Development And Validation Of A Clinical Predictive Model For The Overall Survival Rate Of Osteosarcoma

Objective:This study aimed to develop a predictive system for prognostic evaluation of osteosarcoma patients.Methods:We obtained osteosarcoma sample data from 1998 to 2016 using SEER*Stat software version 8.3.8,and established a multivariable Cox regression model using R-4.0.3 software.Data were extracted from the Surveillance,Epidemiology,and End Results(SEER)database.The diagnosis of the model was completed through influential cases,proportionality,and multicollinearity.The predictive ability of the model was tested using area under the curve(AUC),calibration curves,and Brier scores.Finally,the bootstrap method was used to internally verify the model.Results:A total of 3566 osteosarcoma cases were included in the study.The multivariate cox regression model determined the independent influencing factors,and the diagnosis of the model found that the strong influence points of all patients in the model were within the acceptable range(|dfbeta|<2δ),the proportional hazard assumption was also established,and the model did not exist Multicollinearity.The nomogram and K-M survival curve were drawn,and the variables included the patient’s gender,age at diagnosis,survival time,primary tumor site,treatment,histological classification and grade,and diameter.We obtained the AUC(0.831,0.764,and 0.752)of the training set for 1 year,3 years,and 5 years and the AUC(0.828,0.756,and 0.745)of the verification set for 1 year,3 years,and 5years respectively,indicating that our model has Very good distinction.At the same time,we also obtained the Brier scores(0.104,0.181,and 0.197)of the training set for 1 year,3 years,and 5 years and the Brier scores of the verification set for 1 year,3 years,and 5 years(0.105,0.184,and 0.199),indicating that Our model has good predictive calibration.Conclusion:We developed a prognostic evaluation system for patients with osteosarcoma for 1-,3-,and 5-year overall survival with good predictive ability using sample data extracted from the SEER database.This has important clinical significance for the early identification and treatment of high-risk groups of osteosarcoma patients.