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.
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%).
Distinct sources of stress have emerged during the COVID-19 pandemic. Particularly, fear is expected to generate significant psychological burden on individuals and influence on either unsafe behavior that may hinder recovery efforts or virus-mitigating behaviors. However, little is known about the properties of measures to capture them in research and clinical settings. To resolve this gap, we evaluated the psychometric properties of a novel measure of fear of illness and viruses and tested its predictive value for future development of distress. We extracted a random sample of 450 Chilean adult participants from a large cross-sectional survey panel and invited to participate in this intensive longitudinal study for 35 days. Of these, 163 ended up enrolling in the study after the demanding nature of the measurement schedule was clearly explained to them. For this final sample, we calculated different Confirmatory Factor Analyses (CFA) to evaluate the preliminary proposed structure for the instrument. Complementarily, we conducted a content analysis of the items to qualitatively extract its latent structure, which was also subject to empirical test via CFA. Results indicated that the original structure did not fit the data well; however, the new proposed structure based on the content analysis did. Overall, the modified instrument showed good reliability through all subscales both by its internal consistency with Cronbach’s alphas ranging from 0.814 to 0.913, and with test–retest correlations ranging from 0.715 to 0.804. Regarding its convergent validity, individuals who scored higher in fears tended to also score higher in depressive and posttraumatic stress symptoms at baseline. Furthermore, higher fears at baseline predicted a higher score in posttraumatic stress symptomatology 7 days later. These results provide evidence for the validity, reliability, and predictive performance of the scale. As the scale is free and multidimensional potentially not circumscribed to COVID-19, it might work as a step toward understanding the psychological impact of current and future pandemics, or further life-threatening health situations of similar characteristics. Limitations, practical implications, and future directions for research are discussed.
Se estudió la relación entre estilo de vivencia depresiva, satisfacción familiar, malestar en las relaciones interpersonales y conducta suicida en 405 consultantes a salud mental en la Región Metropolitana, Chile, a través de una muestra intencionada. Se clasificaron en: intento de suicidio de alta gravedad, intento de suicidio de baja gravedad, ideación suicida y sin conducta suicida. Se utilizaron los instrumentos DEQ, OQ-45.2, APGAR, RFL, Escala de Riesgo-Rescate y Escala de Intención Suicida. Se realizaron ANOVA, 2 y modelos de mediación y moderación de procesos condicionales. El grupo con intento suicida de alta gravedad mostró una predominancia del estilo dependiente. Hubo una alta presencia del estilo autocrítico en la muestra total, especialmente en el grupo con ideación suicida. Los grupos con riesgo suicida presentaron mayores índices disfuncionales de malestar interpersonal y una mayor percepción de disfuncionalidad familiar grave que el grupo sin conducta suicida. La satisfacción con el funcionamiento familiar mostró un efecto en la intencionalidad de morir al momento del intento de suicidio. Estos resultados subrayan la importancia del funcionamiento familiar y las relaciones interpersonales en el riesgo suicida.Palabras clave: suicidio, relaciones familiares, relaciones interpersonales, trastorno depresivo, riesgo suicidaThe relationship between depressive experience style, family satisfaction, discomfort in interpersonal relationships, and suicidal behavior was studied in a purposive sample of 405 mental health patients in the Metropolitan Region of Chile. They were classified into high severity suicide attempt, low severity suicide attempt, suicidal ideation, and no suicidal behavior. The instruments used were: DEQ, OQ-45.2, APGAR, RFL, Risk-Rescue Rating Scale, and Suicidal Intent Scale. ANOVA, 2 , and models of mediation and moderation of conditional processes were conducted. The high severity suicide attempt group showed a significant predominance of the dependent style compared with the group without suicidal behavior. There was a high presence of the self-critical style throughout the sample, especially in the suicidal ideation group. The groups with suicide risk had higher dysfunctional rates of interpersonal discomfort and a greater perception of severe family dysfunction than the group without suicidal behavior. Satisfaction with family functioning was observed to influence the intention to die at the time of the suicide attempt. These results underscore the importance of family functioning and interpersonal relationships in suicide risk.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.