Platinum sensitivity and overall survival stratification in epithelial tubo-ovarian carcinoma: a comparative evaluation of large language models and gynaecological oncologists

Abstract Background Platinum sensitivity is a key predictive and prognostic factor in epithelial tubo-ovarian carcinoma, however early prognostic estimation at multidisciplinary tumour boards remains challenging. Large language models can process unstructured clinical narratives, but their prognostic utility in gynaecological oncology remains unclear. We compared the performance of contemporary large language models with that of gynaecological oncologists in predicting platinum sensitivity and overall survival from baseline tumour board data. Methods In this retrospective cohort study, 69 patients with epithelial tubo-ovarian carcinoma were included. Standardized vignettes were independently assessed by five models using identical prompts and by three gynaecological oncologists from different institutions. Both models and experts classified platinum sensitivity (recurrence ≤6 months vs >6 months after first-line platinum-based therapy), overall survival ( < 2, 2–5, >5 years), and confidence (low, moderate, high). Exploratory analyses assessed performance by confidence level, neoadjuvant chemotherapy, case difficulty, and repeated assessment of LLM predictions. Results 86% of patients were platinum-sensitive. Platinum sensitivity accuracy ranged from 50.7% to 85.5% among large language models and from 49.3 % to 76.8% among experts, with no significant difference between groups ( P = 0.304). Large language models showed high sensitivity (52.5–100%) but low specificity (0–40%). Survival prediction accuracy was moderate (40.6–52.2% for large language models; 44.8–49.3% for experts), with no significant difference between groups ( P = 0.671). Accuracy increased with higher confidence but declined in neoadjuvant-treated patients and complex cases. In repeated assessments, mean model accuracy decreased for platinum sensitivity (71.5% to 62.6%) and overall survival (45.2% to 40.0%). Conclusion Large language models achieved similar overall accuracy to gynaecological oncologists when predicting platinum sensitivity and overall survival. However, limited specificity for platinum resistance, lower performance in complex cases, and temporal variability highlight important limitations. Large language models may serve as adjunctive decision-support tools but require prospective validation before clinical implementation.