An approximate CUSUM procedure for surveillance of health events

The CUSUM method is frequently used by epidemiologists for detecting a shift in the incidence of rare health events. An exact solution for a Poisson process has been proposed by other works, but potential applications have been limited by the fact that the size, the structure of the at-risk population and the baseline rate may not be constant during the period of surveillance. Furthermore, for practical use tables of critical values are available only for some expected values and in any case less then 9. This paper proposes an approximate CUSUM procedure, based on the normal approximation to a Poisson process, which may be an efficient solution of the problems previously pointed out. Analyses of simulated and actual data sets illustrate the usefulness of the proposed procedure. An application to mortality data for respiratory diseases in a north Tuscany area, characterized by the presence of chemical plants, is showed. No shift in the mortality rate during the 1980-1989 period was detected compared with the 1970-1979 period, in contrast with the result obtained with the standard CUSUM method for a Poisson variate.