精确预先鉴别良性和恶性附属物肿块，特别是那些具有复杂超声形态学的肿块，对初级超声医师仍然是一个巨大的挑战。本研究的目的是开发和验证基于卵巢-附属物报告和数据系统（O-RADS）的名册图来预测具有复杂超声形态学的附属物肿块的恶性风险。共选择了从2019年1月至2020年12月的243名患者，他们的数据包括附属物肿块复杂超声形态学，作为训练队列，而从2021年1月至2021年12月的106名患者则作为验证队列。运用单变量和多变量分析，确定训练队列中恶性肿瘤的独立风险因素。随后，发展并验证预测名册图模型。分别通过校准曲线、受试者工作特征曲线（ROC）和决策曲线分析（DCA）评估名册图模型的校准、鉴别和临床净收益。最后，我们将此模型与O-RADS进行比较。 O-RADS类别、升高的CA125水平、声影和带有彩色多普勒流的乳头状突起是独立预测因子，并纳入名册图模型中。训练队列中名册图模型的ROC曲线下面积（AUC）为0.958（95% CI，0.932-0.984）。其特异性和敏感性分别为0.939和0.893。该名册图模型在验证队列中也表现出良好的识别能力（AUC = 0.940，95% CI，0.899-0.981），其敏感性为0.915，特异性为0.797。此外，名册图模型在训练和验证队列中均表现出良好的校准效果。DCA表明名册图在临床上是有用的。此外，名册图模型的AUC和净收益比O-RADS高。 基于O-RADS的名册图表现出了在预测具有复杂超声形态学的附属物肿块的恶性风险方面的良好预测能力，并能为初级超声医师提供帮助。© 2023年，作者。

The accurate preoperative differentiation of benign and malignant adnexal masses, especially those with complex ultrasound morphology, remains a great challenge for junior sonographers. The purpose of this study was to develop and validate a nomogram based on the Ovarian-Adnexal Reporting and Data System (O-RADS) for predicting the malignancy risk of adnexal masses with complex ultrasound morphology.A total of 243 patients with data on adnexal masses with complex ultrasound morphology from January 2019 to December 2020 were selected to establish the training cohort, while 106 patients with data from January 2021 to December 2021 served as the validation cohort. Univariate and multivariate analyses were used to determine independent risk factors for malignant tumors in the training cohort. Subsequently, a predictive nomogram model was developed and validated in the validation cohort. The calibration, discrimination, and clinical net benefit of the nomogram model were assessed separately by calibration curves, receiver operating characteristic (ROC) curves, and decision curve analysis (DCA). Finally, we compared this model to the O-RADS.The O-RADS category, an elevated CA125 level, acoustic shadowing and a papillary projection with color Doppler flow were the independent predictors and were incorporated into the nomogram model. The area under the ROC curve (AUC) of the nomogram model was 0.958 (95% CI, 0.932-0.984) in the training cohort. The specificity and sensitivity were 0.939 and 0.893, respectively. This nomogram also showed good discrimination in the validation cohort (AUC = 0.940, 95% CI, 0.899-0.981), with a sensitivity of 0.915 and specificity of 0.797. In addition, the nomogram model showed good calibration efficiency in both the training and validation cohorts. DCA indicated that the nomogram was clinically useful. Furthermore, the nomogram model had higher AUC and net benefit than the O-RADS.The nomogram based on the O-RADS showed a good predictive ability for the malignancy risk of adnexal masses with complex ultrasound morphology and could provide help for junior sonographers.© 2023. The Author(s).