The Food and Drug Administration granted a 510(k) clearance for a triage AI solution (Cina Head; Avicenna.AI, La Ciotat, France) for neurovascular emergencies. The FDA's decision covers the automatic detection capabilities for both intracranial hemorrhage (ICH) and large vessel occlusion (LVO) from CT-scan imaging.
Using a combination of deep learning and machine learning technologies, the AI solution automatically detects and prioritizes acute ICH and LVO cases within 20 seconds, seamlessly alerting the radiologist within their existing systems and workflowThe AI solution ICH detection capability was validated using data from 814 cases conducted at more than 250 imaging centers across the US, with 96% accuracy, 91.4% sensitivity and 97.5% specificity. The product's LVO detection capability was validated based on 476 cases, with 97.7% accuracy 97.9% sensitivity and 97.6% specificity.
Dr. Peter Chang, radiologist and cofounder of Avicenna.AI, said, "When dealing with a stroke, time is of the essence and being able to prioritize effectively is critical to saving lives and improving outcomes. Not only does Cina Head help radiologists to identify pathologies quickly, but also to highlight those that require the most urgent care."
Cyril Di Grandi, cofounder and chief executive officer of Avicenna.AI, said, "We're excited to have received FDA clearance for Cina Head and are looking forward to working with emergency departments and stroke centers across the US to help improve detection, decision-making and patient outcomes. As a triage AI tool that identifies multiple pathologies, we believe that Cina Head delivers more value than AI tools or algorithms that only target a single condition."
The AI solution is the first in a family of AI tools for emergency radiology being developed by Avicenna.AI. Subsequent products spanning the trauma and vascular fields are expected to be unveiled in the next 12 months.
James Geyer, MD, and Paul Cox
Jill M. Giordano Farmer, DO
Monideep Dutt, MD; Jamika Hallman-Cooper, MD; Ekta Bery, MD; Mohammed Shahnawaz, MD; and Grace Gombolay, MD