A screened predictive model for esophageal squamous cell carcinoma based on salivary flora data
-
Published:2023
Issue:10
Volume:20
Page:18368-18385
-
ISSN:1551-0018
-
Container-title:Mathematical Biosciences and Engineering
-
language:
-
Short-container-title:MBE
Author:
Meng Yunxiang1, Duan Qihong1, Jiao Kai2, Xue Jiang1
Affiliation:
1. School of Mathematics and Statistics, Xi'an JiaoTong University, Xi'an, China 2. Department of Oral Mucosal Diseases, State Key Laboratory of Military Stomatology & National Clinical Research Center for Oral Diseases & Shaanxi Key Laboratory of Stomatology, School of Stomatology, The Fourth Military Medical University, Xi'an, China
Abstract
<abstract><p>Esophageal squamous cell carcinoma (ESCC) is a malignant tumor of the digestive system in the esophageal squamous epithelium. Many studies have linked esophageal cancer (EC) to the imbalance of oral microecology. In this work, different machine learning (ML) models including Random Forest (RF), Gaussian mixture model (GMM), K-nearest neighbor (KNN), logistic regression (LR), support vector machine (SVM) and extreme gradient boosting (XGBoost) based on Genetic Algorithm (GA) optimization was developed to predict the relationship between salivary flora and ESCC by combining the relative abundance data of <italic>Bacteroides</italic>, <italic>Firmicutes</italic>, <italic>Proteobacteria</italic>, <italic>Fusobacteria</italic> and <italic>Actinobacteria</italic> in the saliva of patients with ESCC and healthy control. The results showed that the XGBoost model without parameter optimization performed best on the entire dataset for ESCC diagnosis by cross-validation (Accuracy = 73.50%). Accuracy and the other evaluation indicators, including Precision, Recall, F1-score and the area under curve (AUC) of the receiver operating characteristic (ROC), revealed XGBoost optimized by the GA (GA-XGBoost) achieved the best outcome on the testing set (Accuracy = 89.88%, Precision = 89.43%, Recall = 90.75%, F1-score = 90.09%, AUC = 0.97). The predictive ability of GA-XGBoost was validated in phylum-level salivary microbiota data from ESCC patients and controls in an external cohort. The results obtained in this validation (Accuracy = 70.60%, Precision = 46.00%, Recall = 90.55%, F1-score = 61.01%) illustrate the reliability of the predictive performance of the model. The feature importance rankings obtained by XGBoost indicate that <italic>Bacteroides</italic> and <italic>Actinobacteria</italic> are the two most important factors in predicting ESCC. Based on these results, GA-XGBoost can predict and diagnose ESCC according to the relative abundance of salivary flora, providing an effective tool for the non-invasive prediction of esophageal malignancies.</p></abstract>
Publisher
American Institute of Mathematical Sciences (AIMS)
Subject
Applied Mathematics,Computational Mathematics,General Agricultural and Biological Sciences,Modeling and Simulation,General Medicine
Reference44 articles.
1. M. Arnold, I. Soerjomataram, J. Ferlay, D. Forman, Global incidence of oesophageal cancer by histological subtype in 2012, Gut, 64 (2015), 381–387. https://doi.org/10.1136/gutjnl-2014-308124 2. E. J. Snider, G. Compres, D. E. Freedberg, H. Khiabanian, Y. R. Nobel, S. Stump, et al., Alterations to the Esophageal Microbiome Associated with Progression from Barrett's Esophagus to Esophageal Adenocarcinoma, Cancer Epidem. Biomar. Prev., 28 (2019), 1687–1693. https://doi.org/10.1158/1055-9965.EPI-19-0008 3. J. Zhao, Y. T. He, R. S. Zheng, S. W. Zhang, W. Q. Chen, Analysis of esophageal cancer time trends in China, 1989–2008, Asian Pac. J. Cancer Prev., 13 (2012), 4613–4617. https://doi.org/10.7314/apjcp.2012.13.9.4613 4. A. Q. Liu, E. Vogtmann, D. T. Shao, C. C. Abnet, H. Y. Dou, Y. Qin, et al., A Comparison of Biopsy and Mucosal Swab Specimens for Examining the Microbiota of Upper Gastrointestinal Carcinoma, Cancer Epidem. Biomar. Prev., 28 (2019), 2030–2037. https://doi.org/10.1158/1055-9965.EPI-18-1210 5. R. Lozano, M. Naghavi, K. Foreman, S. Lim, K. Shibuya, V. Aboyans, et al., Global and regional mortality from 235 causes of death for 20 age groups in 1990 and 2010: a systematic analysis for the Global Burden of Disease Study 2010, Lancet, 380 (2012), 2095–2128. https://doi.org/10.1016/S0140-6736(12)61728-0
|
|