Asthma-prone areas modeling using a machine learning model

Novel Machine Learning Identifies 5 Asthma Phenotypes Using Cluster Analysis of Real-World Data

BACKGROUND

Asthma classification into different subphenotypes is important to guide personalized therapy and improve outcomes.

OBJECTIVES

To further explore asthma heterogeneity through determination of multiple patient groups by using novel machine learning (ML) approaches and large-scale real-world data.

METHODS

We used electronic health records of patients with asthma followed at the Cleveland Clinic between 2010 and 2021. We used k-prototype unsupervised ML to develop a clustering model where predictors were age, sex, race, body mass index, prebronchodilator and postbronchodilator spirometry measurements, and the usage of inhaled/systemic steroids. We applied elbow and silhouette plots to select the optimal number of clusters. These clusters were then evaluated through LightGBM's supervised ML approach on their cross-validated F1 score to support their distinctiveness.

RESULTS

Data from 13,498 patients with asthma with available postbronchodilator spirometry measurements were extracted to identify 5 stable clusters. Cluster 1 included a young nonsevere asthma population with normal lung function and higher frequency of acute exacerbation (0.8 /patient-year). Cluster 2 had the highest body mass index (mean ± SD, 44.44 ± 7.83 kg/m2), and the highest proportion of females (77.5%) and Blacks (28.9%). Cluster 3 comprised patients with normal lung function. Cluster 4 included patients with lower percent of predicted FEV1 of 77.03 (12.79) and poor response to bronchodilators. Cluster 5 had the lowest percent of predicted FEV1 of 68.08 (15.02), the highest postbronchodilator reversibility, and the highest proportion of severe asthma (44.9%) and blood eosinophilia (>300 cells/μL) (34.8%).

CONCLUSIONS

Using real-world data and unsupervised ML, we classified asthma into 5 clinically important subphenotypes where group-specific asthma treatment and management strategies can be designed and deployed.

Socioeconomic and environmental determinants of asthma prevalence: a cross-sectional study at the U.S. County level using geographically weighted random forests

BACKGROUND

Some studies have established associations between the prevalence of new-onset asthma and asthma exacerbation and socioeconomic and environmental determinants. However, research remains limited concerning the shape of these associations, the importance of the risk factors, and how these factors vary geographically.

OBJECTIVE

We aimed (1) to examine ecological associations between asthma prevalence and multiple socio-physical determinants in the United States; and (2) to assess geographic variations in their relative importance.

METHODS

Our study design is cross sectional based on county-level data for 2020 across the United States. We obtained self-reported asthma prevalence data of adults aged 18 years or older for each county. We applied conventional and geographically weighted random forest (GWRF) to investigate the associations between asthma prevalence and socioeconomic (e.g., poverty) and environmental determinants (e.g., air pollution and green space). To enhance the interpretability of the GWRF, we (1) assessed the shape of the associations through partial dependence plots, (2) ranked the determinants according to their global importance scores, and (3) mapped the local variable importance spatially.

RESULTS

Of the 3059 counties, the average asthma prevalence was 9.9 (standard deviation ± 0.99). The GWRF outperformed the conventional random forest. We found an indication, for example, that temperature was inversely associated with asthma prevalence, while poverty showed positive associations. The partial dependence plots showed that these associations had a non-linear shape. Ranking the socio-physical environmental factors concerning their global importance showed that smoking prevalence and depression prevalence were most relevant, while green space and limited language were of minor relevance. The local variable importance measures showed striking geographical differences.

CONCLUSION

Our findings strengthen the evidence that socio-physical environments play a role in explaining asthma prevalence, but their relevance seems to vary geographically. The results are vital for implementing future asthma prevention programs that should be tailor-made for specific areas.

EAACI guidelines on environmental science in allergic diseases and asthma - Leveraging artificial intelligence and machine learning to develop a causality model in exposomics

Allergic diseases and asthma are intrinsically linked to the environment we live in and to patterns of exposure. The integrated approach to understanding the effects of exposures on the immune system includes the ongoing collection of large-scale and complex data. This requires sophisticated methods to take full advantage of what this data can offer. Here we discuss the progress and further promise of applying artificial intelligence and machine-learning approaches to help unlock the power of complex environmental data sets toward providing causality models of exposure and intervention. We discuss a range of relevant machine-learning paradigms and models including the way such models are trained and validated together with examples of machine learning applied to allergic disease in the context of specific environmental exposures as well as attempts to tie these environmental data streams to the full representative exposome. We also discuss the promise of artificial intelligence in personalized medicine and the methodological approaches to healthcare with the final AI to improve public health.

Spatial distribution of hospital admissions for asthma in the central area of Asturias, Northern Spain

BACKGROUND

Asturias is one of the communities with the highest rates of hospital admission for asthma in Spain. The environmental pollution or people lifestyle are some of the factors that contribute to the appearance or aggravation of this illness. The aim of this study was to show the spatial distribution of asthma admissions risks in the central municipalities of Asturias and to analyze the observed spatial patterns.

METHODS

Urgent hospital admissions for asthma and status asthmaticus occurred between 2016 to 2018 on the public hospitals of the central area of Asturias were used. Population data were assigned in 5 age groups. Standardised admission ratio (SAR), smoothed relative risk (SRR) and posterior risk probability (PP) were calculated for each census tract (CT). A spatial trend analysis was run, a spatial autocorrelation index (Morans I) was calculated and a cluster and outlier analysis (Anselin Local Morans I) was finally performed in order to analyze spatial clusters.

RESULTS

The total number of hospital urgent asthma admissions during the study period was 2324, 1475 (63.46%) men and 849 (36.56%) women. The municipalities with the highest values of SRR and PP were located on the northwest area: Avilés, Gozón, Carreño, Corvera de Asturias, Castrillón and Illas. A high risk cluster was found for the municipalities of Avilés, Gozón y Corvera de Asturias.

CONCLUSIONS

The spatial analysis showed high risk of hospitalization for asthma on the municipalities of the northwest area of the study, which highlight the existence of spatial inequalities on the distribution of urgent hospital admissions.

[Geographical variation of asthma prevalence among Mexican children during the COVID-19 pandemic]

OBJECTIVE

The purpose of this study was to analyze the geographic variation in the prevalence of asthma in children, according to their place of residence in Mexico.

METHODS

A cross-sectional analysis of the epidemiological surveillance system dataset for respiratory diseases in Mexico carried on. From 27 February to 5 November 2020, a total of 1,048,576 subjects were screened for SARS-CoV2 infection, of which 35,899 were children under 18 years of age. The strength of the association was estimated by odds ratio (OR).

RESULTS

Of 1,048,576 patients who attended for SARS-CoV2 infection detection, 35,899 corresponded to pediatric patients who met the study criteria. The estimated national prevalence of asthma was 3.9% (95% CI: 3.7-4.1%). The nationwide prevalence of asthma was 3.9% (95% CI: 3.7% - 4.1%); the minimum was 2.8% (Southeast region) and the maximum 6.8% (Southeast region). Compared to the South-West Region that presented the minimum prevalence at the national level, the Northwest (OR = 2.41) and Southeast (OR = 1.33) regions showed the highest risk of asthma in pediatric population.

CONCLUSIONS

The prevalence of asthma in children differed markedly among the different regions of Mexico; two regions, Northwest and Southeast, stood out. This study puts into context the role of the environment on the prevalence of asthma in children.

Geographic Medical Overview of Noncommunicable Diseases (Cardiovascular Diseases and Diabetes) in the Territory of the AP Vojvodina (Northern Serbia)

The objective of this study was a geographic medical analysis of noncommunicable diseases (cardiovascular diseases from 2010 to 2020 and diabetes from 2010 to 2019) in the AP Vojvodina (northern Serbia) in order to identify the most and least burdened counties as well as to present trends in the mentioned diseases. The Mann-Kendall trend test, a cluster analysis, and Getis-Ord Gi* method for hot spot analysis were applied in this analysis. Regarding acute coronary syndrome and myocardial infarction, the North Backa County had a lower mortality rate although the number of newly reported cases was above average. The largest number of new cases of unstable angina pectoris was in the North Backa, North Banat, and Middle Banat Counties, while the West Backa County was identified as a county with a higher mortality rate. The cluster analysis showed that the number of death cases from diabetes in the Srem County is significantly higher than that in the other counties. Likewise, the West Backa County had a high number of new diabetes patients, but also a much lower mortality rate. Chronic noncommunicable diseases are predominant in newly diagnosed incidences and death cases in the AP Vojvodina. Studies of this kind promote public health and healthcare systems in the researched area and in the Republic of Serbia, as well as in other countries.

Novelty in Public Health and Epidemiology Informatics

OBJECTIVES

To highlight novelty studies and current trends in Public Health and Epidemiology Informatics (PHEI).

METHODS

Similar to last year's edition, a PubMed search of 2021 scientific publications on PHEI has been conducted. The resulting references were reviewed by the two section editors. Then, 11 candidate best papers were selected from the initial 782 references. These papers were then peer-reviewed by selected external reviewers. They included at least two senior researchers, to allow the Editorial Committee of the 2022 IMIA Yearbook edition to make an informed decision for selecting the best papers of the PHEI section.

RESULTS

Among the 782 references retrieved from PubMed, two were selected as the best papers. The first best paper reports a study which performed a comprehensive comparison of traditional statistical approaches (e.g., Cox Proportional Hazards models) vs. machine learning techniques in a large, real-world dataset for predicting breast cancer survival, with a focus on explainability. The second paper describes the engineering of deep learning models to establish associations between ocular features and major hepatobiliary diseases and to advance automated screening and identification of hepatobiliary diseases from ocular images.

CONCLUSION

Overall, from this year edition, we observed that the number of studies related to PHEI has decreased. The findings of the two studies selected as best papers on the topic suggest that a significant effort is still being made by the community to compare traditional learning methods with deep learning methods. Using multimodality datasets (images, texts) could improve approaches for tackling public health issues.

Spatial autocorrelation may bias the risk estimation: An application of eigenvector spatial filtering on the risk of air pollutant on asthma

Air pollutants are major risk factors for respiratory diseases, particularly asthma, socially and spatially correlated. Many existing environment-asthma-related studies, however, have evaluated the impact of crude trends at the largest district level, which accounts only for temporal effects and may produce biased results with spatial autocorrelation. This study aimed to investigate how the spatial autocorrelation affects the air pollution effect estimations (sulfur dioxide [SO₂], nitrogen dioxide [NO₂], carbon monoxide [CO], and particulate matter [PM₁₀]) on daily asthma emergency department (ED) visits in two metropolitan areas in Korea (Seoul Metropolitan Area [SMA] and Busan Metropolitan City, Ulsan Metropolitan City, Gyeongsangnamdo [BUG]). We applied eigenvector spatial filter (ESF) to the spatio-temporal model to remove spatial autocorrelation and distributed lag nonlinear model (DLNM) to explore nonlinear patterns between air pollutant concentration and lagged days on the three models including aggregated model (a temporal model), spatial model without ESF, and spatial model with ESF (both are spatio-temporal models). The effect of SO₂ was not statistically significant for asthma ED visits in the aggregated model for SMA (cumulative relative risks [CRR] = 0.99, confidence intervals [CI]: 0.93-1.05), while the effect was statistically significant in the spatial model with ESF (CRR = 1.10, CI: 1.08-1.12). NO₂ and CO were positively correlated to asthma ED visits in the spatial model without ESF (CRR = 0.84, CI: 0.81-0.86; 0.91, 0.89-0.94, respectively), but the spatial model with ESF showed significant risks (CRR = 1.21, CI: 1.18-1.24; 1.13, 1.11-1.16). Moreover, the spatial model with ESF successfully removed spatial autocorrelation (P-values for Moran's I 0.83-0.98) and demonstrated the highest model fit (McFadden's pseudo R² 0.42-0.43 for SMA and 0.26-0.27 for BUG) among the three models. Our findings demonstrate how ESF can be introduced into spatial correlation to remove bias and construct more reliable models.

Exposure to urban greenspace and pathways to respiratory health: An exploratory systematic review

BACKGROUND/OBJECTIVE

Urban greenspace may have a beneficial or adverse effect on respiratory health. Our objective was to perform an exploratory systematic review to synthesise the evidence and identify the potential causal pathways relating urban greenspace and respiratory health.

METHODS

We followed PRISMA guidelines on systematic reviews and searched five databases for eligible studies during 2000-2021. We incorporated a broad range of urban greenspace and respiratory health search terms, including both observational and experimental studies. Screening, data extraction, and risk of bias, assessed using the Navigation Guide criteria, were performed independently by two authors. We performed a narrative synthesis and discuss suggested pathways to respiratory health.

RESULTS

We identified 108 eligible papers (n = 104 observational, n = 4 experimental). The most common greenspace indicators were the overall greenery or vegetation (also known as greenness), green land use/land cover of physical area classes (e.g., parks, forests), and tree canopy cover. A wide range of respiratory health indicators were studied, with asthma prevalence being the most common. Two thirds (n = 195) of the associations in these studies were positive (i.e., beneficial) with health, with 31% (n = 91) statistically significant; only 9% (n = 25) of reported associations were negative (i.e., adverse) with health and statistically significant. The most consistent positive evidence was apparent for respiratory mortality. There were n = 35 (32%) 'probably low' and n = 73 (68%) 'probably high' overall ratings of bias. Hypothesised causal pathways for health benefits included lower air pollution, more physically active populations, and exposure to microbial diversity; suggested mechanisms with poorer health included exposure to pollen and other aeroallergens.

CONCLUSION

Many studies showed positive association between urban greenspace and respiratory health, especially lower respiratory mortality; this is suggestive, but not conclusive, of causal effects. Results underscore the importance of contextual factors, greenspace metric employed, and the potential bias of subtle selection factors, which should be explored further.

Environmental Pollution Analysis and Impact Study-A Case Study for the Salton Sea in California

A natural experiment conducted on the shrinking Salton Sea, a saline lake in California, showed that each one foot drop in lake elevation resulted in a 2.6% average increase in PM2.5 concentrations. The shrinking has caused the asthma rate continues to increase among children, with one in five children being sent to the emergency department, which is related to asthma. In this paper, several data-driven machine learning (ML) models are developed for forecasting air quality and dust emission to study, evaluate and predict the impacts on human health due to the shrinkage of the sea, such as the Salton Sea. The paper presents an improved long short-term memory (LSTM) model to predict the hourly air quality (O3 and CO) based on air pollutants and weather data in the previous 5 h. According to our experiment results, the model generates a very good R2 score of 0.924 and 0.835 for O3 and CO, respectively. In addition, the paper proposes an ensemble model based on random forest (RF) and gradient boosting (GBoost) algorithms for forecasting hourly PM2.5 and PM10 using the air quality and weather data in the previous 5 h. Furthermore, the paper shares our research results for PM2.5 and PM10 prediction based on the proposed ensemble ML models using satellite remote sensing data. Daily PM2.5 and PM10 concentration maps in 2018 are created to display the regional air pollution density and severity. Finally, the paper reports Artificial Intelligence (AI) based research findings of measuring air pollution impact on asthma prevalence rate of local residents in the Salton Sea region. A stacked ensemble model based on support vector regression (SVR), elastic net regression (ENR), RF and GBoost is developed for asthma prediction with a good R2 score of 0.978.

Coronavirus disease vulnerability map using a geographic information system (GIS) from 16 April to 16 May 2020

In recent months, the world has been affected by the infectious coronavirus disease and Iran is one of the most affected countries. The Iranian government's health facilities for an urgent investigation of all provinces do not exist simultaneously. There is no management tool to identify the vulnerabilities of Iranian provinces in prioritizing health services. The aim of this study was to prepare a coronavirus vulnerability map of Iranian provinces using geographic information system (GIS) to monitor the disease. For this purpose, four criteria affecting coronavirus, including population density, percentage of older people, temperature, and humidity, were prepared in the GIS. A multiscale geographically weighted regression (MGWR) model was used to determine the vulnerability of coronavirus in Iran. An adaptive neuro-fuzzy inference system (ANFIS) model was used to predict vulnerability in the next two months. Results indicated that, population density and older people have a more significant impact on coronavirus in Iran. Based on MGWR models, Tehran, Mazandaran, Gilan, and Alborz provinces were more vulnerable to coronavirus in February and March. The ANFIS model findings showed that West Azerbaijan, Zanjan, Fars, Yazd, Semnan, Sistan and Baluchistan, and Tehran provinces were more vulnerable in April and May.

Issue 1 - "Update on adverse respiratory effects of outdoor air pollution" Part 2): Outdoor air pollution and respiratory diseases: Perspectives from Angola, Brazil, Canada, Iran, Mozambique and Portugal

OBJECTIVE

To analyse the GARD perspective on the health effects of outdoor air pollution, and to synthesise the Portuguese epidemiological contribution to knowledge on its respiratory impact.

RESULTS

Ambient air pollution has deleterious respiratory effects which are more apparent in larger, densely populated and industrialised countries, such as Canada, Iran, Brazil and Portugal, but it also affects people living in low-level exposure areas. While low- and middle-income countries (LMICs), are particularly affected, evidence based on epidemiological studies from LMICs is both limited and heterogeneous. While nationally, Portugal has a relatively low level of air pollution, many major cities face with substantial air pollution problems. Time series and cross-sectional epidemiological studies have suggested increased respiratory hospital admissions, and increased risk of respiratory diseases in people who live in urban areas and are exposed to even a relatively low level of air pollution.

CONCLUSIONS

Adverse respiratory effects due to air pollution, even at low levels, have been confirmed by epidemiological studies. However, evidence from LMICs is heterogeneous and relatively limited. Furthermore, longitudinal cohort studies designed to study and quantify the link between exposure to air pollutants and respiratory diseases are needed. Worldwide, an integrated approach must involve multi-level stakeholders including governments (in Portugal, the Portuguese Ministry of Health, which hosts GARD-Portugal), academia, health professionals, scientific societies, patient associations and the community at large. Such an approach not only will garner a robust commitment, establish strong advocacy and clear objectives, and raise greater awareness, it will also support a strategy with adequate measures to be implemented to achieve better air quality and reduce the burden of chronic respiratory diseases (CRDs).

A Practical Model for the Evaluation of High School Student Performance Based on Machine Learning

The objective of this research is to develop an machine learning (ML) -based system that evaluates the performance of high school students during the semester and identify the most significant factors affecting student performance. It also specifies how the performance of models is affected when models run on data that only include the most important features. Classifiers employed for the system include random forest (RF), support vector machines (SVM), logistic regression (LR) and artificial neural network (ANN) techniques. Moreover, the Boruta algorithm was used to calculate the importance of features. The dataset includes behavioral information, individual information and the scores of students that were collected from teachers and a one-by-one survey through an online questionnaire. As a result, the effective features of the database were identified, and the least important features were eliminated from the dataset. The ANN accuracy, which was the best accuracy in the original dataset, was reduced in the decreased dataset. On the contrary, SVM performance was improved, which had the highest accuracy among other models, with 0.78. Moreover, the LR and RF models could provide the same performance in the decreased dataset. The results showed that ML models are influential for evaluating students, and stakeholders can use the identified effective factors to improve education.

Spatio-temporal modeling of PM2.5 risk mapping using three machine learning algorithms

Urban air pollution is one of the most critical issues that affect the environment, community health, economy, and management of urban areas. From a public health perspective, PM_2.5 is one of the primary air pollutants, especially in Tehran's metropolis. Owing to the different patterns of PM_2.5 in different seasons, Spatio-temporal modeling and identification of high-risk areas to reduce its effects seems necessary. The purpose of this study was Spatio-temporal modeling and preparation of PM_2.5 risk mapping using three machine learning algorithms (random forest (RF), AdaBoost, and stochastic gradient descent (SGD)) in the metropolis of Tehran, Iran. Therefore, in the first step, to prepare the dependent variable data, the PM_2.5 average was used for the four seasons of spring, summer, autumn, and winter. Then, using remote sensing (RS) and a geographic information system (GIS), independent data such as temperature, maximum temperature, minimum temperature, wind speed, rainfall, humidity, normalized difference vegetation index (NDVI), population density, street density, and distance to industrial centers were prepared as a seasonal average. To Spatio-temporal modeling using machine learning algorithms, 70% of the data were used for training and 30% for validation. The frequency ratio (FR) model was used as input to machine learning algorithms to calculate the spatial relationship between PM_2.5 and the effective parameters. Finally, Spatio-temporal modeling and PM_2.5 risk mapping were performed using three machine learning algorithms. The receiver operating characteristic (ROC) area under the curve (AUC) results showed that the RF algorithm had the greatest modeling accuracy, with values of 0.926, 0.94, 0.949, and 0.949 for spring, summer, autumn, and winter, respectively. According to the RF model, the most important variable in spring and autumn was NDVI. Temperature and distance to industrial centers were the most important variables in the summer and winter, respectively. The results showed that autumn, winter, summer, and spring had the highest risk of PM_2.5, respectively.

COVID-19 Risk Mapping with Considering Socio-Economic Criteria Using Machine Learning Algorithms

The reduction of population concentration in some urban land uses is one way to prevent and reduce the spread of COVID-19 disease. Therefore, the objective of this study is to prepare the risk mapping of COVID-19 in Tehran, Iran, using machine learning algorithms according to socio-economic criteria of land use. Initially, a spatial database was created using 2282 locations of patients with COVID-19 from 2 February 2020 to 21 March 2020 and eight socio-economic land uses affecting the disease-public transport stations, supermarkets, banks, automated teller machines (ATMs), bakeries, pharmacies, fuel stations, and hospitals. The modeling was performed using three machine learning algorithms that included random forest (RF), adaptive neuro-fuzzy inference system (ANFIS), and logistic regression (LR). Feature selection was performed using the OneR method, and the correlation between land uses was obtained using the Pearson coefficient. We deployed 70% and 30% of COVID-19 patient locations for modeling and validation, respectively. The results of the receiver operating characteristic (ROC) curve and the area under the curve (AUC) showed that the RF algorithm, which had a value of 0.803, had the highest modeling accuracy, which was followed by the ANFIS algorithm with a value of 0.758 and the LR algorithm with a value of 0.747. The results showed that the central and the eastern regions of Tehran are more at risk. Public transportation stations and pharmacies were the most correlated with the location of COVID-19 patients in Tehran, according to the results of the OneR technique, RF, and LR algorithms. The results of the Pearson correlation showed that pharmacies and banks are the most incompatible in distribution, and the density of these land uses in Tehran has caused the prevalence of COVID-19.

Optimised deep neural network model to predict asthma exacerbation based on personalised weather triggers

Background - Recently, there have been attempts to develop mHealth applications for asthma self-management. However, there is a lack of applications that can offer accurate predictions of asthma exacerbation using the weather triggers and demographic characteristics to give tailored response to users. This paper proposes an optimised Deep Neural Network Regression (DNNR) model to predict asthma exacerbation based on personalised weather triggers. Methods - With the aim of integrating weather, demography, and asthma tracking, an mHealth application was developed where users conduct the Asthma Control Test (ACT) to identify the chances of their asthma exacerbation. The asthma dataset consists of panel data from 10 users that includes 1010 ACT scores as the target output. Moreover, the dataset contains 10 input features which include five weather features (temperature, humidity, air-pressure, UV-index, wind-speed) and five demography features (age, gender, outdoor-job, outdoor-activities, location). Results - Using the DNNR model on the asthma dataset, a score of 0.83 was achieved with Mean Absolute Error (MAE)=1.44 and Mean Squared Error (MSE)=3.62. It was recognised that, for effective asthma self-management, the prediction errors must be in the acceptable loss range (error<0.5). Therefore, an optimisation process was proposed to reduce the error rates and increase the accuracy by applying standardisation and fragmented-grid-search. Consequently, the optimised-DNNR model (with 2 hidden-layers and 50 hidden-nodes) using the Adam optimiser achieved a 94% accuracy with MAE=0.20 and MSE=0.09. Conclusions - This study is the first of its kind that recognises the potentials of DNNR to identify the correlation patterns among asthma, weather, and demographic variables. The optimised-DNNR model provides predictions with a significantly higher accuracy rate than the existing predictive models and using less computing time. Thus, the optimisation process is useful to build an enhanced model that can be integrated into the asthma self-management for mHealth application.

Effects of air pollution in Spatio-temporal modeling of asthma-prone areas using a machine learning model

Industrialization and increasing urbanization have led to increased air pollution, which has a devastating effect on public health and asthma. This study aimed to model the spatial-temporal of asthma in Tehran, Iran using a machine learning model. Initially, a spatial database was created consisting of 872 locations of asthma children and six air pollution parameters, including carbon monoxide (CO), particulate matter (PM₁₀ and PM_2.5), nitrogen dioxide (NO₂), sulfur dioxide (SO₂), and ozone (O₃) in four-seasons (spring, summer, autumn, and winter). Spatial-temporal modeling and mapping of asthma-prone areas were performed using a random forest (RF) model. For Spatio-temporal modeling and assessment, 70% and 30% of the dataset were used, respectively. The Spearman correlation and RF model findings showed that during different seasons, the PM_2.5 parameter had the most important effect on asthma occurrence in Tehran. The assessment of the Spatio-temporal modeling of asthma using the receiver operating characteristic (ROC)-area under the curve (AUC) showed an accuracy of 0.823, 0.821, 0.83, and 0.827, respectively for spring, summer, autumn, and winter. According to the results, asthma occurs more often in autumn than in other seasons.

Spatial Modeling of Asthma-Prone Areas Using Remote Sensing and Ensemble Machine Learning Algorithms

In this study, asthma-prone area modeling of Tehran, Iran was provided by employing three ensemble machine learning algorithms (Bootstrap aggregating (Bagging), Adaptive Boosting (AdaBoost), and Stacking). First, a spatial database was created with 872 locations of asthma patients and affecting factors (particulate matter (PM10 and PM2.5), ozone (O3), sulfur dioxide (SO2), carbon monoxide (CO), nitrogen dioxide (NO2), rainfall, wind speed, humidity, temperature, distance to street, traffic volume, and a normalized difference vegetation index (NDVI)). We created four factors using remote sensing (RS) imagery, including air pollution (O3, SO2, CO, and NO2), altitude, and NDVI. All criteria were prepared using a geographic information system (GIS). For modeling and validation, 70% and 30% of the data were used, respectively. The weight of evidence (WOE) model was used to assess the spatial relationship between the dependent and independent data. Finally, three ensemble algorithms were used to perform asthma-prone areas mapping. According to the Gini index, the most influential factors on asthma occurrence were distance to the street, NDVI, and traffic volume. The area under the curve (AUC) of receiver operating characteristic (ROC) values for the AdaBoost, Bagging, and Stacking algorithms was 0.849, 0.82, and 0.785, respectively. According to the findings, the AdaBoost algorithm outperforms the Bagging and Stacking algorithms in spatial modeling of asthma-prone areas.

Groundwater-Potential Mapping Using a Self-Learning Bayesian Network Model: A Comparison among Metaheuristic Algorithms

Owing to the reduction of surface-water resources and frequent droughts, the exploitation of groundwater resources has faced critical challenges. For optimal management of these valuable resources, careful studies of groundwater potential status are essential. The main goal of this study was to determine the optimal network structure of a Bayesian network (BayesNet) machine-learning model using three metaheuristic optimization algorithms—a genetic algorithm (GA), a simulated annealing (SA) algorithm, and a Tabu search (TS) algorithm—to prepare groundwater-potential maps. The methodology was applied to the town of Baghmalek in the Khuzestan province of Iran. For modeling, the location of 187 springs in the study area and 13 parameters (altitude, slope angle, slope aspect, plan curvature, profile curvature, topography wetness index (TWI), distance to river, distance to fault, drainage density, rainfall, land use/cover, lithology, and soil) affecting the potential of groundwater were provided. In addition, the statistical method of certainty factor (CF) was utilized to determine the input weight of the hybrid models. The results of the OneR technique showed that the parameters of altitude, lithology, and drainage density were more important for the potential of groundwater compared to the other parameters. The results of groundwater-potential mapping (GPM) employing the receiver operating characteristic (ROC) area under the curve (AUC) showed an estimation accuracy of 0.830, 0.818, 0.810, and 0.792, for the BayesNet-GA, BayesNet-SA, BayesNet-TS, and BayesNet models, respectively. The BayesNet-GA model improved the GPM estimation accuracy of the BayesNet-SA (4.6% and 7.5%) and BayesNet-TS (21.8% and 17.5%) models with respect to the root mean square error (RMSE) and mean absolute error (MAE), respectively. Based on metric indices, the GA provides a higher capability than the SA and TS algorithms for optimizing the BayesNet model in determining the GPM.