Treatment toxicity in endometrial cancer: can we identify and manage it better?

Construction and validation of a clinical risk model based on machine learning for screening characteristic factors of lymphovascular space invasion in endometrial cancer

This study aimed to identify factors that affect lymphovascular space invasion (LVSI) in endometrial cancer (EC) using machine learning technology, and to build a clinical risk assessment model based on these factors. Samples were collected from May 2017 to March 2022, including 312 EC patients who received treatment at Xuzhou Medical University Affiliated Hospital of Lianyungang. Of these, 219 cases were collected for the training group and 93 for the validation group. Clinical data and laboratory indicators were analyzed. Logistic regression and least absolute shrinkage and selection operator (LASSO) regression were used to analyze risk factors and construct risk models. The LVSI and non-LVSI groups showed statistical significance in clinical data and laboratory indicators (P < 0.05). Multivariable logistic regression analysis identified independent risk factors for LVSI in EC, which were myometrial infiltration depth, cervical stromal invasion, lymphocyte count (LYM), monocyte count (MONO), albumin (ALB), and fibrinogen (FIB) (P < 0.05). LASSO regression identified 19 key feature factors for model construction. In the training and validation groups, the risk scores for the logistic and LASSO models were significantly higher in the LVSI group compared with that in the non-LVSI group (P < 0.001). The model was built based on machine learning and can effectively predict LVSI in EC and enhance preoperative decision-making. The reliability of the model was demonstrated by the significant difference in risk scores between LVSI and non-LVSI patients in both the training and validation groups.

An Immune-Related Long Noncoding RNA Signature as a Prognostic Biomarker for Human Endometrial Cancer

Background

Endometrial cancer is among the most common malignant tumors threatening the health of women. Recently, immunity and long noncoding RNA (lncRNA) have been widely examined in oncology and shown to play important roles in oncology. Here, we searched for immune-related lncRNAs as prognostic biomarkers to predict the outcome of patients with endometrial cancer.

Methods

RNA sequencing data for 575 endometrial cancer samples and immune-related genes were downloaded from The Cancer Genome Atlas (TCGA) database and gene set enrichment analysis (GSEA) gene sets, respectively. Immune-related lncRNAs showing a coexpression relationship with immune-related genes were obtained, and Cox regression analysis was performed to construct the prognostic model. Survival, independent prognostic, and clinical correlation analyses were performed to evaluate the prognostic model. Immune infiltration of endometrial cancer samples was also evaluated. Functional annotation of 12 immune-related lncRNAs was performed using GSEA software. Prognostic nomogram and survival analysis for independent prognostic risk factors were performed to evaluate the prognostic model and calculate the survival time based on the prognostic model.

Results

Twelve immune-related lncRNAs (ELN-AS1, AC103563.7, PCAT19, AF131215.5, LINC01871, AC084117.1, NRAV, SCARNA9, AL049539.1, POC1B-AS1, AC108134.4, and AC019080.5) were obtained, and a prognostic model was constructed. The survival rate in the high-risk group was significantly lower than that in the low-risk group. Patient age, pathological grade, the International Federation of Gynecology and Obstetrics (FIGO) stage, and risk status were the risk factors. The 12 immune-related lncRNAs correlated with patient age, pathological grade, and FIGO stage. Principal component analysis and functional annotation showed that the high-risk and low-risk groups separated better, and the immune status of the high-risk and low-risk groups differed. Nomogram and receiver operating characteristic (ROC) curves effectively predicted the prognosis of endometrial cancer. Additionally, age, pathological grade, FIGO stage, and risk status were all related to patient survival.

Conclusion

We identified 12 immune-related lncRNAs affecting the prognosis of endometrial cancer, which may be useful as therapeutic targets and molecular biomarkers.