Shuaixin Wang

Development and validation of a prediction model for lymph node metastasis based on molecular typing in clinically early-stage endometrial carcinoma

To develop and externally validate a machine learning-based preoperative model integrating molecular typing and clinical features to predict lymph node metastasis (LNM) in patients with early-stage endometrial carcinoma (EC). This retrospective study included 465 patients with clinically early-stage EC treated at Qilu Hospital of Shandong University. Tumors were classified into molecular subtypes using The Cancer Genome Atlas-based methods. Least Absolute Shrinkage and Selection Operator regression identified five preoperative predictors: molecular typing (CN-H vs. non-CN-H), histological subtype, depth of myometrial invasion, neutrophil-to-lymphocyte ratio, and CA125 levels. Multiple machine learning algorithms were evaluated, and logistic regression (LR) was selected based on optimal discrimination and clinical applicability. Model performance was assessed using area under the curve (AUC), calibration plots, and decision curve analysis (DCA). A web-based nomogram was developed for clinical use. The LR model demonstrated excellent discrimination, with AUCs of 0.843 in the training cohort and 0.809 in the testing cohort. The CN-H subtype was significantly associated with increased LNM risk. The model enabled effective risk stratification and calibration curves and DCA confirmed the model's accuracy and clinical utility. By integrating molecular and preoperative clinical features, this model offers accurate LNM risk stratification for early-stage EC. It supports clinical decision-making and has been implemented as a user-friendly online tool. Further prospective multicenter validation is warranted.

Molecular subtyping of endometrial cancer via a simplified one-step NGS classifier, ARID1A and ZFHX4 mutations help further subclassify CNL/MSI-H patients

Abstract Background Molecular subtyping has changed the prognostic stratification and therapeutic guidance for patients with endometrial cancer (EC). However, simultaneous application of sanger sequencing and immunohistochemistry under ProMisE criteria may be time- and tissue-consuming. This study attempted to measure subtype-specific biomarkers by one-step next-generation sequencing (NGS) resulting in a shorter turnaround time and less requirement of tissue samples. Methods FFPE samples from 233 EC patients were retrospectively collected. Overall survival (OS) information was available for 131 patients with a median follow-up of 66 months. Genomic DNA was extracted and subjected to a one-step NGS panel including TP53, POLE and MSI measurement. Further comprehensive genomic analyses were performed on DNA from MSI-H and copy number low (CNL) subtypes. Results The molecular typing ratio of the 233 patients was 8.15% for POLE subtype, 18.88% for MSI-H subtype, 11.59% for copy number high (CNH) subtype and 61.37% for CNL subtype. The 10-year OS and disease-specific survival (DSS) rate was 100% in POLE subtype, while only 33.51% and 39.69% in CNH subtype. In patients with CNL and CNL/MSI-H subtypes, ARID1A and ZFHX4 mutations were significantly associated with worse prognosis respectively. Conclusion This simplified one-step NGS panel can effectively subgroup EC patients into four prognostically different subtypes. New biomarkers are able to potentially refine the classification of patients with CNL/MSI-H subtypes into groups with distinct clinical outcomes.