Development of a model to predict breast cancer survival using data from the National Cancer Data Base

摘要: Background With the large amounts of data on patient, tumor, and treatment factors available to clinicians, it has become critically important harness this information guide clinicians in discussing a patient's prognosis. However, no widely accepted survival calculator is that uses national includes multiple prognostic factors. Our objective was develop model for predicting among patients diagnosed with breast cancer using National Cancer Data Base (NCDB) serve as prototype Commission Cancer's “Cancer Survival Prognostic Calculator.” Patients methods A retrospective cohort (2003–2006) NCDB included. multivariable Cox proportional hazards regression predict overall developed. Model discrimination by 10-fold internal cross-validation calibration assessed. Results There were 296,284 development validation. The c-index ranged from 0.779 0.788 after inclusion all pertinent plot observed versus predicted 5 year showed minimal deviation reference line. Conclusion This be used building Calculator” will offer an opportunity estimate personalized long-term based patient demographic characteristics, tumor factors, delivered.