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

Abstract

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.

Development and validation of a machine learning model for differential diagnosis of malignant pleural effusion using routine laboratory data

“…However, the application of machine learning models based on the laboratory information for identifying MPE from BPE has been relatively limited in previous studies. 17,18…”

“…However, the application of machine learning models based on the laboratory information for identifying MPE from BPE has been relatively limited in previous studies. 17,18 This study aims to establish an advanced machine learning model that surpasses CEA in the differential diagnosis of MPE and BPE. First, we collected and analyzed the clinical data, predominantly comprising routine laboratory variables, from patients with PE.…”

The Diagnosis of Malignant Pleural Effusion Using Tumor-Marker Combinations: A Cost-Effectiveness Analysis Based on a Stacking Model

“…Therefore, using cut-off values of tumor-marker concentrations to diagnose MPE has been popular in past years [6,7,10,11]. To handle the complex associations between tumor markers, machine learning methods, such as logistic regression, support vector machine (SVM), random forest, etc., have been widely used in this field and show good performance [12][13][14]. However, faced with so many algorithms, which one to choose in a real application becomes a challenging issue.…”

“…Despite the diagnostic accuracy of tumor markers, some studies discovered that the discriminating ability of single tumor markers was not high enough to make a precise MPE diagnosis, indicating the need for multi-marker combinations [13,14]. But the more tumor markers tested, the more costs and medical resources are consumed.…”

Prediction of Maternity Recovery Rate of Group Long-Term Disability Insurance Using XGBoost

“…XGBoost performs better than Support Vector Machines (SVM) in discriminating certain diseases in patients from healthy controls, using confusion matrix as its evaluation metric (Binson et al, 2021;Ogunleye et al, 2019). On the soil liquefaction prediction, whose data are sampled using different techniques, the study found that XGBoost perform better than Random Forests and SVM Demir et al (2022), data undergoing transformation Sahin (2023), better than random forest and gradient boosting machine on landslide data using RMSE as the evaluation metric Sahin (2020), better than logistic regression, Bayesian Additive Regression Tree (BART), random forest, and SVM on tumor classification problem Zhang et al (2023), better than SVM and K-nearest neighbour (KNN) on company bankruptcy classification problem Muslim et al (2021), and on surface water flooding data that stated XGBoost had a better generalization ability than SVM to improve prediction accuracy (Wang et al, 2021).…”