressure. Neurophotonics. doi.org/10.1117/1.NPh.9.4.045001.

.