Skip to main content
Fig. 4 | BMC Pediatrics

Fig. 4

From: Diagnostic model based on bioinformatics and machine learning to distinguish Kawasaki disease using multiple datasets

Fig. 4

Screening results of Kawasaki disease-related DEGs using a random forest classifier. a Influence of the number of decision trees on the error rate. The x-axis is the number of decision trees, and the y-axis is the error rate. b Ranking of input variables in the random forest model to classify KD and healthy control samples. All genes are sorted by the value of “MeanDecreaseAccuracy” and “MeanDecreaseGini,” separately. c Gene number screening from fivefold cross-validation method in the construction of random forest. d Visualization of neural network topology of GSE68004 with 8 input layers, 5 hidden layers, and 2 output layers

Back to article page

BMC Pediatrics

ISSN: 1471-2431

Contact us