Establishment and Analysis of a Combined Diagnostic Model of Polycystic Ovary Syndrome with Random Forest and Artificial Neural Network

Figure 1

Schematic illustration of study design. A total of 264 differentially expressed genes (DEGs) were obtained in differential expression analysis with GSE6798 dataset (skeletal muscle, ) (step 1), and functional enrichment analysis were also performed (step 2). All the 264 DEGs were tested for their potential as classification-related genes with random forest model, and 12 key genes were identified (step 3). Artificial neural network (ANN), another machine learning algorithm, was used to calculate the weight of genes (step 4). Therefore, a versatile classification model, designated as neuralPCOS, was established with the use of RF and ANN (step 5). Finally, the utility of neuralPCOS was validated in microarray data and RNA-seq data (step 6).