Diagnostic accuracy of epithelial membrane antigen for malignant effusions: a meta-analysis

Diagnosis of malignant pleural effusion with combinations of multiple tumor markers: A comparison study of five machine learning models

BACKGROUND

To evaluate the diagnostic value of combinations of tumor markers carcinoembryonic antigen (CEA), carbohydrate antigen (CA) 125, CA153, and CA19-9 in identifying malignant pleural effusion (MPE) from non-malignant pleural effusion (non-MPE) using machine learning, and compare the performance of popular machine learning methods.

METHODS

A total of 319 samples were collected from patients with pleural effusion in Beijing and Wuhan, China, from January 2018 to June 2020. Five machine learning methods including Logistic regression, extreme gradient boosting (XGBoost), Bayesian additive regression tree, random forest, and support vector machine were applied to evaluate the diagnostic performance. Sensitivity, specificity, Youden's index, and the area under the receiver operating characteristic curve (AUC) were used to evaluate the performance of different diagnostic models.

RESULTS

For diagnostic models with a single tumor marker, the model using CEA, constructed by XGBoost, performed best (AUC = 0.895, sensitivity = 0.80), and the model with CA153, also by XGBoost, showed the largest specificity 0.98. Among all combinations of tumor markers, the combination of CEA and CA153 achieved the best performance (AUC = 0.921, sensitivity = 0.85) in identifying MPE under the diagnostic model constructed by XGBoost.

CONCLUSIONS

Diagnostic models for MPE with a combination of multiple tumor markers outperformed the models with a single tumor marker, particularly in sensitivity. Using machine learning methods, especially XGBoost, could comprehensively improve the diagnostic accuracy of MPE.

Expression of E-cadherin, β-catenin, and epithelial membrane antigen does not predict survival in patients with high-risk non-muscle-invasive bladder cancer

The aim of the study

The aim of the study was to validate the value of E-cadherin and β-catenin expression and to test an alternative prognostic marker, epithelial membrane antigen (EMA).

Material and methods

Forty-nine consecutive patients with primary stage T1 non-muscle-invasive bladder cancer (NMIBC) were enrolled in this study. Tissue specimens were stained with the following mouse anti-human antibodies: anti-E-cadherin, anti-β-catenin, and anti-EMA. Reaction intensity within cancer cells was assessed according to the immunoreactive score (IRS). Finally, the association between the expression of selected proteins and patient survival was assessed.

Results

The mean follow-up was 34.8 months. Recurrence-free survival, progression-free survival, and overall survival (OS) were 47.5%, 72.5%, and 72.5%, respectively. Differences in the IRS for β-catenin and EMA were found clinically, but were not statistically significant in prediction of the risk of disease progression (p > 0.05). No difference in protein expression was observed regarding the risk of recurrence, OS, or cancer-specific mortality (p > 0.05). Stratification of patients based on the IRS into three groups (poor, moderate, and intensive reaction) failed to identify a prognostic marker among the tested proteins (p > 0.05).

Conclusions

Expression of E-cadherin, β-catenin, and EMA cannot reliably predict survival in patients with high-risk NMIBC. Further searches are needed to identify tissue markers of progression and recurrence in NMIBC.