AUTHOR=Zhang Yimeng , Wang Yu , Zhang Zhaoxin , Wang Yuqi , Jia Jie 

TITLE=Study on machine learning of molar incisor hypomineralization in an endemic fluorosis region in central China

JOURNAL=Frontiers in Physiology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2023.1088703

DOI=10.3389/fphys.2023.1088703

ISSN=1664-042X

ABSTRACT=Objectives The aim of the present study was to develop machine learning model to predict the risk for MIH and identify associated factors in an endemic fluorosis region in central China.
Methods A cross-sectional study was conducted with selected regions of 1568 schoolchildren. The clinical examination included the investigation of MIH based on the European Academy of Paediatric Dentistry (EAPD) criteria. In this study, supervised machine learning (e.g., Logistic Regression) and correlation analysis (e.g., Pearson correlation analysis) were used for classification and prediction. 
Results Overall prevalence of MIH was 13.7%. The nomograph showed that non-dental fluorosis (DF) had great influence on the early occurrence of MIH that was decreased with the strengthen of DF severity. Then, we examined the association between MIH and DF and found DF had a protective correlation with MIH, and the effect of protection became more obvious with the increasing severity of DF. Furthermore, children whose enamel was defective were more prone to experience caries, meanwhile, dental caries was positively correlated with MIH (OR=1.843; 95% CI:1.260 -2.694). However, Exposure to poor quality shallow underground water, as well as gender and oral hygiene, did not increase the likelihood of developing MIH. 
Conclusions DF should be considered a protective factor within the multifactorial etiology of MIH.
Clinical Significance In this study, the correlation between various factors, especially fluorosis, and MIH was explored, and a machine learning model was constructed to make it possible to predict the incidence of MIH. Our study may contribute to the early intervention and clinical planning towards the population with MIH.