When do I know I am cured? Using conditional estimates to provide better information about cancer survival prospects

Abstract

Objective: To report the latest conditional survival estimates for patients with cancer in Queensland, Australia.

Design, setting and participants: Descriptive study of state-wide population-based data from the Queensland Cancer Registry on patients aged 15-89 years who were diagnosed with invasive cancer between 1982 and 2007.

Main outcome measure: Conditional 5-year relative survival for the 13 most common types of invasive cancer, and all cancers combined.

Results: The prognosis for patients with cancer generally improves with each additional year that they survive. A significant excess in mortality compared with the general population ceases to occur within 10 years after diagnosis for survivors of stomach, colorectal, cervical and thyroid cancer and melanoma, with these groups having a conditional 5-year relative survival of at least 95% after 10 years. For the remaining cancers we studied (pancreatic, lung, breast, prostate, kidney, and bladder cancer, non-Hodgkin lymphoma, and leukaemia), conditional 5-year relative survival estimates (at 10 years after diagnosis) ranged from 82% to 94%, suggesting that patients in these cohorts continue to have poorer survival compared with the age-matched general population.

Conclusions: Estimates of conditional survival have the potential to provide useful information for cancer clinicians, patients and their carers as they are confronted by personal and surveillance-related decisions. This knowledge may be effective in building realistic hope and helping people manage uncertainty about the future. We suggest that measures of conditional survival be incorporated into routine statistical reporting in Australia.