Posted in | News | Spectroscopy

Intracranial Pressure Monitoring With Near-Infrared Spectroscopy

Brain bleeds, brain tumors, cerebral edema, traumatic brain injury, and hydrocephalus are some of the serious conditions that can lead to a rise in intracranial pressure (ICP), a deadly condition.

Image Credit: Siarhei

ICP monitoring is, therefore, a crucial component of patient management for people with these conditions.

Additionally, ICP measurements are relevant when estimating cerebral perfusion pressure (CPP), an indicator of cerebral autoregulation (CA). Neurovascular coupling and neuronal function are linked to CPP, and CA defines how the brain maintains a steady blood flow.

Precise ICP monitoring is a critical patient management tool given these extensive implications and uses in clinical decision-making.

The existing ICP monitoring techniques are precise, but they take a lot of time and there is a risk of bleeding or infection. Although there are noninvasive alternatives, they have drawbacks like insufficient generalizability, a lack of reliability, and low predictive capacity.

As a result, noninvasive techniques like diffuse correlation spectroscopy (DCS) and near-infrared spectroscopy (NIRS) are promising.

NIRS offers numerous benefits over other noninvasive techniques, including affordability, bedside suitability for long-term monitoring, and user independence.

Researchers from Carnegie Mellon University (CMU) successfully used a NIRS device to continuously monitor changes in hemoglobin content in a recent study that was published in Neurophotonics.

The researchers expanded on earlier research in which they calculated ICP from cardiac waveform characteristics obtained using DCS and also discovered a link between oxyhemoglobin concentration variations and ICP. 

We developed and trained a random forest (RF) regression algorithm to correlate the morphology of cardiac pulse waveforms obtained through NIRS with intracranial pressure.

Filip Relander, Study First Author, Carnegie Mellon University

The researchers performed early experiments in a preclinical model to validate their algorithm. They analyzed the variations in hemoglobin concentrations while measuring invasive ICP and arterial blood pressure variations. Then, to confirm their algorithm's accuracy, they looked at the performance of signals obtained from the hemoglobin concentration and CBF.

The results were encouraging from a proof-of-concept perspective. The real ICP measured using intrusive methods, and the ICP calculated using the RF algorithm were highly correlated.

We showed, by validating the findings 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, Study Senior Author and Associate Professor, Biomedical Engineering, Carnegie Mellon University

The results further demonstrated the applicability of the RF technique by showing that it could read waveform components collected from both NIRS and DCS.

The NIRS measurements can be paired with electrocardiograms and mean arterial blood pressure readings, often used for clinical evaluation, to obtain the parameters utilized in the algorithm. The potential for clinical usage of this RF-based technology would thus be enormous if it can provide reliable ICP readings in subsequent human trials.

Assessing ICP noninvasively is of great value for monitoring patients in a critical condition, such as those in the intensive care unit. The future of NIRS in this space is exciting!

Rickson C. Mesquita, Professor, University of Campinas

Journal Reference

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

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.