FIGURE 1.
Machine learning modeling to classify subjects into Insomnia disorder and controls. (A) The functional connectivity among 39 brain regions comprised the top 20 features of the model, depicted here in a SHAP plot. The x-axis depicts the impact of each feature on the model output, while the color of each data point indicates whether a high or low functional connectivity is associated with the output. (B) The regions are demonstrated on a model brain. (C) The graph demonstrates the mean importance of each network on the model’s classification.