MammaPrint separated node-negative breast cancers by risk of spread

In FDA's review of MammaPrint, 95% of low risk and 78% of high risk patients were free of distant metastasis at five years. The validation covered 302 European patients.

  • Not rated an organization

    The validation used archived tumors from patients diagnosed before 1999, and the test guided no treatment.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Intended benefit.
Evidence

foundstudiedreportedclaimed

An independent regulatory document supports the benefit.

Compared with

Clinical risk assessment with Adjuvant on-line. Measured.

Without the system
Unadjusted hazard ratio of 2.32 (95% CI: 1.35 to 4.00)
With it
Hazard ratio of 2.13 (95% CI: 1.19 to 3.82) after adjustment for clinical risk
The system’s part
Not isolated. The validation compared outcomes across the signature's risk groups and adjusted for clinical risk. It did not compare care with and without the test. The classifier correlates each profile with a template and was derived on a training set, but FDA does not describe it as machine learning.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
MammaPrint
Made by
Agendia BV
Used by
TRANSBIG consortium (independent validation on tumors from five European centers)
Where
Villejuif and Saint-Cloud, France; Stockholm, Sweden; London and Oxford, United Kingdom
Stage
Tested in a laboratory
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Analyzing Data or Information
Collections
Scrutiny and findings, Cross-border records
Last revised
31 October 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    U.S. Food and Drug Administration, Center for Devices and Radiological Health. 510(k) substantial equivalence determination decision summary for MammaPrint (k062694), classified through the de novo process (DEN070009). Granted 2007-02-06.

    Adjustment for being at high risk of metastases via the Adjuvant on-line still resulted in a hazard ratio of 2.13 (95% CI: 1.19 to 3.82). The modest drop in the hazard probably reflects that the genomic signature may be related to the clinical factors but is clearly providing additional information.

Details

AI system

Workflow

RNA from fresh-frozen tumor sections was amplified, labeled and hybridized to a custom Agilent microarray. The test ran as a service in a single Agendia laboratory in Amsterdam.

Follow-up

Conditions for replication

The patient is under 61 with stage I or II, lymph node negative breast cancer and a tumor of 5.0 cm or less. Physicians use the result as a prognostic marker with other clinicopathological factors.

Entry details

Sector

Healthcare.

Purpose

Agendia built MammaPrint to assess the risk of distant metastasis in patients under 61 with stage I or II, node-negative breast cancer, as a prognostic marker.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). MammaPrint separated node-negative breast cancers by risk of spread (AIBD-0813). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0813.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions