Application of machine learning approaches to predict the impact of ambient air pollution on outpatient visits for acute respiratory infections

Predicting hospital outpatient volume using XGBoost: a machine learning approach

Hospital outpatient volume is influenced by a variety of factors, including environmental conditions and healthcare resource availability. Accurate prediction of outpatient demand can significantly enhance operational efficiency and optimize the allocation of medical resources. This study aims to develop a predictive model for daily hospital outpatient volume using the XGBoost algorithm. Meanwhile, the forecasting performance was compared with that of the Seasonal AutoRegressive Integrated Moving Average with exogenous regressors (SARIMAX) and Random Forest (RF) models. The dataset comprises daily climate data (e.g., temperature, precipitation, PM2.5 levels), historical outpatient volume records, and the number of outpatient specialists available each day. The data range involved spans from January 1, 2014, to October 31, 2024. Data preprocessing involved addressing missing values and encoding categorical variables. Model performance was assessed using three metrics: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE) , Mean Absolute Percentage Error (MAPE), and R-squared (R2) metrics. The XGBoost model exhibited superior predictive accuracy compared to both the SARIMAX and RF models, with the lowest MAE, RMSE, MAPE, and the highest R2, successfully capturing key relationships between climate factors, resource availability, and outpatient volume. The number of outpatient specialists, temporal variables (such as year, quarter, month, and weekday), meteorological conditions (average temperature), and air quality (PM2.5) had the most significant impact on the prediction model. This study underscores the potential of machine learning algorithms like XGBoost in effectively predicting hospital outpatient demand. The findings offer valuable insights for hospitals to make proactive adjustments to their resource allocation, thereby improving their service capacity.

Statistical inference and neural network training based on stochastic difference model for air pollution and associated disease transmission

A polluted air environment can potentially provoke infections of diverse respiratory diseases. The development of mathematical models can study the mechanism of air pollution and its effect on the spread of diseases. The key is to characterize the intrinsic correlation between the disease infection and the change in air pollutant concentration. In this paper, we establish a coupled discrete susceptible-exposed-infectious-susceptible (SEIS) model with demography to characterize the transmission of disease, and the change in the concentration of air pollutants is described in the form of the Beverton-Holt (BH) model with a time-varying inflow rate of air pollutants. Considering the periodic variation characteristics of data, time-varying parameters are defined as specific functional forms. We estimate the change point at which the parameters switch and the parameter values within the switching interval based on Bayesian statistical theory. The data fitting of the model can reflect the seasonal peaks and annual growth trends of values of air quality index (AQI) and the number of influenza-like illnesses (ILI) cases. However, the bias in data fitting indicates a more complex correlation pattern between disease and pollutant concentration changes. To explore unknown mechanisms, we propose the extended transmission-dynamics-informed neural network (TDINN) algorithm by combining deep learning with difference equations and obtain the curves of the transmission rate and inflow rate functions over time. The results show that neural network models can help us determine time-varying parameters in the model, thereby better reflecting the trend of data changes.

Temporal trends and predictive modeling of air pollutants in Delhi: a comparative study of artificial intelligence models

Air pollution monitoring and modeling are the most important focus of climate and environment decision-making organizations. The development of new methods for air quality prediction is one of the best strategies for understanding weather contamination. In this research, different air quality parameters were forecasted, including Carbon Monoxide (CO), Nitrogen Monoxide (NO), Nitrogen Dioxide (NO2), Ozone (O3), Sulphur Dioxide (SO2), Fine Particles Matter (PM2.5), Coarse Particles Matter (PM10), and Ammonia (NH3). Hourly datasets were collected for air quality monitoring stations near Delhi, India, from November 25, 2020 to January 24, 2023. In this context, five intelligent models were developed, including Long Short-Term Memory (LSTM), Bidirectional Long-Short Term Memory (Bi-LSTM), Gated Recurrent Unit (GRU), Multilayer Perceptron (MLP), and Extreme Gradient Boosting (XGBoost). The modelling results revealed that Bi-LSTM model had the best predictability performance for forecasting CO with (R2 = 0.979), NO with (R2 = 0.961), NO2 with (R2 = 0.956), SO2 with (R2 = 0.955), PM10 with (R2 = 0.9751) and NH3 with (R2 = 0.971). Meanwhile, GRU and LSTM models performed better in forecasting O3 and PM2.5 with (R2 = 0.9624) and (R2 = 0.973), respectively. The current research provides illuminating visuals highlighting the potential of deep learning to comprehend air quality modeling, enabling improved environmental decisions.

Forecasting rheumatoid arthritis patient arrivals by including meteorological factors and air pollutants

The burden of rheumatoid arthritis (RA) has gradually elevated, increasing the need for medical resource redistribution. Forecasting RA patient arrivals can be helpful in managing medical resources. However, no relevant studies have been conducted yet. This study aims to construct a long short-term memory (LSTM) model, a deep learning model recently developed for novel data processing, to forecast RA patient arrivals considering meteorological factors and air pollutants and compares this model with traditional methods. Data on RA patients, meteorological factors and air pollutants from 2015 to 2022 were collected and normalized to construct moving average (MA)- and autoregressive (AR)-based and LSTM models. After data normalization, the root mean square error (RMSE) was adopted to evaluate models' forecast ability. A total of 2422 individuals were enrolled. Not using the environmental data, the RMSEs of the MA- and AR-based models' test sets are 0.131, 0.132, and 0.117 when the training set: test set ratio is 2:1, 3:1, and 7:1, while they are 0.110, 0.130, and 0.112 for the univariate LSTM models. Considering meteorological factors and air pollutants, the RMSEs of the MA- and AR-based model test sets were 0.142, 0.303, and 0.164 when the training set: test set ratio is 2:1, 3:1, and 7:1, while they were 0.108, 0.119, and 0.109 for the multivariable LSTM models. Our study demonstrated that LSTM models can forecast RA patient arrivals more accurately than MA- and AR-based models for datasets of all three sizes. Considering the meteorological factors and air pollutants can further improve the forecasting ability of the LSTM models. This novel method provides valuable information for medical management, the optimization of medical resource redistribution, and the alleviation of resource shortages.

Factors of acute respiratory infection among under-five children across sub-Saharan African countries using machine learning approaches

Symptoms of Acute Respiratory infections (ARIs) among under-five children are a global health challenge. We aimed to train and evaluate ten machine learning (ML) classification approaches in predicting symptoms of ARIs reported by mothers among children younger than 5 years in sub-Saharan African (sSA) countries. We used the most recent (2012-2022) nationally representative Demographic and Health Surveys data of 33 sSA countries. The air pollution covariates such as global annual surface particulate matter (PM 2.5) and the nitrogen dioxide available in the form of raster images were obtained from the National Aeronautics and Space Administration (NASA). The MLA was used for predicting the symptoms of ARIs among under-five children. We randomly split the dataset into two, 80% was used to train the model, and the remaining 20% was used to test the trained model. Model performance was evaluated using sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve. A total of 327,507 under-five children were included in the study. About 7.10, 4.19, 20.61, and 21.02% of children reported symptoms of ARI, Severe ARI, cough, and fever in the 2 weeks preceding the survey years respectively. The prevalence of ARI was highest in Mozambique (15.3%), Uganda (15.05%), Togo (14.27%), and Namibia (13.65%,), whereas Uganda (40.10%), Burundi (38.18%), Zimbabwe (36.95%), and Namibia (31.2%) had the highest prevalence of cough. The results of the random forest plot revealed that spatial locations (longitude, latitude), particulate matter, land surface temperature, nitrogen dioxide, and the number of cattle in the houses are the most important features in predicting the diagnosis of symptoms of ARIs among under-five children in sSA. The RF algorithm was selected as the best ML model (AUC = 0.77, Accuracy = 0.72) to predict the symptoms of ARIs among children under five. The MLA performed well in predicting the symptoms of ARIs and associated predictors among under-five children across the sSA countries. Random forest MLA was identified as the best classifier to be employed for the prediction of the symptoms of ARI among under-five children.

Forecasting hospital discharges for respiratory conditions in Costa Rica using climate and pollution data

Respiratory diseases represent one of the most significant economic burdens on healthcare systems worldwide. The variation in the increasing number of cases depends greatly on climatic seasonal effects, socioeconomic factors, and pollution. Therefore, understanding these variations and obtaining precise forecasts allows health authorities to make correct decisions regarding the allocation of limited economic and human resources. We aimed to model and forecast weekly hospitalizations due to respiratory conditions in seven regional hospitals in Costa Rica using four statistical learning techniques (Random Forest, XGboost, Facebook's Prophet forecasting model, and an ensemble method combining the above methods), along with 22 climate change indices and aerosol optical depth as an indicator of pollution. Models were trained using data from 2000 to 2018 and were evaluated using data from 2019 as testing data. During the training period, we set up 2-year sliding windows and a 1-year assessment period, along with the grid search method to optimize hyperparameters for each model. The best model for each region was selected using testing data, based on predictive precision and to prevent overfitting. Prediction intervals were then computed using conformal inference. The relative importance of all climatic variables was computed for the best model, and similar patterns in some of the seven regions were observed based on the selected model. Finally, reliable predictions were obtained for each of the seven regional hospitals.

A comprehensive evaluation of influencing factors of neonicotinoid insecticides (NEOs) in farmland soils across China: First focus on film mulching

Neonicotinoid insecticide (NEO) residues in agricultural soils have concerning and adverse effects on agroecosystems. Previous studies on the effects of farmland type on NEOs are limited to comparing greenhouses with open fields. On the other hand, both NEOs and microplastics (MPs) are commonly found in agricultural fields, but their co-occurrence characteristics under realistic fields have not been reported. This study grouped farmlands into three types according to the covering degree of the film, collected 391 soil samples in mainland China, and found significant differences in NEO residues in the soils of the three different farmlands, with greenhouse having the highest NEO residue, followed by farmland with film mulching and farmland without film mulching (both open fields). Furthermore, this study found that MPs were significantly and positively correlated with NEOs. As far as we know this is the first report to disclose the association of film mulching and MPs with NEOs under realistic fields. Moreover, multiple linear regression and random forest models were used to comprehensively evaluate the factors influencing NEOs (including climatic, soil, and agricultural indicators). The results indicated that the random forest model was more reliable, with MPs, farmland type, and total nitrogen having higher relative contributions.

Long-term spatiotemporal evolution and coordinated control of air pollutants in a typical mega-mountain city of Cheng-Yu region under the "dual carbon" goal

Clarifying the spatiotemporal distribution and impact mechanism of pollution is the prerequisite for megacities to formulate relevant air pollution prevention and control measures and achieve carbon neutrality goals. Chongqing is one of the dual-core key megacities in Cheng-Yu region and as a typical mountain-city in China, environmental problems are complex and sensitive. This research aims to investigate the exceeding standard levels and spatio-temporal evolution of criteria pollutants between 2014 and 2020. The results indicated that PM10, PM2.5, CO and SO2 were decreased significantly by 45.91%, 52.86%, 38.89% and 66.67%, respectively. Conversely, the concentration of pollutant O3 present a fluctuating growth and found a "seesaw" phenomenon between it and PM. Furthermore, PM and O3 are highest in winter and summer, respectively. SO2, NO2, CO, and PM showed a "U-shaped", and O3 showed an inverted "U-shaped" seasonal variation. PM and O3 concentrations are still far behind the WHO, 2021AQGs standards. Significant spatial heterogeneity was observed in air pollution distribution. These results are of great significance for Chongqing to achieve "double control and double reduction" of PM2.5 and O3 pollution, and formulate a regional carbon peaking roadmap under climate coordination. Besides, it can provide an important platform for exploring air pollution in typical terrain around the world and provide references for related epidemiological research.Implications: Chongqing is one of the dual-core key megacities in Cheng-Yu region and as a typical mountain city, environmental problems are complex and sensitive. Under the background of the "14th Five-Year Plan", the construction of the "Cheng-Yu Dual-City Economic Circle" and the "Dual-Carbon" goal, this article comprehensively discussed the annual and seasonal excess levels and spatiotemporal evolution of pollutants under the multiple policy and the newest international standards (WHO,2021AQG) backgrounds from 2014 to 2020 in Chongqing. Furthermore, suggestions and measures related to the collaborative management of pollutants were discussed. Finally, limitations and recommendations were also put forward.Clarifying the spatiotemporal distribution and impact mechanism of pollution is the prerequisite for cities to formulate relevant air pollution control measures and achieve carbon neutrality goals. This study is of great significance for Chongqing to achieve "double control and double reduction" of PM2.5 and O3 pollution, study and formulate a regional carbon peaking roadmap under climate coordination and an action plan for sustained improvement of air quality.In addition, this research can advanced our understanding of air pollution in complex terrain. Furthermore, it also promote the construction of the China national strategic Cheng-Yu economic circle and build a beautiful west. Moreover, it provides scientific insights for local policymakers to guide smart urban planning, industrial layout, energy structure, and transportation planning to improve air quality throughout the Cheng-Yu region. Finally, this is also conducive to future scientific research in other regions of China, and even megacities with complex terrain in the world.

Application of machine learning to predict hospital visits for respiratory diseases using meteorological and air pollution factors in Linyi, China

Urbanization and industrial development have resulted in increased air pollution, which is concerning for public health. This study evaluates the effect of meteorological factors and air pollution on hospital visits for respiratory diseases (pneumonia, acute upper respiratory infections, and chronic lower respiratory diseases). The test dataset comprises meteorological parameters, air pollutant concentrations, and outpatient hospital visits for respiratory diseases in Linyi, China, from January 1, 2016 to August 20, 2022. We use support vector regression (SVR) to build models that enable analysis of the effect of meteorological factors and air pollutants on the number of outpatient visits for respiratory diseases. Spearman correlation analysis and SVR model results indicate that NO2, PM2.5, and PM10 are correlated with the occurrence of respiratory diseases, with the strongest correlation relating to pneumonia. An increase in the daily average temperature and daily relative humidity decreases the number of patients with pneumonia and chronic lower respiratory diseases but increases the number of patients with acute upper respiratory infections. The SVR modeling has the potential to predict the number of respiratory-related hospital visits. This work demonstrates that machine learning can be combined with meteorological and air pollution data for disease prediction, providing a useful tool whereby policymakers can take preventive measures.