Machine Learning Models for Predicting the Occurrence of Respiratory Diseases Using Climatic and Air-Pollution Factors

Abstract

Objectives. Because climatic and air-pollution factors are known to influence the occurrence of respiratory diseases, we used these factors to develop machine learning models for predicting the occurrence of respiratory diseases.Methods. We obtained the daily number of respiratory disease patients in Seoul. We used climatic and air-pollution factors to predict the daily number of patients treated for respiratory diseases per 10,000 inhabitants. We applied the reliefbased feature selection algorithm to evaluate the importance of feature selection. We used the gradient boosting and Gaussian process regression (GPR) methods, respectively, to develop two different prediction models. We also employed the holdout cross-validation method, in which 75% of the data was used to train the model, and the remaining 25% was used to test the trained model. We determined the estimated number of respiratory disease patients by applying the developed prediction models to the test set. To evaluate the performance of each model, we calculated the coefficient of determination (R 2 ) and the root mean square error (RMSE) between the original and estimated numbers of respiratory disease patients. We used the Shapley Additive exPlanations (SHAP) approach to interpret the estimated output of each machine learning model. Results.Features with negative weights in the relief-based algorithm were excluded. When applying gradient boosting to unseen test data, R 2 and RMSE were 0.68 and 13.8, respectively. For GPR, the R 2 and RMSE were 0.67 and 13.9, respectively. SHAP analysis showed that reductions in average temperature, daylight duration, average humidity, sulfur dioxide (SO2), total solar insolation amount, and temperature difference increased the number of respiratory disease patients, whereas increases in atmospheric pressure, carbon monoxide (CO), and particulate matter ≤2.5 µm in aerodynamic diameter (PM2.5) increased the number of respiratory disease patients.Conclusions. We successfully developed models for predicting the occurrence of respiratory diseases using climatic and airpollution factors. These models could evolve into public warning systems.

Multioutput Ensemble Machine Learning Algorithm: A Prediction Model of Acute Respiratory infection and Pneumonia Occurrence

“…Our algorithm achieved an R2 value of 99%, outperforming the approach proposed by Khatri K L, Tamil L S (2) and Khaiwal R, Bahadur S S, Katoch V, Bhardwaj S, Kaur-Sidhu M, Gupta M, et al (4) by a margin of 17% and 12% respectively. Also, our algorithm demonstrated higher R2 and RMSE values, with R2 reaching 99% and RMSE 0.46 and 0.22, compared to the R2 of 67% and RMSE of 13.9 reported by Ku Y, Kwon SB, Yoon JH, Mun SK, and Chang M (3) . In addition to the above findings, our algorithm demonstrates remarkably low forecasting errors for ARI and Pneumonia, with rates of 2.25% and 5.12% respectively.…”

“…Moreover, the research did not take into account separating the meteorological and air pollution data individually. Ku Y, Kwon SB, Yoon JH, Mun SK, and Chang M (3) compare Gaussian process regressor and gradient boosting methods for patient arrival forecasting for the period of 2014-2019. Both models demonstrated competitive prediction performance, with R2 values of over 0.67 and RMSE values below 13.9.…”

Long-term exposure to particulate matter was associated with increased dementia risk using both traditional approaches and novel machine learning methods

“…More associations will be identified with the accumulation of NHIRD and EPA monitoring data. ML models for predicting the incidence of disease using environmental and air pollution factors could evolve into medical and public health warning systems 67 .…”

Associations between Peritonsillar Abscess and Deep Neck Infection in Chronic Periodontitis Patients: Two Nested Case—Control Studies Using a National Health Screening Cohort

“…We could not include the treatment histories of medication and surgical procedures for CP and DNI, which may have led to heterogeneity in the analyses. Although we included several variables, including demographic and socioeconomic factors and comorbidities, there are several potential confounders, such as a history of tonsillectomy or other neck surgeries and a history of airway infection, that can influence the relationship between CP and DNI [29,30]. Further studies may be warranted to determine the specific associations between CP and DNI according to severity and subtype.…”