Abstract P4-09-02: Validation of iPrevent using the prospective family study cohort (ProF-SC)

Abstract

Background: iPrevent (https://www.petermac.org/iprevent) provides women with highly-tailored risk management information after first estimating their breast cancer (BC) risk using the established risk prediction models, IBIS and BOADICEA. iPrevent has an internal switching algorithm that governs which model is used for each woman, depending on her risk factor data (i.e. LCIS/atypical hyperplasia status, BRCA status, and cancer family history). This study assessed the calibration and discriminatory accuracy of the 10-year BC risk estimates provided by iPrevent. Methods: Subjects were 16,574 women in the ProF-SC, aged 18-70 years and without BC or bilateral mastectomy at recruitment. After 10 years follow-up, 655 women (4%) were diagnosed with invasive BC. A “batch mode” for iPrevent is not available, so the iPrevent-assigned cumulative 10-year invasive BC risks were calculated by entering self-reported risk factors at cohort entry into either the IBIS (10,169 women) or BOADICEA (6,405 women) software packages (according to the iPrevent switching algorithm). To assess calibration, the mean iPrevent-assigned risk was compared with the mean 10-year observed invasive BC incidence, using a chi-squared goodness-of-fit statistic for the whole cohort, and by quartiles of risk. To evaluate discriminatory accuracy, the overall area under the receiver operating characteristic curve (AUC) for the development of invasive BC within 10 years was computed. Data were censored at date of invasive or in situ BC diagnosis, bilateral mastectomy, death, loss to follow-up, or at 10 years of follow-up. Results: For the whole cohort, iPrevent assigned risk was well-calibrated – 690 expected BCs (E) 655 observed (O) (E/O=1.05, 95% CI: 0.98-1.14), although for women in the highest risk quartile, i.e. >6% 10-year risk, E/O=1.19, 95% CI: 1.07-1.32. The AUC was 0.70, 95% CI: 0.68-0.72. Conclusions: iPrevent is well calibrated overall and has good discriminatory accuracy for predicting 10-year BC risk, thus justifying its clinical use. Citation Format: Phillips K-A, Liao Y, Collins IM, Buchsbaum R, Weideman P, Bickerstaffe A, MacInnis RJ, kConFab Investigators, Cuzick J, Antoniou A, Andrulis IL, John EM, Daly MB, Buys SS, Hopper JL, Terry MB. Validation of iPrevent using the prospective family study cohort (ProF-SC) [abstract]. In: Proceedings of the 2018 San Antonio Breast Cancer Symposium; 2018 Dec 4-8; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2019;79(4 Suppl):Abstract nr P4-09-02.