Aidoc, an Israeli provider of artificial intelligence products for radiologists, announced today that it has received FDA clearance for a tool that identifies potential cases of pulmonary embolism — a blockage in one of the lung’s pulmonary arteries — for expert review.
“We chose to focus on this product because these are patients who might not necessarily have clear symptoms of pulmonary embolism,” Elad Walach, CEO of Aidoc, told MobiHealthNews. “By focusing on the image itself, we’re able to tell the hospital and the radiologist, ‘Hey, look, there’s a patient at much higher risk because the AI detects something, it’s probably worth looking at right now.’”
WHY IT MATTERS
Much like its other FDA-cleared product for acute intracranial hemorrhage, the pulmonary embolism tool is designed as an integrated, end-to-end tool. It analyzes chest images immediately after the patient is scanned to quickly flag the specialist’s attention. While the service has the potential to streamline radiologists’ workflows and reduce missed cases, Walach said that its greatest impact will likely be the prompt identification of a time-sensitive condition.
“There are a lot of benefits, but the true focus of this product is the reduction of hours of turnaround time,” he said. “We ran one study in a US-based medical center that saw that the average turnaround time for pulmonary embolism time was 10 hours. So it’s a ticking time bomb, and it’s 10 hours until someone even opens it. You could have left the hospital, you could have gone home. … We make sure that if you have this the radiologist looks at it right away, and instead of going home with a ticking time bomb you get treated on the spot.”
Walach also highlighted the conversations between his company and the FDA, which he said has allowed Aidoc to more quickly clear a second product with similar use cases and underlying AI technology. With another eight tools in active clinical trials (and a fresh $27 million in the bank), he said that his company wants to make its mark by providing radiologists with a single workflow tool that can easily and efficiently triage their patients.
“One thing that’s important in this is that we understood that a hospital can’t do 12 different point solutions. What we need is a comprehensive set of tools that would cover them in the background, constantly, across different anatomical regions,” he said. “For us, it’s about creating a high-velocity technology that can create those algorithms really quickly in order to provide comprehensive coverage to our customers and partners, so they know they can rely on us for their acute findings triage.”
WHAT’S THE TREND
The pulmonary embolism tool is the latest in a slew of clearances employing algorithm-based services to help with disease detection. Just this week Zebra Medical Vision, another Israel-based AI company, announced its 510(k) for a pneumothorax screen that similarly scans chest images and flags radiologists. Looking a bit further back, Viz.ai and IDx also received their first clearances for AI-based clinical decision support tools within the last year.
For Walach, the wave of clearances is the natural result of an open-minded regulatory agency and a new appreciation within the market for automated clinical services with validated results.
“If you look two or three years back, you’ll see that a lot of the AI companies are focused on creating algorithms. If you look now it’s much more about solutions and focused on solutions and what chan be achieved and what that means for patients. What that means is that in the last year, radiologists have seen more and more evidence about the value of AI and the fact that it can change the standard of care,” Walach said.
“This is where the market is going to see what is real beyond the hype, and I think that’s going to be up to the market to device: which solutions do provide value over time. … Hopefully you’ll see that we are going to be able to provide to the market much more value, in a much more comprehensive package.”
