Israel-based start-up Aidoc has secured approval from the Food and Drug Administration (FDA) for its artificial intelligence (AI) triage solution that detects incidental pulmonary embolism in CT scans.

The company said that its system can flag incidental and critical findings that physicians did not originally suspect.

Detecting incidental findings is considered a very complex technical problem as there are fewer unsuspected cases.

According to Aidoc, the recently approved solution will offer an ‘always-on safety net’ for unexpected cases.

It is the company’s sixth clearance for an AI solution from FDA.

The other five existing FDA approved solutions are for the triage and notification of intracranial haemorrhage, c-spine fractures, large vessel occlusion, free intra-abdominal gas, and pulmonary embolism.

Aidoc CTO Michael Braginsky said: “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.”

The latest approval comes close on the heels of Aidoc, raising an additional $20m as part of its Series B extension round.

In April last year, the company raised $27m in a Series B funding round led by Square Peg Capital to support its technology and marketing team.