Fig. 2From: Leading dietary determinants identified using machine learning techniques and a healthy diet score for changes in cardiometabolic risk factors in children: a longitudinal analysisLeading dietary determinants for changes in cardiometabolic risk scores in children. This figure shows the contribution of the total variance in percentage by leading dietary determinants (selected from 26 food groups). Machine learning models including general linear regression model, random forest, and gradient boost machine were used to analyze the importance of dietary predictors for CMRS. Random forest had the highest prediction performance and this figure shows the leading dietary determinants derived from the random forestBack to article page