CogNet AI-MT+
K252482Medcognetics, Inc. · cleared 2025-12-11 · product code QFM · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.5)
“The MedCognetics CogNet AI-MT+ is a non-invasive computer-assisted triage and notification software as a medical device (SaMD) that analyzes DBT screening mammograms using a machine learning algorithm and notifies a PACS/workstation of the presence of findings suspicious of cancer in a study.”
AlgorithmDeep Learning techniques to extract features
source quote (p.6)
“Mammogram Learning Module – This module accepts the normalized image data from the pre-processing module and uses Deep Learning techniques to extract features to determine if any lesions suspicious for cancer exist in the mammogram study”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.7)
“MedCognetics is attentive to cybersecurity issues in medical devices. CogNet AI- MT+ is HIPAA compliant and assures that Personal Health Information is protected by promoting anonymization of data prior to analysis.”
Validation studies (1)
Standalone
n=806 patients · 1 site(s)
endpoints: Area Under Receiver Operating Characteristics (AUROC); sensitivity; specificity
standards: IEC 62304, 21 CFR Part 820, DICOM PS3.1
Reported performance (3 observations)
sensitivity0.8809CI 95% CI: 0.8511 - 0.9032
source quote (p.12)
“Sensitivity = 0.8809 (95% CI: 0.8511 - 0.9032)”
specificity0.9156CI 95% CI: 0.8933 - 0.9380
source quote (p.12)
“Specificity = 0.9156 (95% CI: 0.8933 - 0.9380)”
aurocas written: “auc”0.9548CI 95% CI: 0.9364 - 0.9699
source quote (p.12)
“Overall, CogNet AI-MT+ achieved an AUROC = 0.9548 (95% CI: 0.9364 - 0.9699)”
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).