VinDr-Mammo

Evidence summary

Study type: Stand-Alone Performance. Cases: 1000. Reported sensitivity: 88.90%. Reported specificity: 90.60%. Reported accuracy: 0.958

Public source Exact FDA submission Checked 2026-09-01

Structured study metadata from the exact-submission ACR model card; this is not an independent evidence synthesis.

• Source

No contextualized exact-version metric has completed evidence review. Regulatory-document values, when available, are shown above with their limitations.

Postmarket safety review

Not established in reviewed sources

Reviewed sources checked Exact FDA submission Checked 2026-09-04

No native submission-identifier match was found in the checked openFDA radiology recall snapshot. Product-name, manufacturer, and adverse-event searches remain necessary; this does not establish that no recall or safety report exists.

• Verify care setting and population: Confirm the intended care setting, patient population, and service line.
• Verify security and privacy controls: FDA authorization does not establish the current commercial security posture. Request data-flow diagrams, hosting and retention details, access controls, audit logging, attestations, and incident-response documentation.
• Verify training: Training, onboarding, competency, and support commitments are commercial implementation details that require current vendor documentation.
• Verify pricing and total cost: FDA submission materials do not establish current commercial pricing. Request the pricing unit, term, minimum commitment, implementation fees, and included support from the vendor.
• Verify reimbursement and coding relevance: Determine whether any product-specific CPT/HCPCS pathway exists and separate it from billing for the underlying imaging service.
• Verify local validation and lifecycle monitoring: Local acceptance testing, production monitoring, drift review, update control, and incident escalation require a current vendor and site-specific governance plan.
• Verify recalls and postmarket safety signals: No native submission-identifier match was found in the checked openFDA radiology recall snapshot. Product-name, manufacturer, and adverse-event searches remain necessary; this does not establish that no recall or safety report exists.

Exact-submission ACR model-card fields were normalized under the current provenance rules; vendor and independent-study confirmation remain distinct. Automated exact-name discovery found 18 PubMed and 0 ClinicalTrials.gov candidate records. Candidates require human product and version matching; zero candidates is not evidence that no studies exist. Native FDA recall identifiers produced 0 postmarket candidate records; 0 have been reviewed (0 published, 0 rejected) and 0 remain unreviewed.

Candidate leads remain unpublished until a human confirms the exact product and tested version.

Source classes: fda ai list, fda decision summary, acr ai central product, pubmed, clinical trials, openfda device recall

• K233108 FDA decision source U.S. Food and Drug Administration · 2026-08-31
• Artificial Intelligence-Enabled Medical Devices U.S. Food and Drug Administration · 2026-08-31
• VinDr-Mammo model card (K233108) American College of Radiology · 2026-09-01
• PubMed biomedical literature index U.S. National Library of Medicine · 2026-09-01
• ClinicalTrials.gov study registry U.S. National Library of Medicine · 2026-09-01
• openFDA Device Recall API U.S. Food and Drug Administration · 2026-09-02