Abstract B014: Improving prediction of second events after DCIS using whole breast mammogram images

Purpose: We aim to improve prediction of subsequent events after DCIS. Current models show relatively poor performance predicting subsequent events and often are limited to ipsilateral events. National population-based SEER data including over160,000 cases of DCIS and followed an average of 90 months indicate that second events (including risk of invasive breast cancer – IBC) are equality likely in the ipsilateral and contralateral breast. Thus, additional information on risk may be obtained by more complete modeling of risk estimating recurrence. Mammographic images have been largely ignored despite evidence that even breast density improves prediction of breast cancer in the general population. Furthermore, we have shown whole breast mammogram images (WBI) included in Cox models significantly improves prediction of breast cancer risk over using mammographic breast density alone and breast cancer risk factors. Population: We retrieved digital mammograms for women diagnosed with DCIS at Washington University School of Medicine from 2008 onwards and followed for subsequent diagnosis of pathology confirmed breast lesions. Using more than 100 cases and controls matched on year of mammogram and age we fit Cox models to evaluate risk of ipsilateral invasive breast cancer. To compare and accommodate laterality of subsequent breast lesions, we fit competing risk models using baseline covariates that are available on the women-level as well as WBI that are side-specific. Results: Preliminary analysis shows WBI predicts subsequent invasive breast cancer. Further, we will demonstrate appropriate models adjusting for competing risk gives unbiased estimates of invasive breast cancer. Conclusion: WBI and competing risk analysis improves our understanding of associations for side of occurrence of subsequent breast lesions after an initial diagnosis of DCIS.

Citation Format: Shu (Joy) Jiang, Graham A. Colditz. Improving prediction of second events after DCIS using whole breast mammogram images [abstract]. In: Proceedings of the AACR Special Conference on Rethinking DCIS: An Opportunity for Prevention?; 2022 Sep 8-11; Philadelphia, PA. Philadelphia (PA): AACR; Can Prev Res 2022;15(12 Suppl_1): Abstract nr B014.