LaSVM-based big data learning system for dynamic prediction of air pollution in Tehran.

Due to critical impacts of air pollution, prediction and monitoring of air quality in urban areas are important tasks. However, because of the dynamic nature and high spatio-temporal variability, prediction of the air pollutant concentrations is a complex spatio-temporal problem. Distribution of pollutant concentration is influenced by various factors such as the historical pollution data and weather conditions. Conventional methods such as the support vector machine (SVM) or artificial neural networks (ANN) show some deficiencies when huge amount of streaming data have to be analyzed for urban air pollution prediction. In order to overcome the limitations of the conventional methods and improve the performance of urban air pollution prediction in Tehran, a spatio-temporal system is designed using a LaSVM-based online algorithm. Pollutant concentration and meteorological data along with geographical parameters are continually fed to the developed online forecasting system. Performance of the system is evaluated by comparing the prediction results of the Air Quality Index (AQI) with those of a traditional SVM algorithm. Results show an outstanding increase of speed by the online algorithm while preserving the accuracy of the SVM classifier. Comparison of the hourly predictions for next coming 24 h, with those of the measured pollution data in Tehran pollution monitoring stations shows an overall accuracy of 0.71, root mean square error of 0.54 and coefficient of determination of 0.81. These results are indicators of the practical usefulness of the online algorithm for real-time spatial and temporal prediction of the urban air quality.

Circulating fibrinogen is a prognostic and predictive biomarker in malignant pleural mesothelioma.

BACKGROUND: To investigate the clinical utility of pretreatment plasma fibrinogen levels in malignant pleural mesothelioma (MPM) patients. METHODS: A retrospective multicenter study was performed in histologically proven MPM patients. All fibrinogen levels were measured at the time of diagnosis and clinical data were retrospectively collected after approval of the corresponding ethics committees. RESULTS: In total, 176 MPM patients (mean age: 63.5 years ± 10.4 years, 38 females and 138 males) were analysed. Most patients (n=154, 87.5%) had elevated (≥ 390 mg dl(-1)) plasma fibrinogen levels. When patients were grouped by median fibrinogen, patients with low level (≤ 627 mg dl(-1)) had significantly longer overall survival (OS) (19.1 months, confidence interval (CI) 14.5-23.7 months) when compared with those with high level (OS 8.5; CI 6.2-10.7 months). In multivariate survival analyses, fibrinogen was found to be an independent prognostic factor (hazard ratio 1.81, CI 1.23-2.65). Most interestingly, fibrinogen (cutoff 75th percentile per 750 mg dl(-1)) proved to be a predictive biomarker indicating treatment benefit achieved by surgery within multimodality therapy (interaction term: P=0.034). Accordingly, only patients below the 75th percentile benefit from surgery within multimodality therapy (31.3 vs 5.3 months OS). CONCLUSIONS: Fibrinogen is a novel independent prognostic biomarker in MPM. Most importantly, fibrinogen predicted treatment benefit achieved by surgery within multimodality therapy.

Geographic information system-based analysis of the spatial and spatio-temporal distribution of zoonotic cutaneous leishmaniasis in Golestan Province, north-east of Iran.

Zoonotic cutaneous leishmaniasis (ZCL), a vector-borne disease, poses serious psychological as well as social and economic burden to many rural areas of Iran. The main objectives of this study were to analyse yearly spatial distribution and the possible spatial and spatio-temporal clusters of the disease to better understand spatio-temporal epidemiological aspects of ZCL in rural areas of an endemic province, located in north-east of Iran. Cross-sectional survey was performed on 2983 recorded cases during the period of 2010-2012 at village level throughout the study area. Global clustering methods including the average nearest-neighbour distance, Moran's I, general G indices and Ripley's K-function were applied to investigate the annual spatial distribution of the existing point patterns. Presence of spatial and spatio-temporal clusters was investigated using the spatial and space-time scan statistics. For each year, semivariogram analysis and all global clustering methods indicated meaningful persistent spatial autocorrelation and highly clustered distribution of ZCL, respectively. Eight significant spatial clusters, mainly located in north and northeast of the province, and one space-time cluster, observed in northern part of the province and during the period of September 2010-November 2010, were detected. Comparison of the location of ZCL clusters with environmental conditions of the study area showed that 97.8% of cases in clusters were located at low altitudes below 725 m above sea level with predominantly arid and semi-arid climates and poor socio-economic conditions. The identified clusters highlight high-risk areas requiring special plans and resources for more close monitoring and control of the disease.