METHODS: This study proposed an end-to-end air quality predictive model for smart city applications, utilizing four machine learning techniques and two deep learning techniques. These include Ada Boost, SVR, RF, KNN, MLP regressor and LSTM. The study was conducted in four different urban cities in Selangor, Malaysia, including Petaling Jaya, Banting, Klang, and Shah Alam. The model considered the air quality data of various pollution markers such as PM2.5, PM10, O3, and CO. Additionally, meteorological data including wind speed and wind direction were also considered, and their interactions with the pollutant markers were quantified. The study aimed to determine the correlation variance of the dependent variable in predicting air pollution and proposed a feature optimization process to reduce dimensionality and remove irrelevant features to enhance the prediction of PM2.5, improving the existing LSTM model. The study estimates the concentration of pollutants in the air based on training and highlights the contribution of feature optimization in air quality predictions through feature dimension reductions.
RESULTS: In this section, the results of predicting the concentration of pollutants (PM2.5, PM10, O3, and CO) in the air are presented in R2 and RMSE. In predicting the PM10 and PM2.5concentration, LSTM performed the best overall high R2values in the four study areas with the R2 values of 0.998, 0.995, 0.918, and 0.993 in Banting, Petaling, Klang and Shah Alam stations, respectively. The study indicated that among the studied pollution markers, PM2.5,PM10, NO2, wind speed and humidity are the most important elements to monitor. By reducing the number of features used in the model the proposed feature optimization process can make the model more interpretable and provide insights into the most critical factor affecting air quality. Findings from this study can aid policymakers in understanding the underlying causes of air pollution and develop more effective smart strategies for reducing pollution levels.
METHODS: A total of 607 adolescents were recruited from the Malaysian Health and Adolescents Longitudinal Research Team (MyHeART) study, a prospective cohort study conducted from March 2012 to May 2016 that explored the noncommunicable diseases (NCDs) risk factors among 13 to 17 years old students in 3 states of Peninsular Malaysia. Students who participated in all 3 data collection periods in 2012, 2014, and 2016 with kidney function assessment across all 3-time points were included in the current study. The students' estimated glomerular filtration rate (eGFR) was calculated from isotope-dilution mass spectrometry-traceable Schwartz's equation and categorized based on Kidney Disease: Improving Global Outcomes (KDIGO) classification. Changes in kidney function were examined, and the longitudinal relationship between eGFR and multiple NCD risk factors was analyzed using the generalized estimating equation (GEE).
RESULTS: The prevalence of decreased eGFR (60-89 ml/min per 1.73 m2) among the students increased from 6.1% (2012) to 30.0% (2014) and 40.2% (2016). Based on the GEE, the student's eGFR decreased over time, with a steeper decline during early to midadolescence. Males and rural students had lower eGFR compared to their counterparts. Students who are morbidly obese had lower eGFR than those with normal body mass index (BMI). Protein consumption also has a potential moderating effect on eGFR in adolescents.
CONCLUSION: Kidney function changes can be detected as early as adolescence and are likely attributable to multiple NCD risk factors. Therefore, more comprehensive prevention efforts from various stakeholders are needed to identify health issues like CKD.