A Machine Learning-Based Predictive Model for Predicting Lymph Node Metastasis in Patients With Ewing’s Sarcoma

Frontiers in Medicine

article

Wenle Li¹  Qian Zhou³  Wencai Liu⁴  Chan Xu³  Zhi-Ri Tang⁶  Shengtao Dong⁷  Haosheng Wang⁸  Wanying Li²  Kai Zhang¹  Rong Li⁹  Wenshi Zhang⁹  Zhaohui Hu^1,10  Su Shibin^1,11  Qiang Liu²  Sirui Kuang^1,12  Chengliang Yin^1,12 

[1] Department of Orthopedics, Xianyang Central Hospital;Clinical Medical Research Center, Xianyang Central Hospital;Department of Respiratory and Critical Care Medicine, The First People’s Hospital of Chongqing Liang Jiang New Area;Department of Orthopaedic Surgery, The First Affiliated Hospital of Nanchang University;Department of Dermatology, Xianyang Central Hospital;School of Physics and Technology, Wuhan University;Department of Spine Surgery, Second Affiliated Hospital of Dalian Medical University;Department of Orthopaedics, The Second Hospital of Jilin University;The First Clinical Medical College, Shaanxi University of Traditional Chinese Medicine;Department of Spinal Surgery, Liuzhou People’s Hospital;Department of Business Management;Faculty of Medicine, Macau University of Science and Technology

关键词: Ewing sarcoma;    lymph node metastasis;    SEER;    multi-center;    machine learning;    web calculator;   

DOI  :  10.3389/fmed.2022.832108

学科分类：社会科学、人文和艺术（综合）

来源: Frontiers

【 摘 要 】

Objective In order to provide reference for clinicians and bring convenience to clinical work, we seeked to develop and validate a risk prediction model for lymph node metastasis (LNM) of Ewing’s sarcoma (ES) based on machine learning (ML) algorithms. Methods Clinicopathological data of 923 ES patients from the Surveillance, Epidemiology, and End Results (SEER) database and 51 ES patients from multi-center external validation set were retrospectively collected. We applied ML algorithms to establish a risk prediction model. Model performance was checked using 10-fold cross-validation in the training set and receiver operating characteristic (ROC) curve analysis in external validation set. After determining the best model, a web-based calculator was made to promote the clinical application. Results LNM was confirmed or unable to evaluate in 13.86% (135 out of 974) ES patients. In multivariate logistic regression, race, T stage, M stage and lung metastases were independent predictors for LNM in ES. Six prediction models were established using random forest (RF), naive Bayes classifier (NBC), decision tree (DT), xgboost (XGB), gradient boosting machine (GBM), logistic regression (LR). In 10-fold cross-validation, the average area under curve (AUC) ranked from 0.705 to 0.764. In ROC curve analysis, AUC ranged from 0.612 to 0.727. The performance of the RF model ranked best. Accordingly, a web-based calculator was developed ( https://share.streamlit.io/liuwencai2/es_lnm/main/es_lnm.py ). Conclusion With the help of clinicopathological data, clinicians can better identify LNM in ES patients. Risk prediction models established in this study performed well, especially the RF model.

【 授权许可】

CC BY