Fig. 3From: Integration of taxa abundance and occurrence frequency to identify key gut bacteria correlated to clinics in Crohn’s diseasePotential important genera biomarkers in the feces to classify CD or HCs. A random forest algorithm was used to construct a machine learning model to classify CD patients and HCs. (a). MeanDecreaseAccuracy and MeanDecreaseGini of the top 30 genera in the CD/HCs classification model. (b). Cluster and heatmap display of the top 30 key genera in the CD/HCs classification modelBack to article page