Abstract
The availability of longstanding collection of detailed cancer patient information makes multivariable modelling of cancer‐specific hazard of death appealing. We propose to report variation in survival explained by each variable that constitutes these models. We adapted the ranks explained (RE) measure to the relative survival data setting, ie, when competing risks of death are accounted for through life tables from the general population. RE is calculated at each event time. We introduce weights for each death reflecting its probability to be a cancer death. RE varies between −1 and +1 and can be reported at given times in the follow‐up and as a time‐varying measure from diagnosis onward. We present an application for patients diagnosed with colon or lung cancer in England. The RE measure shows reasonable properties and is comparable in both relative and cause‐specific settings. One year after diagnosis, RE for the most complex excess hazard models reaches 0.56, 95% CI: 0.54 to 0.58 (0.58 95% CI: 0.56–0.60) and 0.69, 95% CI: 0.68 to 0.70 (0.67, 95% CI: 0.66–0.69) for lung and colon cancer men (women), respectively. Stage at diagnosis accounts for 12.4% (10.8%) of the overall variation in survival among lung cancer patients whereas it carries 61.8% (53.5%) of the survival variation in colon cancer patients. Variables other than performance status for lung cancer (10%) contribute very little to the overall explained variation. The proportion of the variation in survival explained by key prognostic factors is a crucial information toward understanding the mechanisms underpinning cancer survival. The time‐varying RE provides insights into patterns of influence for strong predictors.
Highlights
Complex, multivariable modelling of time‐to‐event data is accessible through user‐friendly specific commands in common statistical software.[1,2,3,4] In such models, the effects of prognostic factors on hazard of death are modelled and estimated
A measure of explained variation does not aim at providing information on how well a model fits the data at hand but provides information on how much of the variation in survival between records is explained by the model, and by the prognostic factors that compose the model
We presented here an adaptation of the ranks explained (RE) measure for event history data to excess hazard modelling
Summary
Multivariable modelling of time‐to‐event data is accessible through user‐friendly specific commands in common statistical software.[1,2,3,4] In such models, the effects of prognostic factors on hazard of death are modelled and estimated. We adapt a measure of explained variation, ranks explained (RE),[13] to the context of excess hazard models in the relative survival data setting. We address challenges related to the specificities of that setting and the excess hazard modelling, while the interpretation of the adapted RE is kept as simple as with the original RE measure This is exemplified by an extensive illustration using population‐based cancer registry data on patients diagnosed with colon or lung cancer in England. The section summarises the characteristics of the measure of explained variation, RE, presents the excess hazard models and how RE was adapted to the relative survival data setting. The discussion wraps up the main advantages and limitations of the measure proposed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
