Assessment of Daily Personal PM2.5 Exposure Level According to Four Major Activities among Children

Explainable geospatial-artificial intelligence models for the estimation of PM2.5 concentration variation during commuting rush hours in Taiwan

PM2.5 concentrations are higher during rush hours at background stations compared to the average concentration across these stations. Few studies have investigated PM2.5 concentration and its spatial distribution during rush hours using machine learning models. This study employs a geospatial-artificial intelligence (Geo-AI) prediction model to estimate the spatial and temporal variations of PM2.5 concentrations during morning and dusk rush hours in Taiwan. Mean hourly PM2.5 measurements were collected from 2006 to 2020, and aggregated into morning (7 a.m.-9 a.m.) and dusk (4 p.m.-6 p.m.) rush-hour mean concentrations. The Geo-AI prediction model was generated by integrating kriging interpolation, land-use regression, machine learning, and a stacking ensemble approach. A forward stepwise variable selection method based on the SHapley Additive exPlanations (SHAP) index was used to identify the most influential variables. The performance of the Geo-AI models for morning and dusk rush hours had accuracy scores of 0.95 and 0.93, respectively and these results were validated, indicating robust model performance. Spatially, PM2.5 concentrations were higher in southwestern Taiwan for morning rush hours, and suburban areas for dusk rush hours. Key predictors included kriged PM2.5 values, SO2 concentrations, forest density, and the distance to incinerators for both morning and dusk rush hours. These PM2.5 estimates for morning and dusk rush hours can support the development of alternative commuting routes with lower concentrations.

Personal exposure to PM2.5 in different microenvironments and activities for retired adults in two megacities, China

Microenvironmental concentrations and time-activity patterns influence personal exposure to fine particulate matter (PM_2.5). However, the variations and contributions of PM_2.5 exposures from various microenvironments (MEs) and activities remain unclear. In this study, gravimetrically corrected real-time personal PM_2.5 measurements were collected during routine activities in different MEs from 66 non-smoking retired adults. Exposure data were collected for five consecutive days over two seasons in Nanjing (NJ) and Beijing (BJ), China. Measured PM_2.5 concentrations varied substantially both between and within different MEs and activities. The highest average concentrations were observed in restaurants (NJ: mean 192 μg/m³, SD 242 μg/m³; BJ: mean 91 μg/m³, SD 79 μg/m³) and were associated with sources such as passive smoking and cooking emissions. Overall, PM_2.5 concentrations in different MEs and activities were moderately to highly correlated with outdoor PM_2.5 concentrations (Spearman's r = 0.51-0.97) except in restaurants and during passive smoking. The at-home ME contributed approximately 85 % of the total PM_2.5 exposure, corresponding to the participants spending about 87 % of their time there. The majority of household exposures occurred during sleeping, cooking, and other home-based activities. Transportation accounted for <5 % of total exposure. Our results indicate that improving indoor air quality, especially residential indoors, is important to reduce personal exposure to PM_2.5.

Predicting Health Risks of Adult Asthmatics Susceptible to Indoor Air Quality Using Improved Logistic and Quantile Regression Models

The increasing global patterns for asthma disease and its associated fiscal burden to healthcare systems demand a change to healthcare processes and the way asthma risks are managed. Patient-centered health care systems equipped with advanced sensing technologies can empower patients to participate actively in their health risk control, which results in improving health outcomes. Despite having data analytics gradually emerging in health care, the path to well established and successful data driven health care services exhibit some limitations. Low accuracy of existing predictive models causes misclassification and needs improvement. In addition, lack of guidance and explanation of the reasons of a prediction leads to unsuccessful interventions. This paper proposes a modeling framework for an asthma risk management system in which the contributions are three fold: First, the framework uses a deep learning technique to improve the performance of logistic regression classification models. Second, it implements a variable sliding window method considering spatio-temporal properties of the data, which improves the quality of quantile regression models. Lastly, it provides a guidance on how to use the outcomes of the two predictive models in practice. To promote the application of predictive modeling, we present a use case that illustrates the life cycle of the proposed framework. The performance of our proposed framework was extensively evaluated using real datasets in which results showed improvement in the model classification accuracy, approximately 11.5–18.4% in the improved logistic regression classification model and confirmed low relative errors ranging from 0.018 to 0.160 in quantile regression model.

Children's Particulate Matter Exposure Characterization as Part of the New Hampshire Birth Cohort Study

As part of the New Hampshire Birth Cohort Study, children 3 to 5 years of age participated in a personal PM_2.5 exposure study. This paper characterizes the personal PM_2.5 exposure and protocol compliance measured with a wearable sensor. The MicroPEM™ collected personal continuous and integrated measures of PM_2.5 exposure and compliance data on 272 children. PM_2.5, black carbon (BC), and brown carbon tobacco smoke (BrC-ETS) exposure was measured from the filters. We performed a multivariate analysis of woodstove presence and other factors that influenced PM_2.5, BC, and BrC exposures. We collected valid exposure data from 258 of the 272 participants (95%). Children wore the MicroPEM for an average of 46% of the 72-h period, and over 80% for a 2-day, 1-night period (with sleep hours counted as non-compliance for this study). Elevated PM_2.5 exposures occurred in the morning, evening, and overnight. Median PM_2.5, BC, and BrC-ETS concentrations were 8.1 μg/m³, 3.6 μg/m³, and 2.4 μg/m³. The combined BC and BrC-ETS mass comprised 72% of the PM_2.5. Woodstove presence, hours used per day, and the primary heating source were associated with the children’s PM_2.5 exposure and air filters were associated with reduced PM_2.5 concentrations. Our findings suggest that woodstove smoke contributed significantly to this cohort’s PM_2.5 exposure. The high sample validity and compliance rate demonstrated that the MicroPEM can be worn by young children in epidemiologic studies to measure their PM_2.5 exposure, inform interventions to reduce the exposures, and improve children’s health.

Indoor particulate matter and blood heavy metals in housewives: A repeated measured study

BACKGROUND

Particulate matter (PM) less than 2.5 μm in diameter and 10 μm (PM₁₀) contains heavy metals, but whether exposure to PM is significantly associated with the burden of heavy metal exposure in the population is unknown. We investigated the association between exposure to PM and blood concentrations of lead (Pb), cadmium (Cd), and mercury (Hg) in Korean housewives.

MATERIALS & METHODS

From July 2017 to January 2020, we recruited 115 housewives in Ulsan, Republic of Korea. After excluding participants with missing information, we finally included 88 Korean housewives in our study. We measured the concentrations of indoor PM using a gravimetric method 24 h before blood sampling and the concentrations of Cd, Pb, and Hg in blood, twice at a 1-year interval. We used a linear mixed effect model to estimate the associations between indoor PM and blood heavy metals.

RESULTS

Exposure to PM₁₀ was significantly associated with blood concentrations of Cd among Korean housewives. A 10 μg/m³ increase of PM₁₀ the previous day was associated with a 2.8% (95% confidence interval (CI) = 1.1%, 4.6%) and a 1.5% (95% CI = -0.1%, 3.1%) increase in blood concentrations of Cd and Pb in the linear mixed effect model, respectively.

CONCLUSION

There was a significant association between indoor PM exposure and blood Cd concentrations among Korean housewives. This result suggests that the body burden of heavy metals is significantly associated with air pollution.

Association between Peak Expiratory Flow Rate and Exposure Level to Indoor PM2.5 in Asthmatic Children, Using Data from the Escort Intervention Study

Various studies have indicated that particulate matter <2.5 μm (PM2.5) could cause adverse health effects on pulmonary functions in susceptible groups, especially asthmatic children. Although the impact of ambient PM2.5 on children’s lower respiratory health has been well-established, information regarding the associations between indoor PM2.5 levels and respiratory symptoms in asthmatic children is relatively limited. This randomized, crossover intervention study was conducted among 26 asthmatic children’s homes located in Incheon metropolitan city, Korea. We aimed to evaluate the effects of indoor PM2.5 on children’s peak expiratory flow rate (PEFR), with a daily intervention of air purifiers with filter on, compared with those groups with filter off. Children aged between 6–12 years diagnosed with asthma were enrolled and randomly allocated into two groups. During a crossover intervention period of seven weeks, we observed that, in the filter-on group, indoor PM2.5 levels significantly decreased by up to 43%. (p < 0.001). We also found that the daily or weekly unit (1 μg/m³) increase in indoor PM2.5 levels could significantly decrease PEFR by 0.2% (95% confidence interval (CI) = 0.1 to 0.5) or PEFR by 1.2% (95% CI = 0.1 to 2.7) in asthmatic children, respectively. The use of in-home air filtration could be considered as an intervention strategy for indoor air quality control in asthmatic children’s homes.

Machine Learning-Based Activity Pattern Classification Using Personal PM2.5 Exposure Information

The activity pattern is a significant factor in identifying hotspots of personal exposure to air pollutants, such as PM_2.5. However, the recording process of an activity pattern can be annoying to study participants, because they are often asked to bring a diary or a tracking recorder to write or validate their activity patterns when they change their activity profiles. Furthermore, the accuracy of the records of activity patterns can be lower, because people can mistakenly record them. Thus, this paper proposes an idea to overcome these problems and make the whole data-collection process easier and more reliable. Our idea was based on transforming training data using the statistical properties of the children’s personal exposure level to PM_2.5, temperature, and relative humidity and applying the properties to a decision tree algorithm for classification of activity patterns. From our final machine-learning modeling processes, we observed that the accuracy for activity-pattern classification was more than 90% in both the training and test data. We believe that our methodology can be used effectively in data-collection tasks and alleviate the annoyance that study participants may feel.

Indoor and outdoor PM2.5 exposure, and anxiety among schoolchildren in Korea: a panel study

This panel study aimed to evaluate the associations between short-term exposure to indoor and outdoor PM_2.5 and anxiety in schoolchildren. During 3 waves in March, July, and November 2018 with 7 days per wave, 52 children aged 10 years were recruited from two schools in a city in Korea. To assess outdoor exposure, we used PM_2.5 concentration measures for every hour at the national measurement station (NMS) closest to the two participating schools. To assess indoor exposure, we measured PM_2.5 concentration at the children's homes and in classrooms, based on 30-min average. Based on time-activity logs, personal average daily exposure values were calculated for each participant, according to exposure values assessed at 30-min intervals by location. Children's anxiety was assessed via the Korean version of the State Anxiety Inventory for children every day during each wave. Linear mixed effects model was conducted to analyze the association between PM_2.5 exposure and anxiety using repeated measurements. Personal exposure to PM_2.5 by time-activity log was the highest in March and at home. A low correlation coefficient was observed between PM_2.5 concentrations at home and at the NMS (ρ = 0.36, p < 0.0001) whereas a high correlation coefficient was observed between PM_2.5 concentrations in classrooms and at the NMS (ρ = 0.64, p < 0.0001). There was no association between PM_2.5 exposure and anxiety in children based on the analysis of repeated measurements during the study period. Since previous studies reported controversial results, long-term follow-up studies are needed in various regions to further investigate the associations between PM_2.5 exposure and children's mental health.