Prediction of atmospheric PM2.5 level by machine learning techniques in Isfahan, Iran.

With increasing levels of air pollution, air quality prediction has attracted more attention. Mathematical models are being developed by researchers to achieve precise predictions. Monitoring and prediction of atmospheric PM2.5 levels, as a predominant pollutant, is essential in emission mitigation programs. In this study, meteorological datasets from 9 years in Isfahan city, a large metropolis of Iran, were applied to predict the PM2.5 levels, using four machine learning algorithms including Artificial Neural |Networks (ANNs), K-Nearest-Neighbors (KNN), Support Vector |Machines (SVMs) and ensembles of classification trees Random Forest (RF). The data from 7 air quality monitoring stations located in Isfahan City were taken into consideration. The Confusion Matrix and Cross-Entropy Loss were used to analyze the performance of classification models. Several parameters, including sensitivity, specificity, accuracy, F1 score, precision, and the area under the curve (AUC), are computed to assess model performance. Finally, by introducing the predicted data for 2020 into ArcGIS software and using the IDW (Inverse Distance Weighting) method, interpolation was conducted for the area of Isfahan city and the pollution map was illustrated for each month of the year. The results showed that, based on the accuracy percentage, the ANN model has a better performance (90.1%) in predicting PM2.5 grades compared to the other models for the applied meteorological dataset, followed by RF (86.1%), SVM (84.6%) and KNN (82.2%) models, respectively. Therefore, ANN modelling provides a feasible procedure for the managerial planning of air pollution control.

Maternal exposure to benzophenone derivatives and their impacts on offspring's birth outcomes in a Middle Eastern population.

Widespread use of benzophenones (BPs), a group of environmental phenolic compounds, is suspected of interfering with human health. The association of prenatal exposure to benzophenone derivatives with birth outcomes including birth weight and length, head, arm and thoracic circumference, abnormalities, corpulence index and anterior fontanelle diameter (AFD) was investigated. Mother-infant pairs of 166 within PERSIAN cohort population in Isfahan, Iran, in the 1st and 3rd trimesters of pregnancy were assessed. Four common benzophenone metabolites including 2,4-dihydroxy benzophenone (BP-1), 2-hydroxy-4-methoxy benzophenone (BP-3), 4-hydroxy benzophenone (4-OH-BP) and 2,2'-dihydroxy-4-methoxy benzophenone (BP-8) were measured in maternal urine samples. The median concentration of 4-OH-BP, BP-3, BP-1 and BP-8 were 3.15, 16.98, 9.95 and 1.04 µg/g Cr, respectively. In the 1st trimester, 4-OH-BP showed a significant correlation with AFD in total infants, decreasing 0.034 cm AFD per a log unit increase of 4-OH-BP. Within the male neonates, 4-OH-BP in the 1st and BP-8 in the 3rd trimester were significantly associated with head circumference and AFD increase, respectively. Among female neonates in the 3rd trimester, increasing 4-OH-BP and BP-3 concentration was correlated with a decrease in birth weight and AFD, respectively. This study demonstrated that all the target BP derivatives can influence normal fetal growth at any age of the pregnancy, nevertheless, to support these findings further studies are needed in a large and different group population.

Modeling and optimization approach for phytoremediation of formaldehyde from polluted indoor air by Nephrolepis obliterata plant.

This study aimed to model the removal of formaldehyde as an indoor air pollutant by Nephrolepis obliterata (R.Br.) J.Sm. plant using response surface methodology (RSM) and artificial neural network (ANN) models, and optimization of the models by particle swarm optimization algorithm (PSO). The data obtained in pilot-scale experiments under a controlled environment were used in this study. The effects of parameters on the removal efficiency such as formaldehyde concentration, relative humidity, light intensity, and leaf surface area were empirically investigated and considered as model parameters. The results of the RSM model, with power transformation, were in meaningful compromise with the experiments. A multilayer perceptron (MLP) neural network was also designed, and the mean of squared error (MSE), mean absolute error (MAE), and R2 were used to evaluate the network. Several training algorithms were assessed and the best one, the Levenberg Marquardt (LM), was selected. The PSO algorithm proved that the highest removal efficiency of formaldehyde was obtained in the presence of light, maximum leaf surface area and relative humidity, and at the lowest inlet concentration. The empirical system breakthrough occurred at 15 mg/m3 of formaldehyde, and the maximum elimination capacity was about 0.96 mg per m2 of leaves. The findings indicated that the ANN model predicted the removal efficiency more accurately compared to the RSM model.

The association of prenatal exposure to benzophenones with gestational age and offspring size at birth.

In recent decades, emerging environmental pollutants such as endocrine-disrupting chemicals (EDCs) have become a particular concern. This study examined the association of maternal exposure to benzophenones as one of the EDCs with gestational age and evaluated their effects on birth outcomes including birth weight, birth length, head circumference, and Ponderal Index. We assessed 166 pregnant mothers of the PERSIAN cohort population of Isfahan, Iran, in the 1st and 3rd trimesters of pregnancy and their infants at birth. Four common benzophenones (BPs) including 2,4-dihydroxy benzophenone (BP-1), 2-hydroxy-4-methoxy benzophenone (BP-3), 4-hydroxy benzophenone (4-OH-BP), and 2,2'-dihydroxy-4-methoxy benzophenone (BP-8) were measured in maternal urine samples. The median urinary concentrations of 4-OH-BP, BP-3, BP-1, and BP-8 in the 1st trimester were 6.62, 7.5, 4.39, and 1.32 µg/g creatinine and those in the 3rd trimester were 3.15, 16.98, 9.95, and 1.04 µg/g creatinine, respectively. BP-3 was the predominant metabolite in both trimesters. There was a significant correlation between BP-3, BP-1, and 4-OH-BP levels (p < 0.05) but not BP-8. BP-1 showed a significant positive association with gestational age (GA) in all infants in the 1st trimester, but a negative association was observed between BP-3 and BP-1 levels and GA in girls. Classification of infants' birth weight for different GAs represented that the majority of them were appropriate for GA. However, boys' weights were heavier than girls. Also, birth outcomes of preterm (< 37 weeks) infants were noticeably lower than term infants (37-42 weeks). This study demonstrated that benzophenone derivatives especially BP-3 can affect the duration of pregnancy and consequently fetal growth in the early and late stages of pregnancy. This is more pronounced in girls; however, more investigations in a different population are needed to prove the results. Therefore, the application of these compounds as a UV protector requires precise regulation to reduce exposure, especially in pregnant women.

Indoor radon measurement in buildings of a university campus in central Iran and estimation of its effective dose and health risk assessment.

Indoor radon is a serious health concern and contributes about 10% of deaths from lung cancer in the USA and Europe. In this study, radon and thoron levels of 20 multi-floor buildings on the campus of Isfahan University of Medical Sciences were measured in cold and hot seasons of a year. SARAD- RTM1688 radon and thoron monitor was used for measurement. The annual effective dose of radon exposure was also estimated for residences on the campus. The results showed that radon concentration was below the WHO guideline (100 Bq m- 3) in most of the buildings. The ranges of radon were from 3 ± 10% to 322 ± 15% Bq m- 3 in winter and from below the detectable level to 145 ± 8% Bq m- 3 in summer. Mostly, the radon concentration in the basement or ground floors was higher than upper floors, however, exceptions were observed in some locations. For thoron, no special trends were observed, and in the majority of buildings, its concentration was below the detectable level. However, in a few locations besides radon, thoron was also measured at a high level during both seasons. The average annual effective dose via radon exposure was estimated to be 0.261 ± 0.339 mSv y- 1. The mean excess lung cancer risk (ELCR) was estimated to be 0.10%. It was concluded that indoor air ventilation, buildings' flooring and construction materials, along with the geological structure of the ground could be the factors influencing the radon concentration inside the buildings. Thus, some applicable radon prevention and mitigation techniques were suggested.

Artificial neural network and logistic regression modelling to characterize COVID-19 infected patients in local areas of Iran.

BACKGROUND: COVID-19 is an infectious disease that started spreading globally at the end of 2019. Due to differences in patient characteristics and symptoms in different regions, in this research, a comparative study was performed on COVID-19 patients in 6 provinces of Iran. Also, multilayer perceptron (MLP) neural network and Logistic Regression (LR) models were applied for the diagnosis of COVID-19. METHODS: A total of 1043 patients with suspected COVID-19 infection in Iran participated in this study. 29 characteristics, symptoms and underlying disease were obtained from hospitalized patients. Afterwards, we compared the obtained data between confirmed cases. Furthermore, the data was applied for building the ANN and LR models to diagnosis the infected patients by COVID-19. RESULTS: In 750 confirmed patients, Common symptoms were: fever (%) >37.5 °C, cough, shortness of breath, fatigue, chills and headache. The most common underlying diseases were: hypertension, diabetes, chronic obstructive pulmonary disease and coronary heart disease. Finally, the accuracy of the ANN model to the diagnosis of COVID-19 infection was higher than the LR model. CONCLUSION: The prevalent symptoms and underlying diseases of COVID-19 patients were similar in different provinces, but the incidence of symptoms was significantly different from each other. Also, the study demonstrated that ANN and LR models have a high ability in the diagnosis of COVID-19 infection.

Modelling and Optimizing Pyrene Removal from the Soil by Phytoremediation using Response Surface Methodology, Artificial Neural Networks, and Genetic Algorithm.

This study aimed to model and optimize pyrene removal from the soil contaminated by sorghum bicolor plant using Response Surface Methodology (RSM) and Artificial Neural Network (ANN) with Genetic Algorithm (GA) approach. Here, the effects of indole acetic acid (IAA) and pseudomonas aeruginosa bacteria on increasing pyrene removal efficiency by phytoremediation process was studied. The experimental design was done using the Box-Behnken Design (BBD) technique. In the RSM model, the non-linear second-order model was in good agreement with the laboratory results. A two-layer Feed-Forward Back-Propagation Neural Network (FFBPNN) model was designed. Various training algorithms were evaluated and the Levenberg Marquardt (LM) algorithm was selected as the best one. Existence of eight neurons in the hidden layer leads to the highest R and lowest MSE and MAE. The results of the GA determined the optimum performance conditions. The results showed that using indole acetic acid and pseudomonas bacteria increased the efficiency of the sorghum plant in removing pyrene from the soil. The comparison obviously indicated that the prediction capability of the ANN model was much better than that of the RSM model.

Systematic review and meta-analysis on the association between phthalates exposure and insulin resistance.

This study aims to provide an overview of human studies on the association of exposure to phthalates and insulin resistance. We systematically searched human studies available until 15 January 2018.We conducted a literature search in Scopus, ISI Web of Science, PubMed, Google Scholar, and Cochrane Collaboration. We used the following keywords to identify relevant articles: "phthalate", "phthalate ester", "metabolic syndrome", "insulin resistance", "glucose intolerance", and "diabetes". For analyzing data, we conducted meta-analysis using the Stata software. We appraised each study to examine the sources of heterogeneity, including difference in clinical outcomes and exposure measurements. To determine the robustness and whether some of the factors have the highest impact on the results of the present meta-analysis, several sensitivity analyses were conducted. Sensitivity analysis showed that by removing studies with the highest weight and age groups, no change was observed in heterogeneity. Moreover, with excluding the study conducted in Europe, the results remained unchanged and constant. In addition, the funnel plot and Egger's tests were executed to access publication bias. Both the funnel plots and Egger's test did not show any evidence of publication bias (P = 0.31). In the random effects meta-analysis of all studies (n = 8), the pooled correlation coefficient between phthalate exposure and HOMA-IR was 0.10 (95% CI; 0.07-0.12, P < 0.001), with significant heterogeneity (P < 0.001, I2 = 85.5%). Our findings revealed positive association between exposure to phthalate metabolites and increased HOMA-IR; this association remained significant even after adjusting the analysis for multiple confounding variables.

Phytoremediation of Formaldehyde from Indoor Environment by Ornamental Plants: An Approach to Promote Occupants Health.

BACKGROUND: Formaldehyde is a common hazardous indoor air pollutant which recently raised public concerns due to its well-known carcinogenic effects on human. The aim of this study was to investigate a potted plant-soil system ability in formaldehyde removal from a poor ventilated indoor air to promote dwellers health. METHODS: For this purpose, we used one of the common interior plants from the fern species (Nephrolepis obliterata), inside a Plexiglas chamber under controlled environment. Entire plant removal efficiency and potted soil/roots contribution were determined by continuously introducing different formaldehyde vapor concentrations to the chamber (0.6-11 mg/m3) each over a 48-h period. Sampling was conducted from inlet and outlet of the chamber every morning and evening over the study period, and the average of each stage was reported. RESULTS: The results showed that the N. obliterata plant efficiently removed formaldehyde from the polluted air by 90%-100%, depending on the inlet concentrations, in a long time exposure. The contribution of the soil and roots for formaldehyde elimination was 26%. Evaluation of the plant growing characteristics showed that the fumigation did not affect the chlorophyll content, carotenoid, and average height of the plant; however, a decrease in the plant water content was observed. CONCLUSIONS: According to the results of this study, phytoremediation of volatile organic compound-contaminated indoor air by the ornamental potted plants is an effective method which can be economically applicable in buildings. The fern species tested here had high potential to improve interior environments where formaldehyde emission is a health concern.

Phytoremediation of VOCs from indoor air by ornamental potted plants: A pilot study using a palm species under the controlled environment.

Volatile organic compounds (VOCs) in indoor air have recently raised public concern due to their adverse health effects. One of hazardous VOC is Formaldehyde which can cause sensory irritation and induce nasopharyngeal cancer. The aim of this study was to investigate potted plant-soil system ability in formaldehyde removal from indoor air. We applied one of common interior plant from the palm species, Chamaedorea elegans, inside a chamber under the controlled environment. Entire plant, growing media and roots contribution in formaldehyde were evaluated by continuously introduction of different concentrations of formaldehyde into the chamber (0.66-16.4 mg m-3) each over a 48-h period. Our findings showed that the plant efficiently removed formaldehyde from polluted air by 65-100%, depending on the inlet concentrations, for a long time exposure. A maximum elimination capacity of 1.47 mg/m2. h was achieved with an inlet formaldehyde concentration of 14.6 mg m-3. The removal ratio of areal part to pot soil and roots was 2.45:1 (71%: 29%). The plants could remove more formaldehyde in light rather than dark environment. Concentrations up to 16.4 mg m-3 were not high enough to affect the plants growth. However, a trivial decrease in chlorophyll content, carotenoid and water content of the treated plants was observed compared to the control plants. Thus, the palm species tested here showed high tolerance and good potential of formaldehyde removal from interior environments. Therefore, phytoremediation of VOCs from indoor air by the ornamental potted plants is an effective method which can be economically applicable in homes and offices.

Environmental and biological monitoring of exposures to VOCs in a petrochemical complex in Iran.

Exposure to volatile organic compounds (VOCs) can cause cancers in human. This study aimed to measure the concentration of four VOCs including benzene, styrene, ethylbenzene, and phenol in ambient air of a petrochemical complex in Iran. Also, their urinary metabolites including phenol, mandelic acid (MA), and phenylglyoxylic acid (PGA) in the workers were monitored. Urine samples were collected before and after the 8-h workshift according to the NIOSH methods. They were analyzed by a gas chromatograph coupled with a flame ionization detector (GC-FID). High levels of the ambient VOCs were detected in the units of recovery and olefin. The levels of ethylbenzene and phenol were less than the guidelines suggested by NIOSH and ACGIH. However, in some cases, the amounts of benzene and styrene were higher than the guidelines. Excellent positive correlations were observed between VOCs exposure and their urinary metabolites (r 2 > 0.90), except for benzene (r 2 = 0.26). Our finding verified that urinary biomarkers can be applied as bioindicators for ambient exposure to VOCs. There is a risk of exposure to high levels of the pollutants in some of the sites, and it is necessary to adopt some preventive measures to reduce health risk.

Spatio-seasonal variation of airborne asbestos concentration in urban areas of Shiraz, Iran.

Background Asbestos fiber is mainly released from friction product in brakes and clutch linings and from reinforcing agent in the asbestos-cement industry. It leads to serious health problem such as mesothelioma and lung cancer. The objectives of this study were to monitor the levels of asbestos fibers in ambient air of Shiraz, Iran during 2014, and to draw its GIS distribution map for the city. Methods Samples were collected by mixed cellulose ester filters mounted on an open-faced filter holder using a SKC sampling pump. Fiber counting was conducted using both phase contrast microscopy (PCM) method to determine total fibers, and scanning electron microscopy (SEM) method to identify non-asbestos from asbestos fibers. Results The average concentrations of asbestos fibers in ambient air of the city were 1.11 ± 0.25 PCM f/l and 12.21 ± 2.52 SEM f/l. The highest concentration of asbestos fibers was measured in Valiasr square amounting 1.96 ± 0.34 PCM f/l and 16.87  ± 2.14 SEM f/l. Conclusions The average of asbestos fibers in all sampling points was higher than the WHO guideline (0.05 PCM f/l, 2.2 SEM f/l). This may be attributed to the frequently occurrence of heavy traffic, the existence of relevant industries in and around the city, and the topographic characteristics of the city. Thus, product substitution, traffic smoothing and industrial sites relocating are suggested to eliminate the asbestos fibers emission.