Reviewed by Lexie CornerSep 6 2024
Researchers at the Icahn School of Medicine at Mount Sinai have developed a noninvasive method that could significantly improve how physicians monitor intracranial hypertension, a condition where elevated brain pressure can lead to serious complications such as hemorrhages and strokes. The study was published in the journal npj Digital Medicine.
Artificial intelligence-derived intracranial pressure monitors vital information noninvasively, increasing accessibility and decreasing risk. By doing so, it could enable healthcare providers to intervene more quickly to save lives. Image Credit: Faris Gulamali and lab of Girish Nadkarni, MD, Ph.D., at Icahn Mount Sinai
The innovative method, powered by artificial intelligence (AI), offers a faster and safer alternative to the current standard of drilling into the skull for monitoring increased brain pressure.
Currently, invasive procedures that penetrate the skull are required to detect and monitor elevated brain pressure. Instead, the research team explored whether noninvasive waveform data—such as electrocardiograms, pulse oximetry readings for oxygen saturation, and waveforms from routine head ultrasounds in critical care patients—could be used to predict intracranial pressure.
They developed an AI model capable of simulating brain blood pressure, using de-identified patient data from those who had undergone invasive procedures like lumbar catheter implantations or pressure-sensitive skull probe insertions to measure intracranial pressure.
According to the researchers, this real-time monitoring tool allows for the immediate detection of significant changes, enabling healthcare professionals to respond more quickly, potentially saving lives.
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). 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.
Faris Gulamali, MD Candidate and Study First Author, Icahn Mount Sinai
The study used a retrospective analysis of data from two hospitals across several U.S. cities, and the device performed exceptionally well, detecting intracranial pressure within seconds.
Patients who fell within the top 25 % of intracranial pressure measurements during their hospital stay were found to have a 24-fold increased risk of subdural hemorrhage and a seven-fold increased likelihood of needing a craniectomy, a surgical procedure to relieve pressure on the brain.
The researchers emphasized that the relationship between intracranial pressure and clinical outcomes is correlational, not causal, and further investigation is needed to establish causality. Their next steps include conducting additional validation studies, particularly focused on ICU patients with neurological disorders.
The team also plans to seek FDA breakthrough device status to accelerate the path toward clinical adoption of this potentially life-saving innovation.
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. 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.
Girish Nadkarni, Study Senior Author, Icahn Mount Sinai
Girish Nadkarni, MD., Ph.D. is also 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 at the Division of Data-Driven and Digital Medicine.
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.
David L. Reich, Study Co-Author, Icahn Mount Sinai
David L. Reich is also the 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.
Reich said, “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.”
Co-authors from Icahn Mount Sinai, are Pushkala Jayaraman, (Ph.D. candidate); Ashwin S. Sawant, MD; Jacob Desman, MSE, BS (MD candidate); Benjamin Fox (Ph.D. candidate); Annette Chang, MS (MD candidate); Brian Y. Soong, (MD/Ph.D. candidate); Naveen Arivazagan, MS, BS; Alexandra S. Reynolds, MD; Son Q Duong, MD, MS; Akhil Vaid, MD; Patricia Kovatch, B.Sc.; Robert Freeman, DNP, RN; Ira S. Hofer, MD; Ankit Sakhuja, MBBS, MS; Neha S. Dangayach, MD; and Alexander W. Charney, MD, Ph.D.
The study was funded by the Scientific Computing and Data team at the Icahn School of Medicine at Mount Sinai, with support from the Clinical and Translational Science Awards from the National Center for Advancing Translational Sciences. The Office of Research Infrastructure at the National Institutes of Health provided additional backing.
Journal Reference:
Gulamali, F., et al. (2024) Derivation, external and clinical validation of a deep learning approach for detecting intracranial hypertension. npj Digital Medicine. doi.org/10.1038/s41746-024-01227-0.