Skip to main content
Fig. 4 | Journal of Orthopaedic Surgery and Research

Fig. 4

From: Machine learning and experimental validation to construct a metastasis-related gene signature and ceRNA network for predicting osteosarcoma prognosis

Fig. 4

A prognostic model was constructed. A Select the lambda parameter lambda.min = 0.0501, the horizontal axis represents the value of the independent variable lambda, and the vertical axis represents the coefficient of the independent variable. B The relationship between partial likelihood deviation and log () is drawn using the LASSO Cox regression model. C Riskscore and survival time and survival status in the TARGET, where the top represents the Riskscore from low to high scatter ma, different colors represent different expression groups. E Represents the scatter map distribution of survival time and survival status of different samples risk score. F Represents the expression heat map of genes in the signature. D HR (High exp) represents the risk coefficient of high expression group relative to low expression group; if HR > 1 represents the risk factor, if HR < 1; 95%CL represents the HR confidence interval; Median time represents the time of survival rate between high expression group and low expression group. G The ROC curve and AUC for different times of the risk model, where the higher the AUC value is, the stronger the predictive power of the model is

Back to article page