Relationship between adhesion of Escherichia coli to uro-epithelial cells and the pathogenesis of urinary infection: problems in methodology and analysis

Abstract

Escherichia coli strains isolated from patients with urinary infections were tested for their ability to adhere to human uro-epithelial cells. In any single experiment, the numbers of bacteria adhering to individual uro-epithelial cells showed great variations; some cells had hundreds of bacteria adhering to them whereas other cells had few or none. This non-Normal distribution of bacterial attachment must be taken into account when carrying out statistical analyses of the results. The wide discrepancies reported in the literature regarding bacterial adhesion to uro-epithelial cells must, in part, be related to the type of statistical analysis used. In many cases, a Normal rather than a non-Normal distribution has been assumed. We found that even when all variables were kept constant, the experiment was still not reproducible. Therefore the technique shows a high degree of both inter- and intra-experimental error. Adhesion depended on such factors as the type of fimbriae produced by the bacteria, differing viability of uro-epithelial cells and varying pH of the medium used for a particular experiment. It is concluded that the results of in-vitro experiments demonstrating adhesion of E. coli to uro-epithelial cells are difficult to relate to bacterial adhesion in vivo but better results could be obtained if more attention were paid to standardisation of methods and their analysis.