Measurements of endotoxin on ambient loaded PM filters after long-term storage

At present there exist unsolved questions, whether endotoxin measurements on PM filters show valid measurements after long-term storage of loaded PM filters. As part of the TRAPCA study we collected particles with a 50% aerodynamic cut-off diameter of 2.5 mu m (PM2.5) at 40 outdoor sites and particles less than 10 pm in size (PM 10) at a subset of these sites (N=12) in Munich. The PM filters were cut in halves and endotoxin was measured in the extract of one filter half 2-3 years after PM collection. Here we present the results of repeated endotoxin measurements, where the association between previously measured endotoxin concentrations, measurements from stored eluates, and measurements in extracts of the second filter halves were determined. No statistically significant changes were seen between our old measurements and those from the stored eluates. Additionally, no change was observed between previously measured endotoxin concentrations and those from the stored set of filter halves. We found an average increase of 5% between our old measurements and those from the stored eluates and of 19% between the old measurements and those from the stored set of filter halves. The correlations between the previously measured endotoxin concentrations and the repeated measurements from the stored eluates were high (r=0.789) for EU/m(3) PM2.5. Since endotoxin was evaluated from the same set of filter halves, it is obvious that storage over three years did not substantially effect the correlation of the endotoxin content. Regarding the outliers from previous measurements unsymmettic endotoxin spots on one out of 48 filter halves could be determined. Apart from this we conclude that the endotoxin is homogenously distributed on the filter halves and that endotoxin levels, which were repeatedly measured from filters stored over three years, could be determined validly. (c) 2006 Elsevier B.V. All rights reserved.