CINA-VCF

K240612

Avicenna.AI · cleared 2024-05-31 · product code QFM · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.3)

“CINA-VCF is a radiological computer aided triage and notification software indicated for use in patients aged 50 years and over undergoing non-enhanced or contrast-enhanced CT scans which include the chest and/or abdomen.”

Algorithmdeep learning models

source quote (p.5)

“The device uses deep learning models to detect VCF at the T1-L5 level.”

Adaptive (vs locked)No

source quote (p.10)

“CINA-VCF has similar technological characteristics as the predicate device, i.e., the deployment of an artificial intelligence algorithm with a database of images.”

PCCPNo

Cybersecurity addressedNo

Validation studies (1)

Retrospective clinical

n=474 cases

endpoints: evaluate the software's performance in identifying vertebral compression fractures (VCF); CINA-VCF time-to-notification, which was compared to the predicate device for true positive cases only

standards: NEMA PS 3.1 - 3.20

Reported performance (7 observations)

sensitivity0.952CI 90.7% – 97.9%

source quote (p.7)

“Sensitivity and Specificity were 95.2% [95% CI: 90.7% – 97.9%]”

specificity0.929CI 89.4% – 96.5%

source quote (p.7)

“and 92.9% [95% CI: 89.4% – 96.5%], respectively.”

aurocas written: “auc”0.974CI 0.962 - 0.986

source quote (p.7)

“The ROC AUC was 0.974 [95% CI: 0.962 - 0.986], which exceeded the 0.95 performance goal, thus, achieving the primary endpoint.”

accuracyas written: “Accuracy”0.937CI 91.1% - 95.7%

source quote (p.7)

“Similarly, the overall agreement (Accuracy) was 93.7% [95% CI: 91.1% - 95%], which represents very good predictions.”

time_to_resultas written: “Mean time-to-notification (all cases)”23.4CI 22.7 – 24.2

source quote (p.7)

“The mean [95% Cl] time-to-notification for all included cases (n = 474) was estimated to be 23.4 [95% CI: 22.7 – 24.2] seconds for CINA-VCF.”

time_to_resultas written: “Mean time-to-notification (true positive cases)”21.7CI 20.5 – 22.9

source quote (p.8)

“When taking into account only true positive cases (n = 158), the mean [95% CI] time-to-notification was 21.7 [95% CI: 20.5 – 22.9] seconds for CINA-VCF”

time_to_resultas written: “Mean time-to-notification (true positive cases, predicate device)”117.2CI 98.64 – 135.85

source quote (p.8)

“and 117.2 [95% CI: 98.64 – 135.85] seconds for BriefCase, the selected predicate device.”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).