A clinicoradiological model based on clinical and CT features for preoperative prediction of histological classification in patients with epithelial ovarian cancers: a two-center study.

Abstract

Objectives: To develop and validate a clinicoradiological model integrating clinical and computed tomography (CT) features to preoperative predict histological classification in patients with epithelial ovarian cancers (EOCs).

Methods: This retrospective study included 470 patients who were pathologically proven EOCs and performed by contrast enhanced CT before treatment from center I (training cohort, N = 329; internal test cohort, N = 141) and 83 EOC patients who were included as an external test cohort from center II. The univariate analysis and multivariate logistic regression analysis were used to select significant clinical and CT features. The significant clinical model was developed based on clinical characteristics. The significant radiological model was established by CT features. The significant clinical and CT features were used to construct the clinicoradiological model. Model performances were evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve, the Brier score and decision curve analysis (DCA). The AUCs were compared by net reclassification index (NRI) and integrated discrimination improvement (IDI).

Results: The significant clinical and CT parameters including age, transverse diameter, morphology, margin, ascites and lymphadenopathy were incorporated to build the clinicoradioligical model. The clinicoradiological model showed relatively satisfactory discrimination between type I and type II EOCs with the AUC of 0.841 (95% confidence interval [CI] 0.797-0.886), 0.874 (95% CI 0.811-0.937) and 0.826 (95% CI 0.729-0.923) in the training, internal and external test cohorts, respectively. The NRI and IDI showed the clinicoradiological model significantly performed than those of the clinical model (all P < 0.05). No statistical significance was found between radiological and clinicoradiological model. The clinicoradiological model demonstrated optimal classification accuracy and clinical application value.

Conclusion: The easily accessible nomogram based on the clinicoradiologic model showed favorable performance in distinguishing between type I and type II EOCs and could therefore be used to improve the clinical management of EOC patients.