Yunqiang Zhang Yue Shi Xuesong Xiang Jingxin Ding Keqin Hua ^*

• Obstetrics and Gynecology Hospital, Fudan University, Shanghai, China

To study and predict the risk of ovarian metastasis (OM) in patients with cervical adenocarcinoma (ADC). Methods：Patients with ADC received surgical treatment from January 2015 to December 2022 in Obstetrics and Gynecology Hospital of Fudan University were included. Patients were further divided into OP (ovaries were preserved in surgery) and BSO (bilateral salpingo-oophorectomy) group. In patients accepted BSO, 60% were grouped into training cohort and predictive prognostic models were constructed with 10-fold cross-validation through random forest, LASSO, stepwise, and optimum subset analysis. The model owned highest AUC was screened out in testing cohort. The nomogram and its calibration curve gave out possibility of OM in future patients. The prognoses between different population were compared using Kaplan-Meier analysis. Results：934 patients were enrolled in our cohort, 266 had their ovaries preserved and 668 had BSO according to the previous criteria reported. The clinical safety with these criteria was secured while the 5-year overall survival had no significant difference in between BSO and OP group (p=0.069), which suggested the current criteria could be extended and more precise. Four predictive models for ovarian metastasis by machine learning were constructed in our study and the random forest model obtained the highest AUC in both training and testing sets (0.971 for training and 0.962 for testing set) was taken as the best model. The optimal cut-off point of the ROC curve (specificity 99.5% and 90% sensitivity) was utilized to stratify the patients into high- and low-risk of OM. On the basis of this random forest model, nomogram was used to calculate the OM risk and the results were validated with calibration. The predictive model was further applied to the whole cohort (934 patients) and we identified the OM low-risk population (n=822) and the patients with high risk whom should be recommended for BSO (n=112). No significant difference was found in 5-year survival between the low-risk group with our model and the patients already had ovaries preserved according to previous criteria (n=266). Conclusion：The predictive model constructed in our study could identify low-risk population of OM in patients with ADC, which remarkably extended the number with previous criteria.