Prediction of household dust mite concentration based on machine learning algorithm

Household dust mites (HDMs) are the important allergens causing allergic diseases in children. A predictive model can help us understand concentration of HDMs different areas China to better prevent and control this kind allergen. This study used 454 household inspection samples childrens’ room obtained from China, Children, Homes, Health (CCHH) phase 2 study, conducted during 2013-2014. Spearman correlation multiple logistic regression were explore influencing factors concentrations, by comprehensively considering residents’ lifestyle, building characteristics, environmental exposure, especially dampness-related exposures. Gradient Boosting Decision Tree(GBDT) algorithm build prediction model. The data CCHH established It was found that there some differences between two types HDMs. a significant (p<0. 05)with number indoor moisture indicators. 17 concentrations four aspects finally study. training GBDT has reasonable accuracy(R >0. 9). paper provides reference for predicting children's bedrooms influence factors.