Natali_Mis/istock via Getty Imag

Deep learning tool could improve brain pressure monitoring

A deep learning tool that uses routinely collected data could provide a noninvasive method for clinicians to monitor intracranial hypertension in intensive care patients.

A new study published in npj Digital Medicine details how an AI approach could help intensive care teams detect and monitor intracranial hypertension.

The condition -- characterized by increased pressure in the brain -- requires clinicians to act quickly to prevent serious complications, such as hemorrhage and stroke. The current gold standard for flagging and monitoring intracranial hypertension is an invasive procedure that involves drilling into the skull, which comes with risks, like infection.

To reduce these risks, a team at the Icahn School of Medicine at Mount Sinai set out to determine whether elevated brain pressure could be predicted using noninvasive waveform data, such as information from routine head ultrasounds, pulse oximetry and electrocardiograms.

Using de-identified data from patients who had their brain pressure captured via invasive methods, such as pressure-sensitive probes inserted into the skull or lumbar catheters, the researchers built a deep learning model. The tool is designed to generate a representation of brain blood pressure in real time, which could help clinicians more effectively monitor intracranial hypertension and intervene quickly.

"Increased pressure in the brain can lead to a range of serious complications. We created a noninvasive approach -- an AI-derived biomarker for detecting elevated brain pressure -- using data already routinely collected in intensive care units (ICUs)," explained first author Faris Gulamali, an MD candidate at Icahn Mount Sinai, in a press release. "Importantly, our study, the largest to date on intracranial hypertension, is the first to provide external validation for our algorithm and demonstrate a direct link between the biomarker and clinical outcomes, which is required for FDA approval."

Trained using data from the publicly available MIMIC-III Waveform Database and validated using Mount Sinai Hospital data collected from 2020 to 2022, the tool was able to accurately detect elevated intracranial pressure within a few seconds.

The retrospective analysis further revealed that patients in the top 25% of intracranial pressure measurements had a 24-fold increase in subdural hemorrhage risk and a seven-fold increase in the likelihood of requiring a craniectomy to relieve pressure on the brain.

The research team emphasized that more research is needed to validate the model, and future plans involve conducting studies focused on flagging ICU patients with neurological conditions.

"Our vision is to integrate this tool into ICUs as a standard part of monitoring critically ill patients. This technology represents a major leap forward, potentially transforming how we manage critically ill patients, reducing the need for risky procedures and enabling faster responses to neurological emergencies," said senior author Girish Nadkarni, MD, Ph.D., the Irene and Dr. Arthur M. Fishberg Professor of Medicine at Icahn Mount Sinai, director of the Charles Bronfman Institute of Personalized Medicine, and system chief for the division of data-driven and digital medicine. "In addition, our findings suggest it could be a valuable tool not only in neurology but also in managing other severe health conditions, such as post-cardiac arrest, glaucoma, and acute liver failure."

The researchers also indicated that they hope to apply for breakthrough device status with the FDA to help bring the clinical decision support tool to providers in the future.

"Our team's development of this AI-driven clinical decision support tool could be a significant step forward in advancing health outcomes for critically ill patients. If we can validate the use of this tool, we have the potential to improve patient safety by fine-tuning the use of invasive intracranial invasive monitoring in patients with the greatest potential for benefit," noted study co-author David L. Reich, MD, president of The Mount Sinai Hospital and Mount Sinai Queens, the Horace W. Goldsmith Professor of Anesthesiology and professor of artificial intelligence and human health at Icahn Mount Sinai. "One of our goals at Mount Sinai is using technology to bring the right team to the right patient at the right time. This tool exemplifies that commitment, offering a tailored solution that has the potential to improve the standard of care for patients at risk of life-threatening brain injuries."

Shania Kennedy has been covering news related to health IT and analytics since 2022.

Dig Deeper on Artificial intelligence in healthcare

xtelligent Health IT and EHR
xtelligent Healthtech Security
xtelligent Healthcare Payers
xtelligent Pharma Life Sciences
Close