Multimodal data-based graph convolutional networks for predicting outcomes in ovarian cancer receiving neoadjuvant chemotherapy - PubMed
4 days ago
- #neoadjuvant chemotherapy
- #ovarian cancer
- #graph convolutional network
- Developed a graph convolutional network (GCN) integrating clinical and radiomic data to predict ovarian cancer outcomes.
- GCN predicts long-term overall survival (OS) and stratifies short-term surgical outcomes (R0 resection).
- Outperformed CA-125 KELIM score and Cox-based models in performance metrics like C-index and AUC.
- Identified 16.30% of patients with low KELIM scores but favorable survival.
- Operates without high-performance computing resources.