Linearity of Age at Cancer Onset Worldwide: 25-Year Population-Based Cancer Registry Study

Abstract

Background The linear association between median age at cancer onset and median age of the underlying population has been described only for breast cancer. We quantified the shape and strength of such association for 20 cancer types using data from all population-based cancer registries (CRs) worldwide. Methods The patients' median age at cancer onset and of the underlying population were extracted from all CRs listed in volumes VI (1983-1987 years) and XI (2008-2012 years) of Cancer Incidence in Five Continents. The association was assessed at cross-sectional level by linear regression models and longitudinally considering only the long-standing CRs active throughout the study period (i.e., 25-year span). Results During 2008-2012, each one-year increase in median population ageing was associated in men with a nearly half year increase of median age at onset of all cancers, but skin; and a 2/3 year increase in women. Variance explained by linear model was around 60%. In long-standing CRs a decrease in median age at cancer onset was observed for prostate and cervical cancers throughout the 25-year span. Conclusions Population ageing reflected 60% of the median age at cancer onset. Misinterpretation of peaks of cancer incidence in specific age groups may be avoided by examining population pyramids.

Keywords: 25-year; age at onset; cancer; incidence; population pyramid; worldwide.

Figure 1

Scatter plots and linear regression with corresponding 95% predictive intervals, of the median age of the population (independent variable) vs. the median age of studied cancers cases in the populations recorded in all cancer registries listed in the XI volume of Cancer in Five Continents (period 2008–2012).(a) Males; (b) Females.

Figure 1

Scatter plots and linear regression with corresponding 95% predictive intervals, of the median age of the population (independent variable) vs. the median age of studied cancers cases in the populations recorded in all cancer registries listed in the XI volume of Cancer in Five Continents (period 2008–2012).(a) Males; (b) Females.

Figure 1

Scatter plots and linear regression with corresponding 95% predictive intervals, of the median age of the population (independent variable) vs. the median age of studied cancers cases in the populations recorded in all cancer registries listed in the XI volume of Cancer in Five Continents (period 2008–2012).(a) Males; (b) Females.