Study shows novel AI technology is better predictor of stroke than traditional methods

2604
Brajesh Lal during a previous SVS ONLINE session

Boston-based medical technology company Elucid Bio, maker of the Food and Drug Administration (FDA)-cleared and CE-marked vascuCAP software, announced Wednesday, July 1, that its novel artificial intelligence (AI) technology demonstrated a more than 70% improvement in accuracy of stroke prediction as compared to stenosis-based guidelines over a six-year time period.

The interim results of the CRISP trial are set to be presented on Thursday, July 2, during Scientific Session 9 at SVS ONLINE, the digital replacement for the Society for Vascular Surgery’s Vascular Annual Meeting.

The study, led by Brajesh Lal, MD, director of both the University of Maryland’s Center for Vascular Diagnostics and the NIH Vascular Imaging Core Facility, with participation by the Cleveland Clinic, Weill-Cornell and Case Western, sought to improve prediction of major adverse neurological events  by applying AI to traditional carotid imaging using the Elucid Bio vascuCAP software.

The software analyzes routinely-available CT angiograms to characterize plaque tissues in a manner that could previously only be done with a tissue specimen, Elucid Bio said.

Stroke remains the leading cause of disability in the United States and is the 5th leading cause of death. Current risk assessment for patients with carotid atherosclerosis relies primarily on assessing the degree of stenosis. More reliable risk stratification has the potential to improve patient selection for more aggressive treatment for MANE by incorporating a combination of carotid plaque geometry, plaque tissue composition, patient demographics and clinical insights.

“These study results demonstrate that the vascuCAP’s artificial intelligence algorithms for risk stratification in carotid atherosclerosis are a better predictor of stroke than stenosis assessment alone,” stated Lal. “Implementing this predictive model on asymptomatic patients in the clinical setting could help identify and inform treatment for those at high-risk for future major adverse neurological events.”

The Elucid Bio technology is currently in clinical use and may have applications for informing risk for COVID-19 patients who have been experiencing strokes at a significantly higher rate, the medical technology company said. The software can identify endothelial damage—a subtle, but potentially deadly effect of COVID-19 that can cause blood clotting that leads to stroke, the company added.

1 COMMENT

  1. Predicting stroke risk based on ultrasound plaque morphology has been the Holy Grail for cerebro-vascular disease for the past 40 years. This interesting breakthrough, using AI and CT imaging deserves further investigation in a much larger population. Congratulations to BK Lal for this work and his relentless pursuit of improving the care of patients with cerebro-vascular disease.

LEAVE A REPLY

Please enter your comment!
Please enter your name here