MyRadAgent
Home › Tools › Breast cancer risk stratification

Breast cancer risk stratification

Risk stratification is categorical before it is numerical: a pathogenic variant or chest radiation in adolescence puts a patient in the high tier whatever a model says. This tool sorts the categorical criteria into the ACR 2023 tiers and tells you when the lifetime percentage, from Tyrer-Cuzick, is the thing that decides.

High-risk criteria (ACR 2023 / NCCN)
Intermediate-risk criteria
Mammographic density (BI-RADS)
Family history
Lifetime risk from an external model (optional, %)

Run IBIS / Tyrer-Cuzick for the lifetime figure the 20% threshold applies to. NCI BCRAT (Gail) gives 5-year risk for chemoprevention and is not valid for this threshold.

Paste-ready recommendation
Get the percentage from the official calculators.

Risk tiers and supplemental screening (ACR 2023)

TierCriteriaSupplemental screening
High riskPathogenic variant or untested first-degree relative of a carrier; chest radiation at 10-30; calculated lifetime risk 20% or moreAnnual screening breast MRI beginning at age 25-30 (from age 25 for pathogenic-variant carriers and untested first-degree relatives; 8 years after chest radiation but not before age 25), with annual mammography from age 30 (from age 40 in TP53 carriers, where radiation sensitivity is a concern). Contrast-enhanced mammography if MRI is not possible.
Intermediate (higher-than-average) riskPersonal history of breast cancer; ADH, ALH or LCIS; heterogeneously or extremely dense breastsAnnual mammography, with supplemental MRI recommended by ACR 2023 for the criteria selected; contrast-enhanced mammography or ultrasound if MRI is not possible. Where the lifetime risk has not been formally calculated, run Tyrer-Cuzick: a result of 20% or more moves the patient to the high tier.
Average riskNone of the aboveAnnual screening mammography from age 40. No supplemental screening indicated on the risk factors entered. Reassess if family history changes; a formal risk assessment is recommended for all women by age 25.

Family history

Family history alone does not fix a tier. One first-degree relative diagnosed after 50 roughly doubles relative risk but usually leaves the lifetime figure under 20%; two or more first-degree relatives, or one diagnosed before 50, frequently push Tyrer-Cuzick over the threshold. The tool therefore flags a strong family history for formal modelling rather than guessing the percentage.

Which risk model? The Gail model (NCI BCRAT) must NOT be used to establish the 20% lifetime-risk threshold. Gail estimates 5-year risk from a limited family history — first-degree relatives only, no paternal lineage, no age at diagnosis — and systematically underestimates risk in exactly the family-history-driven patients this threshold is meant to capture. Gail has its own valid use: chemoprevention eligibility at a 5-year risk of 1.67% or more. It is the wrong instrument for MRI eligibility.

Which model, and where to run it

ModelGives youUse it for What it does and does not see
Gail / BCRAT5-year and lifetime invasive breast cancer riskChemoprevention eligibility (5-year risk 1.67% or more)First-degree relatives only. No paternal lineage, no age at diagnosis, no BRCA status, no density. Not valid for MRI screening eligibility.
Tyrer-Cuzick (IBIS) v810-year and lifetime riskMRI screening eligibility (lifetime 20% or more)Extended pedigree both sides, ages at diagnosis, BMI, HRT, breast density, BRCA results. The usual choice for the 20% threshold.
BOADICEA / CanRiskBreast and ovarian risk, plus carrier probabilityDetailed family history; genetic counselling referralModels pedigree and known pathogenic variants most thoroughly. Also estimates the chance of carrying a variant, which the others do not.

Why the percentage is computed there and not here

We do not reimplement these models here, and that is deliberate. Each is a coefficient-table model: race and ethnicity stratified regression coefficients plus SEER-derived baseline hazard and competing-mortality tables, several hundred published numbers in total. A transcription slip anywhere in that produces a percentage that looks authoritative and is wrong, and a wrong risk figure changes whether someone gets an MRI or starts tamoxifen. The official implementations are maintained and validated by the groups that built the models. Use those, then bring the number back to the eligibility criteria above.

For educational use by qualified clinicians. This tool sorts published criteria into tiers; it does not calculate risk, diagnose, or replace a formal risk assessment or genetic counselling.

Related

Source. Monticciolo DL, et al. Breast Cancer Screening for Women at Higher-Than-Average Risk: Updated Recommendations From the ACR. J Am Coll Radiol 2023;20(9):902-914. View on PubMed
This calculator, written into your report for you

MyRadAgent drafts the full report - and applies this guideline automatically, with the category and follow-up in the impression. Free trial runs in the browser: 100 reports over 14 days, no card, no IT ticket.

Try it on a report → or watch it live first — no signup →
This is a reference implementation of a published guideline, for use by qualified clinicians. It does not account for patient-specific factors and is not a substitute for clinical judgment or a formal radiology consultation. See our full disclaimer.