Using MammoRisk, a software tool used to estimate an individual’s 5-year risk of developing breast cancer, is feasible in community practices, according to a recent study. The assessment is based on a patient’s clinical data and breast density, with or without a polygenic risk score (PRS). Adding the latter criterion to the model led to four out of 10 women being assigned a different risk category. Of note, three out of 10 women were changed to a higher risk category.
A Multifaceted Assessment
In France, biennial mammographic screening is recommended for women aged 50 to 74 years. A personalized risk assessment approach based not only on age, but also on various risk factors, is a promising strategy that is currently being studied for several types of cancer. These personalized screening approaches seek to contribute to early diagnosis and treatment of breast cancer at an early and curable stage, as well as to decrease overall health costs for society.
Women aged 40 years or older, with no more than one first-degree relative with breast cancer diagnosed after the age of 40 years, were eligible for risk assessment using MammoRisk. Women previously identified as high risk were, therefore, not enrolled. MammoRisk is a machine-learning–based tool that evaluates a patient’s risk with or without considering PRS. A PRS reflects the individual’s genetic risk of developing breast cancer. To calculate this risk, DNA was extracted from saliva samples for genotyping of 76 single-nucleotide polymorphisms (SNPs). Patients underwent a complete breast cancer assessment, including a questionnaire, mammogram with evaluation of breast density, collection of saliva sample, and consultations with a radiologist and a breast cancer specialist.
PRS Influenced Risk
Out of the 290 women who underwent breast cancer assessment between January 2019 and May 2021, 68% were eligible for risk assessment using MammoRisk (median age, 52 years). The others were not eligible because they were younger than 40 years of age, had a history of atypical hyperplasia, were directed to oncogenetic consultation, had a non-White origin, or were considered for Tyrer–Cuzick risk assessment.
Following risk assessment using MammoRisk without PRS, 16% of patients were classified as moderate risk, 53% as intermediate risk, 31% as high risk, and 0% as very high risk. The median risk score (estimated risk at 5 years) was 1.5.
When PRS was added to MammoRisk, 25% were classified as moderate risk, 33% as intermediate risk, 42% as high risk, and 0% as very high risk. Again, the median risk score was 1.5.
A total of 40% of patients were assigned a different risk category when PRS was added to MammoRisk. Importantly, 28% of patients changed from intermediate risk to moderate or high risk.