Machine learning for predicting the survival in osteosarcoma patients: Analysis based on American and Hebei Province cohort

Authors

  • Yahui Hao Cancer Institute, The Fourth Hospital of Hebei Medical University/The Tumor Hospital of Hebei Province, Shijiazhuang, China https://orcid.org/0000-0002-7813-950X
  • Di Liang Cancer Institute, The Fourth Hospital of Hebei Medical University/The Tumor Hospital of Hebei Province, Shijiazhuang, China
  • Shuo Zhang Cancer Institute, The Fourth Hospital of Hebei Medical University/The Tumor Hospital of Hebei Province, Shijiazhuang, China https://orcid.org/0000-0002-4952-576X
  • Siqi Wu Cancer Institute, The Fourth Hospital of Hebei Medical University/The Tumor Hospital of Hebei Province, Shijiazhuang, China https://orcid.org/0000-0002-4460-5904
  • Daojuan Li Cancer Institute, The Fourth Hospital of Hebei Medical University/The Tumor Hospital of Hebei Province, Shijiazhuang, China
  • Yingying Wang Cancer Institute, The Fourth Hospital of Hebei Medical University/The Tumor Hospital of Hebei Province, Shijiazhuang, China https://orcid.org/0000-0002-2051-6341
  • Miaomiao Shi Cancer Institute, The Fourth Hospital of Hebei Medical University/The Tumor Hospital of Hebei Province, Shijiazhuang, China https://orcid.org/0000-0001-6359-7797
  • Yutong He Cancer Institute, The Fourth Hospital of Hebei Medical University/The Tumor Hospital of Hebei Province, Shijiazhuang, China

DOI:

https://doi.org/10.17305/bb.2023.8804

Keywords:

Osteosarcoma, prognosis model, TNM group, Surveillance, Epidemiology, and End Results (SEER), Hebei Province

Abstract

Osteosarcoma, a rare malignant tumor, has a poor prognosis. This study aimed to find the best prognostic model for osteosarcoma. There were 2912 patients included from the SEER database and 225 patients from Hebei Province. Patients from the SEER database (2008-2015) were included in the development dataset. Patients from the SEER database (2004-2007) and Hebei Province cohort were included in the external test datasets. The Cox model and three tree-based machine learning algorithms (survival tree [ST], random survival forest [RSF] and gradient boosting machine [GBM]) were used to develop the prognostic models by 10-fold cross-validation with 200 iterations. Additionally, performance of models in the multivariable group was compared with the TNM group. The 3-year and 5-year cancer specific survival (CSS) were 72.71% and 65.92% in the development dataset, respectively. The predictive ability in the multivariable group was superior to that in the TNM group. The calibration curves and consistency in the multivariable group were superior to those in the TNM group. The Cox and RSF models performed better than the ST and GBM models. A nomogram was constructed to predict the 3-year and 5-year CSS of osteosarcoma patients. The RSF model can be used as a nonparametric alternative to the Cox model. The constructed nomogram based on the Cox model can provide reference for clinicians to formulate specific therapeutic decisions both in America and China.

Downloads

Download data is not yet available.
Machine learning for predicting the survival in osteosarcoma patients: Analysis based on American and Hebei Province cohort

Downloads

Published

04-09-2023

How to Cite

1.
Machine learning for predicting the survival in osteosarcoma patients: Analysis based on American and Hebei Province cohort. Biomol Biomed [Internet]. 2023 Sep. 4 [cited 2024 Apr. 21];23(5):883–893. Available from: https://www.bjbms.org/ojs/index.php/bjbms/article/view/8804