Johns Hopkins Medication researchers have revealed new analysis that experiences on a possible different and less-invasive strategy to measure intracranial stress (ICP) in sufferers.
This analysis was revealed July 12 within the journal Computer systems in Biology and Medication.
ICP is a physiological variable that may enhance abnormally when one has acute mind damage, stroke or obstruction to the move of cerebrospinal fluid. Signs of elevated ICP could embrace complications, blurred imaginative and prescient, vomiting, adjustments in conduct and decreased degree of consciousness. It may be life-threatening, therefore the necessity for ICP monitoring in chosen sufferers who’re at elevated danger. Nevertheless, the present commonplace for ICP monitoring is extremely invasive: It requires the position of an exterior ventricular drain (EVD) or an intraparenchymal mind monitor (IPM) within the purposeful tissue within the mind consisting of neurons and glial cells by drilling by way of the cranium.
ICP is universally accepted as a crucial important signal – there’s an crucial must measure and deal with ICP in sufferers with severe neurological issues, but the present commonplace for ICP measurement is invasive, dangerous, and resource-intensive. Right here we explored a novel strategy leveraging Synthetic Intelligence which we believed might characterize a viable noninvasive different ICP evaluation methodology.”
Robert Stevens, MD., MBA, director, anesthesiology and significant care drugs precision drugs
EVD procedures carry numerous dangers together with catheter misplacement, an infection, and hemorrhaging at 15.3 %, 5.8 %, and 12.1 %, respectively, in line with latest analysis. EVD and IPM procedures additionally require surgical experience and specialised gear that’s not constantly accessible in lots of settings thus establishing a necessity for another methodology in inspecting and monitoring ICP in sufferers.
The Johns Hopkins College Faculty of Medication group, an interdisciplinary group led by Stevens, hypothesized that extreme types of mind damage, and elevations in ICP particularly, are related to pathological adjustments in systemic cardiocirculatory operate due, for instance, to dysregulation of the central autonomic nervous system. This speculation means that extracranial physiological waveforms might be studied to raised perceive mind exercise and ICP severity.
On this examine, the Johns Hopkins group got down to discover the connection between the ICP waveform and the three physiological waveforms which might be routinely captured within the ICU: invasive arterial blood stress (ABP), photoplethysmography (PPG) and electrocardiography (ECG). ABP, PPG and ECG knowledge have been used to coach and distinction a panel of various deep studying algorithms, leading to a degree of accuracy in figuring out ICP that rivals or exceeds different methodologies.
General examine findings counsel a very new, noninvasive different to watch ICP in sufferers.
Stevens says, “with validation, physiology-based AI options, such because the one used right here, might considerably broaden the proportion of sufferers and well being care settings by which ICP monitoring and administration might be delivered.”
Co-authors embrace latest Johns Hopkins College biomedical engineering graduates Shiker Nair ’23, Alina Guo ’23, Arushi Tandon ’23, and Joseph Boen ’22; grasp’s scholar Meer Patel; biomedical engineering seniors Atas Aggarwal, Ojas Chahal and Sreenidhi Sankararaman; Nicholas D. Durr, affiliate professor of biomedical engineering; Tej D. Azad, a resident doctor within the Johns Hopkins Division of Neurosurgery; and Romain Pirracchio, a professor of anesthesia on the College of California San Francisco.
Supply:
Journal reference:
Nair, S. S., et al. (2024). A Deep Studying Method for Producing Intracranial Stress Waveforms from Extracranial Indicators Routinely Measured within the Intensive Care Unit. Computer systems in Biology and Medication. doi.org/10.1016/j.compbiomed.2024.108677.