Prognostic Machine Learning Model for Children with Wilms Tumor: A SEER Database Study

Read full text Summarise with VIRAT
Authors: Jie Chen, Pingping Yu, Changyuan Wang
Cited by: 0
References: 28

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Abstract Objective : This study aimed to establish and validate a machine learning based prognostic model to predict the prognostic risk of childhood Wilms tumor. Methods : Data of 1958 children with Wilms tumor (data from 2000-2022) were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. The data were divided into a training set (70%) and a validation set (30%). Prognostic factors were analyzed by Cox regression. Five machine learning algorithms were used to construct models, which were evaluated by C-index, receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA). Meanwhile, a nomogram was drawn to visualize the model. Results : The results of the multivariate Cox regression analysis showed that age, lymph node density (LND), tumor stage, and place of residence were independent risk factors related to the prognosis. Among the fitted machine learning models, the LASSO-Cox model demonstrated relatively stable and accurate predictive performance. The C-index of the training set was 0.755 (95% CI: 0.704-0.806), and the C-index of the validation set was 0.752 (95% CI: 0.660-0.844). Conclusion : This study has identified the key prognostic indicators for childhood Wilms tumor, which can assist surgeons in accurately identifying the high-risk population with poor prognosis of Wilms tumor.

Fields of Study & Subjects

Renal and related cancers Neuroblastoma Research and Treatments Sarcoma Diagnosis and Treatment

Publication details

Journal / source
Research Square
Publication date
27 March 2026
Language
EN
Document type
Preprint