Objective: To analyze suicidal behavior and build a predictive model for suicide risk using data mining (DM) analysis. Methods: A study of 707 Chilean mental health patients (with and without suicide risk) was carried out across three healthcare centers in the Metropolitan Region of Santiago, Chile. Three hundred fortythree variables were studied using five questionnaires. DM and machine-learning tools were used via the support vector machine technique. Results: The model selected 22 variables that, depending on the circumstances in which they all occur, define whether a person belongs in a suicide risk zone (accuracy = 0.78, sensitivity = 0.77, and specificity = 0.79). Being in a suicide risk zone means patients are more vulnerable to suicide attempts or are thinking about suicide. The interrelationship between these variables is highly nonlinear, and it is interesting to note the particular ways in which they are configured for each case. The model shows that the variables of a suicide risk zone are related to individual unrest, personal satisfaction, and reasons for living, particularly those related to beliefs in one's own capacities and coping abilities. Conclusion: These variables can be used to create an assessment tool and enables us to identify individual risk and protective factors. This may also contribute to therapeutic intervention by strengthening feelings of personal well-being and reasons for staying alive. Our results prompted the design of a new clinical tool, which is fast and easy to use and aids in evaluating the trajectory of suicide risk at a given moment.

No abstract

aim: In efforts to develop reliable methods to detect the likelihood of impending suicidal behaviors, we have proposed the following.Objective: To gain a deeper understanding of the state of suicide risk by determining the combination of variables that distinguishes between groups with and without suicide risk.Method: A study involving 707 patients consulting for mental health issues in three health centers in Greater Santiago, Chile. Using 345 variables, an analysis was carried out with artificial intelligence tools, Cross Industry Standard Process for Data Mining processes, and decision tree techniques. The basic algorithm was top-down, and the most suitable division produced by the tree was selected by using the lowest Gini index as a criterion and by looping it until the condition of belonging to the group with suicidal behavior was fulfilled.results: Four trees distinguishing the groups were obtained, of which the elements of one were analyzed in greater detail, since this tree included both clinical and personality variables. This specific tree consists of six nodes without suicide risk and eight nodes with suicide risk (tree decision 01, accuracy 0.674, precision 0.652, recall 0.678, specificity 0.670, F measure 0.665, receiver operating characteristic (ROC) area under the curve (AUC) 73.35%; tree decision 02, accuracy 0.669, precision 0.642, recall 0.694, specificity 0.647, F measure 0.667, ROC AUC 68.91%; tree decision 03, accuracy 0.681, precision 0.675, recall 0.638, specificity 0.721, F measure, 0.656, ROC AUC 65.86%; tree decision 04, accuracy 0.714, precision 0.734, recall 0.628, specificity 0.792, F measure 0.677, ROC AUC 58.85%).

No abstract