Israeli Medical Startup Aidoc Gets 6th FDA Approval

Science and Health

Aidoc received the clearance for the commercial use of its triaging and notification algorithms for flagging and communicating incidental pulmonary embolism.

Aidoc, an Israeli startup which develops diagnostic tools for radiologists powered by artificial intelligence, has received regulatory clearance from the US Food and Drug Administration for the commercial use of its triaging and notification algorithms for flagging and communicating incidental pulmonary embolism.

This marks the sixth time that the company has acquired such approval from the FDA. Without such FDA sanction a medical company may as well shut down.

Founded in 2016 by 3 graduates of the Israeli military’s elite science unit, Talpiot, CEO Elad Walach, CTO Michael Braginsky, and VP of R&D Guy Reiner Aidoc is based in Tel Aviv. The company has so far raised $47 million in investment.

“Triaging and notification algorithms,” is a real mouthful. So what does that mean exactly?

Well for all of us lay people it is basically a way for doctors to determine the severity of a heart problem.

Radiologists, the doctors who handle all of the x rays, must decide who is in most need of urgent care. Failing to spot the problem early is a major factor in avoidable heart attack deaths.

This new tech allows for early detection of such problems which is a crucial factor in the treatment of any disease.

[embedded content]

“The most common use case we experienced is for critical unsuspected findings in oncology surveillance patients” said Dr. Cindy Kallman, Chief, Section of CT at Cedars-Sinai Medical Center. “The ability to call the referring physician while the patient is still in the house is huge. We are essentially offering a point-of-care diagnosis of PE for our outpatients. Our referring physicians have been completely wowed by this.”

“There’s a reason why most AI triage solutions don’t focus on incidental findings,” said Michael Braginsky, Aidoc’s CTO. “Because the prevalence of incidental findings is relatively low, the specificity of the AI must be especially high, otherwise the false positive rate will be excessive and user adoption will be negatively impacted. In addition, an incidental PE algorithm detects PE in non-dedicated exams, where contrast is by definition suboptimal, and there’s an extremely high variability of protocols which challenges the AI even further. It was a scientific breakthrough that our team achieved that made this possible.”


Read more about: , , , , , , , ,