0.05). The net benefit of model was improved and cognition resulted in continuous reclassification improvement with NRI of 5.3%. Several clinical dimensions were significant predictors in the XGBoost classification algorithm. Limitations A limited sample size and failure to include sufficient suicide risk factors in the predictive model. Conclusion This study demonstrate that cognitive deficits may serve as an important risk factor to predict suicide attempts in patients with MDD. Combined with other demographic characteristics and attributes drawn from clinical questionnaires, cognitive function can improve the predictive effectiveness of the ML model. Additionally, explanatory ML models can help clinicians detect specific risk factors for each suicide attempter within MDD patients. These findings may be helpful for clinicians to detect those at high risk of suicide attempts quickly and accurately, and help them make proactive treatment decisions."/>
Skip to main content
Fig. 3 | BMC Psychiatry

Fig. 3

From: Can cognition help predict suicide risk in patients with major depressive disorder? A machine learning study

Fig. 3

The pre-selected feature sets of the optimal model were evaluated through SHAP. a Features are listed in descending order according to contributions for the XGBoost-2 in predicting suicide attempts. b The feature effects on identifying suicide attempts. The color indicates the values of the features from high to low. The horizontal location shows whether the effect of the value leads to the prediction of suicide attempts. Each point is a SHAP value for a case and a feature. c The decision plot of XGBoost-2 predicting suicide attempts. Each line represents a case. From the bottom of the plot to the top, SHAP values for each feature are added to the base value of model, and each line strikes the x-axis at its corresponding observation’s predicted value to obtain prediction results. *IGT: IOWA gambling task, SST: suicide stroop task, HAMD-24:Hamilton Depression Scale-24 items, CTQ: Childhood Trauma Questionnaire

Back to article page