The optimal SVM model from multi-model comparison outperforms conventional criteria in preoperative prediction of ovarian cancer residual disease.
Authors
Affiliations (10)
Affiliations (10)
- Department of Gynecological Oncology, Sun Yat-sen Memorial Hospital of Sun Yat-Sen University, 107 Yan Jiang West Road, Guangzhou, 510289, China.
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-sen Memorial Hospital, Sun Yat-sen University,, Guangzhou, Guangdong, China.
- Department of Gynecologic Oncology, Zhejiang cancer hospital, Hangzhou, 310022, China.
- Obstetrics and Gynecology Hospital, Fudan University, Shanghai, China.
- Department of Nuclear Medicine, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.
- Department of Gynecological Oncology, Sun Yat-sen Memorial Hospital of Sun Yat-Sen University, 107 Yan Jiang West Road, Guangzhou, 510289, China. [email protected].
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-sen Memorial Hospital, Sun Yat-sen University,, Guangzhou, Guangdong, China. [email protected].
- Department of Gynecologic Oncology, Zhejiang cancer hospital, Hangzhou, 310022, China. [email protected].
- Department of Gynecological Oncology, Sun Yat-sen Memorial Hospital of Sun Yat-Sen University, 107 Yan Jiang West Road, Guangzhou, 510289, China. [email protected].
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-sen Memorial Hospital, Sun Yat-sen University,, Guangzhou, Guangdong, China. [email protected].
Abstract
To develop an interpretable artificial intelligence (AI)-based machine learning model integrating <sup>18</sup>F-fluorodeoxyglucose positron emission tomography/computed tomography (<sup>18</sup>F-FDG PET/CT) radiomics, metabolic parameters, and clinical biomarkers for predicting residual disease after primary debulking surgery of ovarian cancer. This multicenter retrospective study included 203 epithelial ovarian cancer patients (2017-2024), including 153 in the training cohort and 50 in the validation cohort. Radiomic features and metabolic parameters were extracted from preoperative PET/CT, and clinical variables were from medical records. After Synthetic Minority Over-sampling Technique (SMOTE) balancing and minimum Redundancy Maximum Relevance (mRMR)-based feature selection, seven models were trained using nested 5 × 10 cross-validation. Performance was assessed by Area Under the Curve (AUC), Brier score, and decision curve analysis (DCA), with comparison to the conventional criteria such as the Suidan criteria or Fagotti criteria. Survival outcomes were analyzed using Kaplan-Meier and Cox regression. The SVM model (constructed using the support vector machine method) achieved superior discrimination (AUC 0.896 [95% CI 0.842-0.937] for training; 0.872 [0.792-0.932] for validation), significantly outperforming the Suidan criteria (AUC 0.696, P < 0.001; DeLong's test). Key predictors included tumor spatial heterogeneity (Elongation, Least Axis Length) and metabolic activity (SUVmax), alongside CA-125 and albumin. The model demonstrated excellent calibration (Brier score 0.119) and clinical net benefit across thresholds (4-85%). Moreover, high-risk patients had increased mortality risk (P < 0.001). The PET/CT-based model improves preoperative prediction of residual disease in ovarian cancer, potentially reducing nontherapeutic surgeries. Automated lesion segmentation and multicenter validation are needed for clinical translation. NCT06533709 (ClinicalTrials.gov, Registration Date: 2024-08-01).