HealthMammo
K200905Zebra Medical Vision Ltd. · cleared 2020-07-16 · product code QFM · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.3)
“The Zebra HealthMammo is a passive notification for prioritization-only, parallel-workflow software tool used by MQSA-qualified interpreting physicians to prioritize patients with suspicious findings in the medical care environment.”
Algorithmartificial intelligence algorithm
source quote (p.3)
“HealthMammo utilizes an artificial intelligence algorithm to analyze 2D FFDM screening mammograms and flags those that are suggestive of the presence of at least one suspicious finding at the exam-level.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this
Validation studies (1)
Retrospective clinical
n=835 cases
endpoints: detection accuracy; triage accuracy
Reported performance (7 observations)
sensitivity0.8989CI [86.69%;92.38%]
source quote (p.9)
“The first operating point, “standard mode,” reported a sensitivity of 89.89% (95% CI: [86.69%;92.38%])”
specificity0.9075CI [87.51%;93.21%]
source quote (p.9)
“and a specificity of 90.75% (95% CI: [87.51%;93.21%]).”
aurocas written: “auc”0.9661CI [0.9552, 0.9769]
source quote (p.9)
“Overall, the HealthMammo was able to demonstrate an area under the ROC curve (AUC) of 0.9661 (95% CI: [0.9552, 0.9769]),”
sensitivityas written: “Sensitivity (high sensitivity mode)”0.9402CI [91.39%;95.89%]
source quote (p.9)
“The second operating point, “high sensitivity” reported a sensitivity of 94.02% (95% CI: [91.39%;95.89%])”
specificityas written: “Specificity (high sensitivity mode)”0.835CI [79.55%;86.82%]
source quote (p.9)
“and a specificity of 83.50% (95% CI: [79.55%;86.82%]).”
sensitivityas written: “Sensitivity (high specificity mode)”0.8414CI [80.41%;87.27%]
source quote (p.9)
“The “high specificity" operating point, reported a sensitivity of 84.14% (95% CI: [80.41%;87.27%])”
specificityas written: “Specificity (high specificity mode)”0.94CI [91.23%;95.94%]
source quote (p.9)
“and a specificity of 94.00% (95% CI: [91.23%;95.94%]).”
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).