Related Experiment Video
Updated: Aug 10, 2026
Establishment and Evaluation of a Risk Prediction Model for Pathological Escalation of Gastric Low-Grade Intraepithelial Neoplasia
Published on: February 16, 2024
Development and validation of a blood biomarker risk prediction model for postmenopausal endometrioid endometrial
Hubin Xu1,2, Mengyu Zhang1,2, Huinan Zhu2
1The Second School of Clinical Medicine, Hangzhou Normal University, Hangzhou, Zhejiang, China.
Objective:
To investigate the association between preoperative peripheral venous blood biomarkers and postmenopausal endometrioid endometrial carcinoma (EEC) and to develop a clinical risk prediction model.
Methods:
A retrospective study was conducted on patients who underwent hysteroscopic examination in the Department of Gynecology, Zhejiang Provincial People's Hospital, between 2018 and 2024. Clinical data, pathological findings, and peripheral venous blood test results were collected. The t-test and least absolute shrinkage and selection operator (LASSO) regression analysis were performed to identify potential risk factors associated with postmenopausal EEC. Logistic regression analysis was subsequently conducted to determine independent risk factors. A clinical risk prediction model was developed based on these factors, and its discriminative and calibration abilities were assessed. Finally, the model was deployed in an online calculator for clinical application.
Results:
After applying inclusion and exclusion criteria, a total of 311 patients were enrolled, including 119 cases of benign endometrial diseases and 192 cases of endometrioid carcinoma. Through t-test analysis, LASSO regression, and logistic regression analysis, five independent risk factors were identified: body mass index (BMI), cancer antigen 125 (CA125), human epididymis protein 4 (HE4), platelet-to-lymphocyte ratio (PLR), and albumin (ALB). A clinical prediction model incorporating these factors was established, yielding an area under the curve (AUC) of 0.936 (95% CI: 0.9081-0.9631). At the optimal Youden index, the model demonstrated a specificity of 89.1% and a sensitivity of 90.1%, indicating excellent discriminative and calibration performance. The final model was implemented in an online calculator to facilitate dynamic clinical risk predictions for postmenopausal EEC.
Conclusion:
BMI, CA125, HE4, PLR, and ALB were identified as independent risk factors for postmenopausal EEC. The clinical risk prediction model based on preoperative blood biomarkers demonstrated robust predictive performance, supporting its potential application in clinical decision-making.