First AI-Powered POC Ultrasound Diagnostic Solution Helps Prioritize Cases Based On Severity

This delay can lead to negative outcomes as many patients are left waiting. While portable point-of-care ultrasound (POCUS) devices exist to eliminate the need for patient transport, they require operation by experts, which doesn't address the underlying issue. Now, a new deep learning technology offers "urgency scores" and AI-generated diagnoses that can be understood by non-experts, allowing for quicker, crucial treatment.

AISAP’s (Tel Aviv, Israel) AI-powered Point Of Care Assisted Diagnosis (POCAD) solution delivers highly accurate, easy-to-understand diagnoses for any physician, not just those specialized in ultrasound. This technology provides a unique "urgency score" to help medical providers prioritize cases based on condition severity, incorporates a quality score for scan operators to guarantee accuracy, and utilizes deep learning AI to ensure accurate readings from even low-quality images typical of handheld devices.

AISAP's POCAD solution stands out among POCUS options by offering detailed diagnoses of specific cardiovascular system valves, a task usually requiring more complex systems. Unlike traditional ultrasounds that can take weeks to analyze and diagnose, AISAP's technology provides results in as little as five minutes. It's supported by algorithms trained on over 300,000 studies with more than 24 million video clips and validated by extensive expert reviews. In a recent study involving 660 emergency and internal medicine patients who had not previously received comprehensive ultrasounds, the AISAP solution identified at least one significant, previously unknown medical condition in 29% of cases.

"Obtaining an accurate ultrasound diagnosis in time can literally be the difference between life and death, so the fact that so many patients are forced to wait up to a month for one is nothing short of a global health crisis," said AISAP CEO Roni Attali. "This problem is particularly acute in rural areas or those with fewer resources, and therefore disproportionately impacts disadvantaged populations."