Effects of coagulation function indicators and tumor markers on diagnosis and clinicopathological characteristics of endometrial cancer.

BACKGROUND: Endometrial cancer is currently the prevalent malignant cancer worldwide. Diagnostic efficiency of tumor markers is limited, and coagulation function indicators in endometrial cancer are less concerned. METHODS: This study attempted to evaluate the effects of coagulation function indicators and tumor markers on the clinical diagnosis and clinicopathological characteristics of patients with endometrial cancer. The retrospective analysis compared the differences in coagulation function indicators and tumor markers among 175 patients with endometrial cancer and 170 healthy women from January 2020 to October 2022. RESULTS: Compared to the healthy control, the levels of D-dimer, fibrinogen, human epididymis protein 4 (HE4), carbohydrate antigen 125 (CA125), CA153, and CA199 in patients with endometrial cancer were significantly higher (P < 0.05). Univariate and multivariate regression analyses revealed that abnormal levels of D-dimer, fibrinogen, HE4, CA125, CA153, and CA199 were related risk factors affecting the incidence of endometrial cancer. Receiver operating characteristic curve analysis exhibited that the area under the curve (0.931) and accuracy (85.2%) of combined diagnosis of coagulation function indicators (D-dimer, fibrinogen) and tumor markers (HE4, CA125, CA153, CA199) were the highest, and its sensitivity (82.3%) and specificity (88.2%) were higher than any single or combined indicators of four tumor markers. Moreover, relative expression levels of the combined indicators were significantly different among clinicopathological characteristics that had the highest predictive value in the FIGO stage (P < 0.001). CONCLUSIONS: D-dimer and fibrinogen represent potential diagnostic factors for endometrial cancer. The combination of coagulation function indicators and tumor markers exhibited high diagnostic value in endometrial cancer, as well as predictive value for clinicopathological characteristics.

Development of prediction model to estimate future risk of ovarian lesions: A multi-center retrospective study.

Background: To develop the preoperative prediction of ovarian lesions using regression-based statistics analyses and machine learning methods based on multiple serological biomarkers in China. Methods: 1137 patients with ovarian lesions in Zhujiang Hospital and 518 patients in others hospital in China were randomly assigned to training, test and external validation cohorts. Five machine learning classifiers, including Random Forest (RF), Extreme Gradient Boosting (XGB), Support Vector Classifier (SVC), K-nearest Neighbor (KN), Multi-Layer Perceptron (MLP) and the Lasso-Logistics prediction model (LLRM) were used to derive diagnostic information from 23 predictors. Results: The RF model had a high diagnostic value (AUC = 0.968) in predicting benign and malignant ovarian disease. Age and MLR were also potential diagnostic indicators for predicting ovarian disease except tumor indicators. The RF model well distinguished borderline ovarian tumors (AUC = 0.742). The RFM had a high predictive power to identify ovarian serous adenocarcinoma (AUC = 0.943) and ovarian endometriosis cysts (AUC = 0.914). Conclusions: The RF models can effectively predict adnexal lesions, promising to be adjuncts to the preoperative prediction of ovarian cancer.