Giuseppe Scibilia

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.

The Consistency and Quality of ChatGPT Responses Compared to Clinical Guidelines for Ovarian Cancer: A Delphi Approach

Introduction: In recent years, generative Artificial Intelligence models, such as ChatGPT, have increasingly been utilized in healthcare. Despite acknowledging the high potential of AI models in terms of quick access to sources and formulating responses to a clinical question, the results obtained using these models still require validation through comparison with established clinical guidelines. This study compares the responses of the AI model to eight clinical questions with the Italian Association of Medical Oncology (AIOM) guidelines for ovarian cancer. Materials and Methods: The authors used the Delphi method to evaluate responses from ChatGPT and the AIOM guidelines. An expert panel of healthcare professionals assessed responses based on clarity, consistency, comprehensiveness, usability, and quality using a five-point Likert scale. The GRADE methodology assessed the evidence quality and the recommendations’ strength. Results: A survey involving 14 physicians revealed that the AIOM guidelines consistently scored higher averages compared to the AI models, with a statistically significant difference. Post hoc tests showed that AIOM guidelines significantly differed from all AI models, with no significant difference among the AI models. Conclusions: While AI models can provide rapid responses, they must match established clinical guidelines regarding clarity, consistency, comprehensiveness, usability, and quality. These findings underscore the importance of relying on expert-developed guidelines in clinical decision-making and highlight potential areas for AI model improvement.