Hamy, Anne-Sophie

Treatment-induced ovarian function loss is a significant concern for many young patients with breast cancer. Accurately predicting this risk is crucial for counselling young patients and informing their fertility-related decision-making. However, current risk prediction models for treatment-related ovarian function loss have limitations. To provide a broader representation of patient cohorts and improve feature selection, we combined retrospective data from six datasets within the FoRECAsT (Infertility after Cancer Predictor) databank, including 2679 pre-menopausal women diagnosed with breast cancer. This combined dataset presented notable missingness, prompting us to employ cross imputation using the k-nearest neighbours (KNN) machine learning (ML) algorithm. Employing Lasso regression, we developed an ML model to forecast the risk of treatment-related amenorrhea as a surrogate marker of ovarian function loss at 12 months after starting chemotherapy. Our model identified 20 variables significantly associated with risk of developing amenorrhea. Internal validation resulted in an area under the receiver operating characteristic curve (AUC) of 0.820 (95% CI: 0.817–0.823), while external validation with another dataset demonstrated an AUC of 0.743 (95% CI: 0.666–0.818). A cutoff of 0.20 was chosen to achieve higher sensitivity in validation, as false negatives—patients incorrectly classified as likely to regain menses—could miss timely opportunities for fertility preservation if desired. At this threshold, internal validation yielded sensitivity and precision rates of 91.3% and 61.7%, respectively, while external validation showed 92.9% and 60.0%. Leveraging ML methodologies, we not only devised a model for personalised risk prediction of amenorrhea, demonstrating substantial enhancements over existing models but also showcased a robust framework for maximally harnessing available data sources.

PURPOSE To investigate the clinical behavior of breast cancer in young BRCA carriers according to the specific BRCA gene ( BRCA1 v BRCA2 ) and the association of the timing of genetic testing (before v at diagnosis) with prognosis. METHODS This was an international, multicenter, hospital-based, retrospective cohort study that included 4,752 patients harboring germline pathogenic/likely pathogenic variants (PVs) in BRCA1 or BRCA2 , who were diagnosed with stage I-III invasive breast cancer at 40 years or younger between January 2000 and December 2020 in 78 centers worldwide (ClinicalTrials.gov identifier: NCT03673306 ). RESULTS Compared with BRCA2 carriers (n = 1,683), BRCA1 carriers (n = 3,069) had more frequently hormone receptor–negative (74.4% v 15.5%) and high-grade (77.5% v 49.1%) tumors. Similar outcomes were observed in BRCA1 and BRCA2 carriers but with a different pattern and risk of disease-free survival events over time. Compared with patients tested for BRCA at diagnosis (ie, between 2 months before and up to 6 months after diagnosis; n = 1,671), those tested before diagnosis (ie, any time up to 2 months before diagnosis; n = 411) had smaller tumors (T1: 61.3% v 32.4%), less nodal involvement (N0: 65.9% v 50.8%), less frequently received chemotherapy (84.4% v 92.9%), and axillary dissection (37.5% v 47.4%). Patients tested before diagnosis had better overall survival (OS; unadjusted hazard ratio [HR], 0.61 [95% CI, 0.40 to 0.92]); however, this result lost statistical significance after adjustment for potential confounders including tumor stage (adjusted HR, 0.74 [95% CI, 0.47 to 1.15]). CONCLUSION This global study provides evidence on the different clinical behavior of breast cancer in young BRCA1 and BRCA2 carriers. Identifying a BRCA PV in healthy individuals was associated with earlier-stage breast cancer diagnosis and lower treatment burden, as well as better unadjusted OS.