AUTHOR=Li Wenle , Jin Genyang , Wu Huitao , Wu Rilige , Xu Chan , Wang Bing , Liu Qiang , Hu Zhaohui , Wang Haosheng , Dong Shengtao , Tang Zhi-Ri , Peng Haiwen , Zhao Wei , Yin Chengliang 

TITLE=Interpretable clinical visualization model for prediction of prognosis in osteosarcoma: a large cohort data study

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.945362

DOI=10.3389/fonc.2022.945362

ISSN=2234-943X

ABSTRACT=ABSTRACT
Background: Currently, the clinical prediction model for patients with osteosarcoma was almost developed from single-center data, lacking external validation. Due to their low reliability and low predictive power, the clinical application was less. Our study aimed to set up a clinical prediction model with stronger predictive ability, credibility, and clinical application value for osteosarcoma.
Methods: Clinical information was collected related to osteosarcoma patients from 2010 to 2016 in the SEER database and four Chinese different medical centers. Factors were screened using three models (full subset regression, univariate cox, and Lasso) via minimum AIC and maximum AUC values in the SEER database. The model was selected by the strongest predictive power and visualized by three statistical methods: Nomogram, web calculator, and decision tree. The model was further externally validated and evaluated for its clinical utility in four medical centers' data. 
Results: Eight predicting factors, including age, grade, laterality, stage M, surgery, bone metastases, lung metastases, and tumor size, were selected from the model based on minimum AIC and maximum AUC value. The internal and external validation results showed that the model possessed good consistency. ROC curves revealed good predictive ability (AUC > 0.8 both in internal and external validation). The DCA results demonstrated that the model owned an excellent clinical predicted utility in 3-year and 5-year for North America and Chinese patients. 

Conclusions: The clinical prediction model was built and visualized in this study, including Nomogram and web calculator (https://dr-lee.shinyapps.io/osteosarcoma//). which indicated very good consistency, predictive power, and clinical application value.
Keywords: osteosarcoma, SEER, multicenter study, Nomogram, web calculator, prediction model.