Fig. 4From: Can cognition help predict suicide risk in patients with major depressive disorder? A machine learning studyThe force plot for decision process of XGBoost-2 evaluating whether two MDD patients in test set had suicide attempts. Each feature provides a SHAP value for the base value of model. The final prediction value, f (x), are obtained according to the weight of features and the processing of the machine learning algorithm. When f (x) > 0, the model considers the case as DSA, otherwise it is considered as DNS. *IGT: IOWA gambling task, SST: suicide stroop task, HAMD-24:Hamilton Depression Scale-24 items, CTQ: Childhood Trauma QuestionnaireBack to article page