biostudies-literatureUnknown15(2)Ku YChungnam National University<h4>Objectives</h4>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.<h4>Methods</h4>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 relief-based 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 Clinical and experimental otorhinolaryngology168-176https://www.ebi.ac.uk/biostudies/studies/S-EPMC9149237biostudies-literatureMachine Learning Models for Predicting the Occurrence of Respiratory Diseases Using Climatic and Air-Pollution Factors.PMC9149237Ku YChang MKwon SBYoon JHMun SKfalseMachine Learning Models for Predicting the Occurrence of Respiratory Diseases Using Climatic and Air-Pollution Factors.<h4>Objectives</h4>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.<h4>Methods</h4>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 relief-based 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 2022-01-01T00:00:00Z2022 May2025-04-04T11:28:52.923Z2025-04-04T11:28:52.923ZS-EPMC91492373499053610.21053/ceo.2021.01536