Fig. 2From: Can natural language processing help differentiate inflammatory intestinal diseases in China? Models applying random forest and convolutional neural network approachesThe visualization of the result of two classifiers. a: the classifier built by RF; b: the classifier built by CNN. The distance between two dots was proportional to the similarities of the corresponding endoscopic descriptions. Different color of the dots represented different diseases. Purple: Ulcerative colitis (UC); yellow: Crohn’s disease (CD); green, Intestinal tuberculosis (ITB)Back to article page