Search

We developed and tested an improved neural network to predict the average concentration of PM10 (particulate matter with diameter smaller than 10 μm) several hours in advance in summer in Beijing. A genetic algorithm optimization procedure for optimizing initial weights and thresholds of the neural network was also evaluated. This research was based upon the PM10 data from seven monitoring sites in Beijing urban region and meteorological observation data, which were recorded every 3 h during summer of 2002. Two neural network models were developed. Model I was built for predicting PM10 concentrations 3 h in advance while Model II for one day in advance. The predictions of both models were found to be consistent with observations. Percent errors in forecasting the numerical value were about 20%. This brings us to the conclusion that short-term fluctuations of PM10 concentrations in Beijing urban region in summer are to a large extent driven by meteorological conditions. Moreover, the predicted results of Model II were compared with the ones provided by the Models-3 Community Multiscale Air Quality (CMAQ) modeling system. The mean relative errors of both models were 0.21 and 0.26, respectively. The performance of the neural network model was similar to numerical models, when applied to short-time prediction of PM10 concentration. [ABSTRACT FROM AUTHOR]

Background. Although the clinical importance of demonstrating the presence of anti-glomerular basement membrane (anti-GBM) antibodies is well established, less is known concerning the clinical utility of measuring the levels of autoantibodies. Two conformational epitopes of anti-GBM antibodies have been defined at residues 17–31 and 127–141 of the α3(IV)NC1 domain of type IV collagen [α3(IV)NC1], which were named as EA and EB, respectively. In order to elucidate the importance of such antibodies, we studied the levels and the epitope specificities of anti-GBM antibodies in a large cohort of Chinese patients with anti-GBM disease. Methods. All patients, with anti-GBM disease and available clinical data, diagnosed at Peking University First Hospital from 1996 to 2005 were included in the present study. Recombinant chimeric proteins containing previously defined epitope regions designated as EA and EB were used to detect anti-GBM antibodies by ELISA. Results were compared and correlated with clinical data collected at the time of diagnosis, biopsy findings and outcome after 1 year of follow-up. Results. A retrospective diagnosis of anti-GBM disease was made in 147 patients. Haemoptysis was recorded for 47% of these cases while 53.5% cases had oliguria or anuria at the time of diagnosis. Among these patients, the levels of anti-GBM antibodies correlated with serum creatinine at diagnosis (P < 0.05 for anti EA, EB and α3(IV)NC1). Oliguric patients had higher levels of autoantibodies than non-oliguric patients, however, the difference being statistically significant only for EB (P < 0.05). Renal biopsies were performed in 66 patients, and it was found that 50 (75.8%) had cresent formation in >85% of the glomeruli. There was a correlation between the percentage of crescents and levels of antibodies, but it was significant only for anti-EA antibodies (P < 0.05). Clinical data regarding the follow-up were available for 102 patients; at the end of 1 year, 88 (86.3%) were either dead or dialysis dependent. The absorbance values of anti-GBM antibodies against both EA and EB were also associated with the subsequent development, death or terminal renal insufficiency (P < 0.05). Conclusion. In this study, patients with high levels of circulating antibodies against the specific epitopes EA and EB had a more severe renal disease at diagnosis as well as a worse prognosis. [ABSTRACT FROM AUTHOR]