Israeli radiology startup Aidoc has received FDA clearance for its AI-based product meant to help identify potential cases of pulmonary embolism in chest CT scans.
Pulmonary embolism (PE) – which occurs when a blood clot gets lodged in the lung – is considered a silent killer that causes up to 200,000 deaths a year in the United States. The condition often strikes with little to no warning and diagnosis of a case can be extremely time-sensitive.
Aidoc’s technology doesn’t require dedicated hardware and runs continuously on hospital systems, automatically ingesting radiological images. The 70-person company focuses on workflow optimization in radiology to help triage high risk patients for additional and faster review.
Aidoc CEO Elad Walach pointed to the “ticking time bomb” nature of PE and the low likelihood of predicting an issue in advance as creating a strong use case for AI to detect and elevate real-time imaging findings.
“It can be done across all patient settings whether that’s in the emergency department or within the inpatient setting with complaining of shortness of breath,” Walach said, “In essence that’s the concept of alway- on AI.”
Walach explained that the high degree of variability in PE imaging data made developing an algorithm for detection of the condition particularly challenging. The technology was trained on more than 27,000 radiologist-annotated images from around the world across different scanners and care settings.
The FDA decision, which builds on a prior approval of the company’s algorithm for the detection of intracranial hemorrhages through CT scans, is part of a larger vision sketched out by Walach of plugging new algorithms into the Aidoc system to create a new standard of care.
“We understood that what the market really needs is not just a single one off solution,” Walach said. “The big deal about this specific approval is not the fact that it’s pulmonary embolism, but it’s a stepping stone to creating a full-body comprehensive suite applicable across different use cases.”
The news from Aidoc comes just a few weeks after fellow Israeli company Zebra Medical Vision received its own FDA clearance for a AI pneumothorax alert product, a signal of the acceleration happening in the space.
Walach added that Aidoc’s previous work with the FDA has helped to create a more reliable and efficient regulatory pathway leading to the new approval, which took 12 months less than their first clearance.
Moving forward, Walach said the company has eight other products in clinical trials with the next expected release being an AI tool for the detection of cervical spine fractures. That product has already received approval from European regulators.
The company pitches its AI-based technology as a way to help prioritize time-sensitive or life-threatening cases, allowing for faster diagnosis and better outcomes for pulmonary embolism patients.
Research on Aidoc’s machine learning product presented earlier this year at the European Society of Radiology’s ECR 2019 Congress found a 77 percent predictive value for the detection of pulmonary embolism in chest CTs.
Last month, the company announced a $27 million Series B financing round led by Square Peg Capital to invest in further development of the company’s technology and sales operation. The company has raised more than $40 million since its founding in 2016.
Recently, the company said it had reached a milestone by analyzing its 1 millionth CT patient scan and has a stated intention to reach 500 hospital partners in the next two years and build out its comprehensive full body coverage suite.
One factor driving Aidoc’s growth, according to Walach, is the speed in adoption among radiologists who he said are “very interested in taking control of the AI wave.” The company is working with the American College of Radiologists on testing new models for AI validation across different care settings.
One of the company’s customers is Los Angeles-based Cedars Sinai Medical Center which has incorporated both of the company’s FDA cleared solutions into its workflow.
“I was impressed by the fact that the coverage continuously grows, allowing us to add this product in the workflow of more radiologists, becoming part of our daily work. I was also pleased by the ability of the software to prioritize PE studies accurately,” Barry Pressman, chair of Department of Imaging at Cedars-Sinai, said in a statement.
AiDoc also lists the University of Rochester Medical Center, Antwerp University Hospital and AZ Maria Middelares General Hospital in Belgium as a few of its roughly 100 commercial clients.
Picture: Egor Kulinich, Getty Images