Space-time Cluster Analysis Research Articles

Cluster studies in multiple sclerosis.

The word cluster is frequently used in epidemiologic studies of multiple sclerosis (MS), and various forms of cluster studies are potentially powerful tools in the search for clues to the etiology of a disease. The basis for all epidemiologic studies is deviations from a completely random distribution of the disease, and any departure from the random distribution of cases either in space, in time, or along any other axis might be defined as a cluster of cases. A review of the literature shows that such a loose definition of a cluster study has been used. Sixty-one of the 1,181 articles listed in Medline during the period 1966 to 1996 under multiple sclerosis and epidemiology were listed with the additional key word cluster or clustering. We will restrict this discussion to two types of analysis, which are most frequently referred to as cluster analysis. The most common cluster studies are those attempting to interpret an apparent excess of cases within a small geographic area. This is often referred to as post hoc cluster analysis since such clusters in general are not defined by statistical analysis, but are brought to the attention of the epidemiologist or neurologist by local physicians, patients, the mass media, or others. A second type of cluster analysis is the space-time cluster analysis . This is used to test an infectious etiology more formally. Post hoc cluster analysis. The intuitive definition of a cluster of cases is an excess number of new cases of the disease within a small area and over a short period. The rationale for studying such a cluster of cases is that if the outbreak of the disease is caused by an environmental factor, one might assume that the population in such an area is more exposed to the putative agent than the general …

Childhood cancers: space-time distribution in Britain.

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. 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. England, Scotland, and Wales. A national collection of 22,360 children aged 0-15 years with fatal cancers and leukaemias in the period 1953 to 1980. 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. 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.

Clusters of acute appendicitis: further evidence for an infectious aetiology.

The aetiology of appendicitis, the commonest cause of acute abdomen, is unknown. Infection has been proposed but the evidence has been unconvincing. The purpose of the present study was to investigate if temporo-spatial clustering and outbreaks, characteristics of infectious diseases, could be found in appendicitis cases in a defined Swedish population. Temporo-spatial clustering among 1155 cases from three districts of Jönköping County in 1984-1990 was identified by Knox space-time cluster analysis. Outbreaks were identified by retrospective study of temporal variations in 3590 consecutive cases of acute appendicitis from the city of Jönköping in 1969-1990. Space-time clustering was found among patients with operations less than 60 days apart (observed/expected [O/E]-ratio 1.46, P = 0.016). Subset analysis revealed clustering to be commonest among patients from the same households (O/E-ratio 6.52, P = 0.012), among patients younger than 15 years (O/E-ratio 3.61, P = 0.004) and among females (O/E-ratio 2.28, P = 0.004). Three outbreaks with a significantly increased number of cases were observed during the 22-year study period (O/E-ratio 1.6-2.2, P = 0.001-0.049). The finding of temporo-spatial interaction and outbreaks among appendicitis cases supports the concept that appendicitis may be caused by infectious agents.

Space-time clustering of Burkitt's lymphoma in East Africa: analysis of recent data and a new look at old data.

Forty cases of Burkitts' lymphoma (BL) in North Mara, Tanzania, with onset between 1971 and 1977, were analysed for evidence of space-time clustering. Previous analyses in East Africa had produced conflicting results. The Knox method used in those analyses dichotomizes the space and time scales and does not take into account the degree of closeness. The Mantel method, a generalization of Knox's, does permit closeness between pairs of cases to enter into computations. To see whether this method could clarify matters, previously reported data sets from West Nile, Uganda and North Mara were reanalysed. Unexplained differences were found between West Nile and North Mara with respect to age, sex and temporal distributions of BL, and between the eastern and western parts of North Mara with respect to incidence. In West Nile between 1961 and 1965, there was clustering. All of the Mantel analyses and a few of the Knox analyses were highly significant (p less than 0.0025). Since 1966, evidence of clustering is weak. In North Mara, there was no statistical evidence of space-time clustering between 1971 and 1977, as there was none between 1964 and 1970. The conflicting results in East Africa are compatible with a model involving several factors which "move about", or with a single factor which is sporadic in some areas but constant in others. Alternatively, artifactual biases or coincidence may have created or wiped out the appearance of clustering. Results of space-time clustering analyses permit little discrimination between infectious and non-infectious etiologic hypotheses. Either one type or both may be operating.