An unmet significant challenge in the treatment of many early-stage cancers is the lack of effective prognostic models to identify patients who are at high risk of disease progression. The only way to identify these patients currently is to await disease recurrence. By then, the best chance to treat the cancer may have been lost. For example, about 90% of resected stage-1 melanoma patients are cured. Accurate and timely identification of high risk cancer patients can save more lives and reduce the number of cured cancer patients who receive costly over-treatment.
Mixture cure models can account for cure fractions in patients population can be more suitable prognostic models than ordinary survival models such as Cox Proportional Hazard models or Proportional Odds models that ignore the existence of cure fractions. We define new prognostic metrics to evaluate the prognostic accuracy for mixture cure models that considering the cure fraction. The asymptotic theory of these estimators is also established. Intensive simulations are provided to show the validity of these estimators in limit sample.
|
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.