Intracranial pressure (ICP) is a critical physiological parameter that may increase dangerously due to conditions like acute brain injury, stroke, or obstructions in cerebrospinal fluid flow. Symptoms of high ICP include headaches, blurred vision, vomiting, behavioral changes, and a reduced level of consciousness, posing serious health risks. Traditional ICP monitoring methods are highly invasive, involving the insertion of devices such as external ventricular drains (EVD) or intraparenchymal brain monitors (IPM) directly into the brain through the skull. These methods, while effective, carry significant risks including catheter misplacement, infection, and hemorrhaging, occurring in approximately 15.3%, 5.8%, and 12.1% of cases respectively. Additionally, they require surgical expertise and specialized equipment not always available in many medical settings, highlighting the need for less invasive monitoring techniques.

Now, researchers at Johns Hopkins University School of Medicine (Baltimore, MD, USA) have proposed a novel, less invasive method for monitoring ICP. Published in the July 12 journal of Computers in Biology and Medicine, their research explores the correlation between ICP waveforms and three commonly measured physiological signals in the ICU: invasive arterial blood pressure (ABP), photoplethysmography (PPG), and electrocardiography (ECG). By employing these data points, researchers trained various deep learning algorithms, achieving a predictive accuracy for ICP that is comparable or superior to existing methods. This research indicates the possibility of a new, noninvasive technique for ICP monitoring, potentially transforming patient care in critical settings.

“ICP is universally accepted as a critical vital sign - there is an imperative need to measure and treat ICP in patients with serious neurological disorders, yet the current standard for ICP measurement is invasive, risky, and resource-intensive,” said researcher Robert Stevens, MD., MBA. “Here we explored a novel approach leveraging Artificial Intelligence which we believed could represent a viable noninvasive alternative ICP assessment method.” 

http://www.gzjiayumed.com/en/index.asp .