VinDr-Mammo
K233108VinBigData Joint Stock Company · cleared 2024-05-23 · product code QFM · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.5)
“Operating as non-invasive computer-assisted software, known as SaMD, it employs a machine learning algorithm to identify potential suspicious findings within the images.”
Algorithmmachine learning algorithm
source quote (p.5)
“it employs a machine learning algorithm to identify potential suspicious findings within the images.”
Adaptive (vs locked)No
source quote (p.5)
“During the algorithm's training, independent datasets from various global sites were utilized, ensuring a robust and diverse training experience.”
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this
Validation studies (2)
Retrospective clinical
n=1,000 patients
Retrospective clinical
n=1,864 patients · 1 site(s)
endpoints: accuracy of stand-alone detection and triage
Reported performance (3 observations)
sensitivity0.9CI 0.877-0.921
source quote (p.15)
“Sensitivity 0.900 0.877 0.921”
specificity0.91CI 0.897-0.922
source quote (p.15)
“Specificity 0.910 0.897 0.922”
aurocas written: “auc”0.962CI 0.957-0.971
source quote (p.15)
“AUC 0.962 0.957 0.971”
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
0
recalls in product code, 24mo
0
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
0
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).