Evaluating the performance of the BOADICEA model in predicting 10-year breast cancer risks in UK Biobank.

Abstract

BACKGROUND: The BOADICEA model predicts breast cancer risk using cancer family history, epidemiological and genetic data. We evaluated its validity in a large prospective cohort. METHODS: We assessed model calibration, discrimination and risk classification ability in 217,885 women (6,838 incident breast cancers) aged 40-70 years old of self-reported White ethnicity with no previous cancer from the UK Biobank. Age-specific risk classification was assessed using relative risk (RR) thresholds equivalent to the absolute lifetime risk categories of < 17%, 17-30% and ≥30%, recommended by the National Institute for Health and Care Excellence guidelines. We predicted 10-year risks using BOADICEA v.6 considering cancer family history, questionnaire-based risk factors, a 313-SNP polygenic score and pathogenic variants. Mammographic density data were not available. RESULTS: The PRS was the most discriminative risk factor (AUC=0.65). Discrimination was highest when considering all risk factors (AUC=0.66). The model was well calibrated overall (E/O=0.99, 95%CI=0.97-1.02; calibration slope=0.99, 95%CI:0.99-1.00), and in deciles of predicted risks. Discrimination was similar in women younger and older than 50 years. There was some underprediction in women under age 50 (E/O=0.89, 95%CI=0.84-0.94; calibration slope=0.96, 95%CI:0.94-0.97), which was explained by the higher breast cancer incidence in UK Biobank than the UK population incidence in this age group. The model classified 87.2%, 11.4% and 1.4% of women in RR categories <1.6, 1.6-3.1 and ≥3.1, identifying 25.6% of incident breast cancer cases in category RR ≥ 1.6. CONCLUSION: BOADICEA, implemented in CanRisk (www.canrisk.org), provides valid 10-year breast cancer risk which can facilitate risk-stratified screening and personalized breast cancer risk management.