Fig. 4: Receiver operating characteristics–area under the curve (RoC–AUC) of the binary logistic regression model for depression prediction.

The y-axis represents the sensitivity of the model (true positive rate), while the x-axis shows the false positive rate. The curve illustrates the model’s performance, plotting the true positive rate against the false positive rate. The diagonal line represents a random classifier. The RoC–AUC curve ranges from 0 to 1, with the area under the curve for this model being 0.875.