Pilar Ordas

SUROVA study: global real-world treatment strategies and mortality risk prediction in advanced ovarian cancer

This study aimed to compare 5-year overall survival between primary debulking surgery and neoadjuvant chemotherapy followed by interval surgery in patients with stage IIIB to IVB epithelial ovarian cancer, using global real-world data. Secondary objectives included evaluation of progression-free survival and the influence of race, post-operative complications, and residual disease. SUROVA is a retrospective, international cohort study involving patients treated between 2018 and 2019 across 174 centers in 55 countries. Patients underwent primary surgery or received neoadjuvant chemotherapy followed by interval surgery, per institutional protocols. Propensity score matching was based on 7 baseline variables: age, race, Eastern Cooperative Oncology Group performance status at diagnosis, CA125 level at diagnosis, FIGO (International Federation of Gynecology and Obstetrics) stage IV disease, presence of ascites, and final tumor grade. Cox regression models with time-dependent effects and interaction terms were applied. A clinical risk calculator was developed and internally validated. A total of 3286 patients had a mean age of 60.0 years (SD 12); 2978 (90.6%) had high-grade serous carcinoma, and 795 (24.7%) presented with FIGO stage IV disease. A total of 1666 patients (50.7%) underwent primary cytoreductive surgery, and 1620 (49.3%) received neoadjuvant chemotherapy. The median follow-up duration was 43.8 months (interquartile range; 22.6-59.3). After propensity score matching (n=1524), overall survival was similar between groups (67.2 vs 65.0 months; HR 1.002, 95% CI 0.85 to 1.18, p=.98). Outcomes differed by ethnicity, residual disease, and post-operative complications. Post-operative complications (28%) significantly worsened survival (66 vs 46 months; HR 1.5, 95% CI 1.2 to 1.9, p<.001), especially among patients undergoing primary surgery (73 vs 46 months; HR 1.85, 95% CI 1.43 to 2.37, p<.001). The most favorable outcomes were observed among patients with primary surgery, complete resection, and no complications, with median overall survival not reached (HR 1.25, 95% CI 1.12 to 1.40, p<.001). Although overall survival was similar between groups, treatment effects differed by ethnicity, residual disease, and complications. Post-operative complications were associated with significantly worse survival, particularly among patients undergoing primary surgery, while the best outcomes were achieved in those who had primary surgery with complete resection and no complications.

Artificial intelligence for single-omics in ovarian cancer: a methodological review

Ovarian cancer is a leading cause of cancer-related mortality among women, with poor prognosis and limited survival in advanced stages. The integration of artificial intelligence with omics data offers new opportunities to enhance the diagnosis, prognosis, and treatment of this disease. This narrative review synthesizes evidence from 14 studies published between 2021 and 2024 that applied artificial intelligence to genomic, transcriptomic, metabolomic, micro-biomic, and epigenomic data sets in patients with epithelial ovarian cancer. These studies explored artificial intelligence models for disease detection, chemotherapy response prediction, and genetic risk stratification. Despite promising results (eg, high classification accuracy and area under the curve values in some models), significant limitations were observed, including small sample sizes, retrospective and single-center designs, and inconsistent use of validation data sets. The review highlights critical methodological considerations such as data preprocessing, normalization, and feature selection, which substantially influence model performance and reproducibility. Although classification models (eg, deep learning, random forest, and support vector machines) were most commonly used, regression approaches were less frequent and under-used, despite their value for modeling continuous outcomes such as survival time. Overall, artificial intelligence-based approaches demonstrate great potential for advancing personalized medicine in ovarian cancer. However, future research must prioritize larger, multi-center, prospective studies with robust validation strategies and improved model interpretability to enable clinical implementation.