Abstract 4932: Modeling uncertainty in personalised breast cancer risk prediction

Abstract Breast cancer risk prediction models use a range of predictors to estimate an individual’s chance of developing breast cancer in a given timeframe. These can facilitate risk stratification, to identify individuals who would benefit most from screening or preventive options. The BOADICEA breast cancer risk model, implemented in the CanRisk tool (www.canrisk.org), uses genetic, lifestyle, hormonal, family history and anthropometric data to estimate an individual’s risk. When implementing risk prediction models, risk predictor data are often incomplete. Point-estimates calculated when some risk factor data are missing can hide considerable uncertainty. We developed a methodological approach for quantifying uncertainty and the probability of risk-reclassification in the presence of missing data. We employed Monte-Carlo simulation methods to estimate the distribution of breast cancer risk for individuals with missing data. Multiple imputation by chained equations (MICE) with UK Biobank as a reference dataset was used to sample missing covariates. We developed a framework for estimating uncertainty, that can be applied to any given individual with missing risk factor data. We used exemplar cases to assess the probability that collecting missing data would result in a change in risk categorisation, on the basis of the 10-year predicted risk from age 40, using the UK National Institute for Health and Care Excellence (NICE) guidelines. For example, a woman known to have a pathogenic variant in CHEK2, but with all other information unmeasured, will be categorised as at “moderate risk” by the BOADICEA model. Measuring lifestyle and hormonal risk factors would result in reclassification to either the “population-” or “high-risk” group in around 24% of cases (respectively 23% and 1%). Measuring only a polygenic score (PGS) would reclassify the individual about 43% of the time into either the “population-” or “high risk” group (respectively 34% and 9%); measuring a PGS and lifestyle and hormonal risk factors would reclassify the individual to the “population-” or “high-risk” group in around 51% of cases (respectively 43% and 8%). The results demonstrate that there may be a considerable likelihood of reclassification into a different risk category after collecting missing data. The methodology presented here can identify situations where it would be most beneficial to collect additional patient information, and enable better informed clinical decision making. Citation Format: Bethan L. White, Lorenzo Ficorella, Xin Yang, Douglas F. Easton, Antonis C. Antoniou. Modeling uncertainty in personalised breast cancer risk prediction [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 4932.