Skip to main content
. 2024 Mar 14;14:6163. doi: 10.1038/s41598-024-53426-0

Figure 4.

Figure 4

Traditional feature importance analysis provided by XGBoost predicting model. Similar to previous results, anger problem is the most important variable in suicidal risk prediction. The y-axis of the chart indicates the score of each feature with respect to other features in the dataset.