Air Pollution-Related Mortality in Bangkok: A Time-Series Neural Network Analysis

Air pollution and pneumonia hospitalization in Qingyang, China: A time-series analysis

The health hazards caused by air pollution vary significantly depending on factors such as the composition of pollutants in the region, climate, and the susceptibility of the population. Although numerous studies have explored the relationship between air quality and pneumonia, specific research evidence from a particular inland energy city like Qingyang in China is still scarce. This study aims to quantify the short-term impact of air pollution in this under-researched region on pneumonia hospitalizations. We collected the medical records of patients with pneumonia from January 1, 2015, to December 31, 2019, and also obtained data on 6 types of common air pollutants and meteorological conditions. We performed a time series analysis using a generalized additive model and a distributed nonlinear lag model. All measured data exhibited pronounced seasonality: particulate matter less than 2.5 μm in diameter, particulate matter less than 10 μm in diameter, sulfur dioxide (SO2), nitrogen dioxide (NO2), carbon monoxide (CO) concentrations and pneumonia admissions were higher in the cold season and lower in the warm season, a pattern conversely mirrored by ozone (O3) concentrations, average temperature, and relative humidity. In the single pollutant model, for every 10 μg/m3 increase in exposure levels of particulate matter less than 2.5 μm in diameter, particulate matter less than 10 μm in diameter, SO2, NO2, and O3 8 hours and for every 1 mg/m3 increase in CO exposure level, the risk of pneumonia admission was 1.004 (0.991, 1.017), 1.004 (0.999, 1.010), 1.035 (1.022, 1.048), 1.221 (1.174, 1.271), 0.999 (0.981, 1.017), and 1.382 (1.230, 1.552), respectively. The strongest effects occur in lag 1, lag 7, lag 07, lag 07, lag 3, and lag 05, respectively. Our study identifies significant gender- and age-specific susceptibilities to air pollution in Qingyang. Men were more vulnerable to SO2, whereas women were more affected by CO. Children aged ≤14 years constituted a high-risk group. Furthermore, we observed a distinct seasonal pattern: SO2, NO2, and CO were key drivers of pneumonia admissions with stronger effects in the cold season, in contrast to O3, which exhibited adverse effects only during the warm season.

CENTRAL ASIAN

Performance of a hybrid ARIMA-LSTM-Transformer model in influenza-like illness forecasting: A comparative study

Accurate forecasting of influenza-like illness (ILI) incidence is essential for public health surveillance and early epidemic intervention. Traditional statistical models effectively capture linear temporal trends but often fail to model the complex nonlinear dynamics of disease transmission. To address this limitation, this study proposes a hybrid forecasting framework that integrates Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), temporal attention mechanisms, and Transformer architecture. Weekly ILI surveillance data collected from Xinjiang and Shandong provinces, China, between 2023 and 2025 were used for model development and validation. Meteorological variables, including weekly average temperature and relative humidity, were incorporated as exogenous features. The proposed framework decomposes the forecasting task into linear and nonlinear components, where ARIMA captures long-term linear trends and an attention-enhanced LSTM–Transformer branch models nonlinear temporal dependencies. Experimental results demonstrated that the proposed model achieved superior predictive performance on the Xinjiang Production and Construction Corps dataset, with an MAE of 29.371, RMSE of 41.334, MAPE of 10.744%, and R2 of 0.579. Diebold–Mariano tests confirmed statistically significant improvements over standalone ARIMA, LSTM, and ARIMA– LSTM models (P < 0.05). Furthermore, cross-regional validation on the Yantai High-Tech Zone dataset showed comparable forecasting accuracy, indicating strong generalization capability under different climatic conditions. These findings suggest that the proposed hybrid framework effectively captures both linear and nonlinear transmission patterns of ILI and provides a practical tool for early warning and public health resource allocation in grassroots disease surveillance systems.

Prediction of Air Pollution in the Sultanate of Oman using Machine Learning Approaches

Air pollution has become a major environmental and public-health concern worldwide, and understanding its behaviour is essential for effective monitoring and management. This study investigates air-quality patterns across four regions in the Sultanate of Oman—Al Khuwair, Salalah, Al Khoud, and Bediya—using a combination of statistical modelling and machine-learning techniques. Hourly data for 2023, including pollutant concentrations and key meteorological variables, were obtained from the Environment Authority of Oman, cleaned, and pre-processed to construct region-specific datasets. Air Quality Index (AQI) values were calculated for each pollutant and classified into three categories (Good, Moderate, and Unhealthy). Kernel Support Vector Machine (KSVM) and Gaussian Process Regression and models were trained using a 70/30 temporal split to classify AQI levels. Results showed that KSVM achieved the highest accuracy in Salalah (96.97%), Al Khoud (94.33%), and Bediya (93.37%), while Gaussian Process Regression performed best in Al Khuwair (70.32%). In conclusion, this research demonstrates that advanced kernel-based classifiers can effectively model non-linear environmental data, providing a scalable solution for regional environmental management.

Time-series Forecasting of Hypertension Prevalence using Arima, Lstm, and Hybrid Arima–lstm Models

Hypertension is a major global risk factor for cardiovascular disease and premature mortality, with increasing public health implications in India. This study compares ARIMA, LSTM, and Hybrid ARIMA–LSTM models for forecasting India’s hypertension burden using annual data from 1990–2025 across six epidemiological indicators: prevalence, prevalence cases, ASPR, incidence, deaths, and DALYs. After data pre-processing and stationarity testing, ARIMA captured linear trends, LSTM modeled nonlinear patterns, and the hybrid model integrated both approaches. Model performance was evaluated using MAE, RMSE, MAPE, R², and residual diagnostics. The Hybrid ARIMA–LSTM model consistently achieved superior forecasting accuracy, with lower errors and better goodness-of-fit than the standalone models. Forecasts for 2026–2045 suggest that hypertension will remain a significant health challenge, with prevalence reaching 30.87% and affecting approximately 350.11 million people by 2045, along with 13.83 million incident cases, 217.77 thousand deaths, and 5.54 million DALYs. The findings highlight the need for strengthened prevention, early detection, disease management, and evidence-based health policies, while supporting the Hybrid ARIMA–LSTM framework as a robust tool for long-term epidemiological forecasting.

Monthly trends, determinants, and forecasting of perinatal mortality in Ghana: a comparison of ARIMA, BPNN, DLNN, and GRNN models

This study provides a 16-year monthly hospital time series analysis of perinatal mortality in Ghana, compares classical time-series forecasting with three neural-network approaches, and demonstrates that better ANC coverage and lower hypertension burden track with lower monthly PMR in this setting.