Background: This study used receiver operating characteristic curve to analyze Surveillance, Epidemiologyand End Results (SEER) Ewing sarcoma (ES) outcome data. The aim of this study was to identify and optimizeES-specific survival prediction models and sources of survival disparities. Materials and
Methods: This studyanalyzed socio-economic, staging and treatment factors available in the SEER database for ES. 1844 patientsdiagnosed between 1973-2009 were used for this study. For the risk modeling, each factor was fitted by aGeneralized Linear Model to predict the outcome (bone and joint specific death, yes/no). The area under thereceiver operating characteristic curve (ROC) was computed. Similar strata were combined to construct themost parsimonious models.
Results: The mean follow up time (S.D.) was 74.48 (89.66) months. 36% of thepatients were female. The mean (S.D.) age was 18.7 (12) years. The SEER staging has the highest ROC (S.D.)area of 0.616 (0.032) among the factors tested. We simplified the 4-layered risk levels (local, regional, distant,un-staged) to a simpler non-metastatic (I and II) versus metastatic (III) versus un-staged model. The ROC area(S.D.) of the 3-tiered model was 0.612 (0.008). Several other biologic factors were also predictive of ES-specificsurvival, but not the socio-economic factors tested here.
Conclusions: ROC analysis measured and optimized theperformance of ES survival prediction models. Optimized models will provide a more efficient way to stratifypatients for clinical trials.