An explainable machine learning ensemble model to predict the risk of ovarian cancer in BRCA-mutated patients undergoing risk-reducing salpingo-oophorectomy

Introduction It has been estimated that 19,880 new cases of ovarian cancer had diagnosed in 2022. Most epithelial are sporadic, while 15%–25% cases, there is evidence a familial or inherited component. Approximately 20%–25% high-grade serous carcinoma caused by germline mutations the BRCA1 and BRCA2 genes. However, owing to lack effective early detection methods, women with BRCA recommended undergo bilateral risk-reducing salpingo-oophorectomy (RRSO) after childbearing. Determining right timing for this procedure difficult decision. crucial find clinical signature identify high-risk BRCA-mutated patients determine appropriate performing RRSO. Methods In work, data referred cohort 184 patients, whom 7.6% were affected adnexal tumors including invasive carcinomas intraepithelial lesions RSSO analyzed. Thus, we proposed an explainable machine learning (ML) ensemble approach using commonly collected practice at high risk consequentially establish correct Results The model was able handle imbalanced achieving accuracy value 83.2%, specificity 85.3%, sensitivity 57.1%, G-mean 69.8%, AUC 71.1%. Discussion agreement promising results achieved, application suitable ML techniques could play key role definition patient-centric consequently personalize management these patients. As far as know, first work addressing task from perspective.