Abstract

STUDY OBJECTIVES--To examine a national data set of all childhood cancers for evidence of space-time interactions within three distinct sets of dates and places (at birth, at diagnosis, and at death), to show whether the patterns found for these events represent separate phenomena or statistically interdependent processes, and to see whether the childhood leukaemias and the childhood solid cancers have separate distinctive patterns in these respects. DESIGN--This was a space-time cluster analysis. The large number of cases enabled division of the data into two sets, one for hypothesis generation and the other for hypothesis testing. SETTING--England, Scotland, and Wales. SUBJECTS--A national collection of 22,360 children aged 0-15 years with fatal cancers and leukaemias in the period 1953 to 1980. MAIN RESULTS--There was significant clustering among the leukaemias and lymphomas on date and place of birth (particularly among cases born within 1 km and up to 5 months apart), and on date and place of diagnosis (particularly among cases diagnosed from 3 to 5 km apart and up to 9 months apart). There was no clustering among the solid cancers. These findings were confirmed in two separate analyses of two separate sets of data. CONCLUSIONS--The birth clustering was significant among pairs diagnosed at differing ages, and diagnosis clustering was significant among pairs born at different times, and it was concluded that the two types of clustering must be regarded as separate and statistically independent phenomena. Both the birth and the diagnosis clusters comprised many independent pairs of cases, with no large multiple case clusters. This suggests the involvement of multiple time-space localised exposures to hazards with short and constant latent intervals; probably an infectious agent or an environmental toxin. Given the separate nature of the two types of clustering, exposure to more than one hazard may be involved.