Though artificial intelligence is a hot topic in healthcare, most programs in the discussion are in the very early stages of development or are still mostly theoretical. Baltimore-based LifeBridge Health, however, has already found ways to integrate life-saving machine learning processes into stroke treatment, according to Daniel J. Durand, MD, the health system's chief innovation officer.
In an article published on LinkedIn, Dr. Durand described how LifeBridge has been using AI to analyze post-stroke brain scans for several years, using a recent stroke patient as an example of this work. After the patient arrived at the hospital with left-sided weakness, he was evaluated in a virtual "telestroke" consultation with a neurologist, who ordered a brain scan using RAPID imaging software.
RAPID uses a deep learning algorithm to analyze CT scan images and, within minutes, determine areas of the brain that are receiving little to no blood flow, a process that can take radiologists more than an hour. Another RAPID algorithm was also used to create a detailed image depicting blood vessel density, which showed that a large blood clot was blocking blood flow to one of the largest vessels in the patient's brain.
Ultimately, the AI technology helped LifeBridge physicians not only diagnose a right-sided stroke, but also identify the blood clot causing it and determine, via blood flow analysis, that most of the patient's brain was still salvageable through an emergency thrombectomy. Following the surgery, Dr. Durand wrote, the patient's symptoms immediately began to subside, and he is now expected to make almost a full recovery.
"In the past, prior to RAPID AI, such patients could not have been treated as quickly or as aggressively," Dr. Durand wrote. "Because 'time equals brain' in the golden hour of stroke, our ability to act quickly and with greater certainty means that there will be more lives saved and a higher quality of life for those who survive."
More articles about AI:
Cleveland Clinic, Case Western receive $3M NIH grant for machine learning-based imaging analysis
AI-powered neural decoder can turn thoughts into speech
FDA clears 1st AI smartphone device to detect 3 types of heart arrhythmia