Objective: Ovarian cancer (OC) is one of the most common cancers in women worldwide. The purpose of this study is to explore the risk factors for lymph node metastasis in patients with ovarian cancer, so as to guide clinical surgery and treatment. Methods: Data of ovarian cancer patients from April 2014 to May 2022 were included. A predictive model for lymph node metastasis of ovarian cancer was established by Logistic regression analysis, and a nomogram was drawn. ROC curve, calibration plot and decision curve analysis were used to evaluate the effectiveness of the model. Results: Of 333 patients in the training set, 92 (27.6%) developed lymph node metastases. Maximum tumor size, multifocal tumor, and Ki67 level were independent risk factors for lymph node metastasis. The AUC of the ROC curve in the training set was 0.819(95%CI:0.770-0.868), and the AUC of the ROC curve in the validation set was 0.794(95%CI:0.717-0.870). The calibration plot and decision curve analysis indicate that the model has good calibration degree and clinical application value. The combined ultrasound and clinical model had higher predictive efficacy than the single model. Conclusion: Based on ultrasound results and patient clinical data, we constructed a prediction model for lymph node metastasis in ovarian cancer patients, which can more accurately assess the risk of lymph node metastasis in patients in the era of precision medicine, and formulate the best treatment plan for patients.