Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism

Original source

Multi-site real-world performance of commercial AI for pulmonary and incidental pulmonary embolism

Across 30,678 CT pulmonary angiograms and 37,191 other CT scans, sensitivity was 86.8% for PE and 73.5% for incidental PE, with specificity above 99%; the vendor had no role.

Evidence

Evidence: Peer-reviewed (evidence step 5 of 6)

Published after review by independent experts.

Bottleneck: Real-world reliability of cleared imaging AI Still open

The story in three lines

Key finding

Real-world PE sensitivity was 86.8% (72.9% sub-segmental) and incidental PE 73.5%, below FDA-clearance benchmarks.

Significance

Clinical: an independent, large check shows cleared imaging AI can underperform in routine practice.

Takeaway

Hospitals should audit cleared AI locally and keep radiologist review, especially for small clots.

Study details (as stated by the source)

Study design

Multi-site retrospective real-world evaluation in a 17-facility academic health system

Sample size

30,678 CTPA and 37,191 CT examinations

External validation

Yes: independent of the vendor

Outcomes

Sensitivity and specificity for PE and incidental PE

Later coverage in the journal

No later coverage in the journal yet.

Corrections and updates

No corrections or updates recorded for this item.