Objectives To identify key clinical factors influencing recurrence in osteosarcoma patients,to construct and validate a Nomogram-based recurrence risk prediction model,thereby providing a quantitative tool for clinical decision-making and recurrence prevention/control.Methods Clinical data of 469 osteosarcoma patients admitted to Yunnan Cancer Hospital between 2013～2022 were retrospectively collected.Statistical analysis was performed using R software(version 4.3.2).Potential influencing factors were initially screened via univariate analysis and LASSO regression analysis.Independent predictors of osteosarcoma recurrence were then identified using multivariate logistic regression analysis.Based on the identified independent factors,a Nomogram prediction model for recurrence risk was constructed.The area under the receiver operating characteristic curve(AUC)was used to evaluate the model's discriminative ability.Results Among the entire cohort,68 patients experienced recurrence,yielding a recurrence rate of 14.50%.Multivariate analysis identified the following as independent predictors of recurrence:Primary Tumor Location:Tibial lesions(P=0.009)were associated with a significantly lower recurrence risk compared to femoral lesions(OR=0.297),while lesions in"Other Bones"(P=0.008)carried a significantly higher risk(OR=3.294).Biopsy Method:Needle biopsy(P=0.033)was associated with a significantly lower recurrence risk compared to open biopsy(OR=0.461).Lung Metastasis Status:Patients with lung metastasis(P<0.001)had a significantly higher recurrence risk than those without(OR=11.873).Lymphocyte Count:A higher lymphocyte count(P=0.001)was a protective factor,associated with a lower recurrence risk(OR=0.450).The constructed Nomogram prediction model demonstrated excellent performance:Validation results showed an AUC=0.842(95%CI:0.806～0.875),indicating outstanding discriminative ability.Conclusions This study successfully constructed and validated a Nomogram prediction model for osteosarcoma recurrence risk integrating key clinical factors.The model demonstrates superior discriminative ability and can accurately and quantitatively assess the recurrence risk for individual patients.This tool thus provides critical reference for guiding clinical treatment decisions.