A genetically informed prediction model for suicidal and aggressive behaviour in teens

A novel prediction model for the probability of aggressive behavior in patients with mood disorders: Based on a cohort study

BACKGROUND

Accurately predicting the probability of aggressive behavior is crucial for guiding early intervention in patients with mood disorders.

METHODS

Cox stepwise regression was conducted to identify potential influencing factors. Nomogram prediction models were constructed to predict the probabilities of aggressive behavior in patients with mood disorders, and their performance was assessed using consistency index (C-index) and calibration plots.

RESULTS

Research findings on 321 patients with mood disorders indicated that being older (HR = 0.92, 95% CI: 0.86-0.98), single (HR = 0.11, 95% CI: 0.02-0.68), having children (one child, HR = 0.07, 95%CI: 0.01-0.87; more than one child, HR = 0.33, 95%CI: 0.04-2.48), living in dormitory (HR = 0.25, 95%CI: 0.08-0.77), non-student (employee, HR = 0.24, 95% CI: 0.07-0.88; non-employee, HR = 0.09, 95% CI: 0.02-0.35), and higher scores in subjective support (HR = 0.90, 95% CI: 0.82-0.99) were protective factors. On the contrary, minorities (HR = 5.26, 95% CI: 1.23-22.48), living alone (HR = 4.37, 95% CI: 1.60-11.94), having suicide history (HR = 2.51, 95% CI: 1.06-5.95), and having higher scores in EPQ-E (HR = 1.04, 95% CI: 1.00-1.08) and EPQ-P (HR = 1.03, 95% CI: 1.00-1.07) were identified as independent risk factors for aggressive behavior in patients with mood disorders. The nomogram prediction model demonstrated high discrimination and goodness-of-fit.

CONCLUSIONS

A novel nomogram prediction model for the probability of aggressive behavior in patients with mood disorders was developed, effective in identifying at-risk populations and offering valuable insights for early intervention and proactive measures.

Evidence for the biopsychosocial model of suicide: a review of whole person modeling studies using machine learning

Background

Traditional approaches to modeling suicide-related thoughts and behaviors focus on few data types from often-siloed disciplines. While psychosocial aspects of risk for these phenotypes are frequently studied, there is a lack of research assessing their impact in the context of biological factors, which are important in determining an individual's fulsome risk profile. To directly test this biopsychosocial model of suicide and identify the relative importance of predictive measures when considered together, a transdisciplinary, multivariate approach is needed. Here, we systematically review the emerging literature on large-scale studies using machine learning to integrate measures of psychological, social, and biological factors simultaneously in the study of suicide.

Methods

We conducted a systematic review of studies that used machine learning to model suicide-related outcomes in human populations including at least one predictor from each of biological, psychological, and sociological data domains. Electronic databases MEDLINE, EMBASE, PsychINFO, PubMed, and Web of Science were searched for reports published between August 2013 and August 30, 2023. We evaluated populations studied, features emerging most consistently as risk or resilience factors, methods used, and strength of evidence for or against the biopsychosocial model of suicide.

Results

Out of 518 full-text articles screened, we identified a total of 20 studies meeting our inclusion criteria, including eight studies conducted in general population samples and 12 in clinical populations. Common important features identified included depressive and anxious symptoms, comorbid psychiatric disorders, social behaviors, lifestyle factors such as exercise, alcohol intake, smoking exposure, and marital and vocational status, and biological factors such as hypothalamic-pituitary-thyroid axis activity markers, sleep-related measures, and selected genetic markers. A minority of studies conducted iterative modeling testing each data type for contribution to model performance, instead of reporting basic measures of relative feature importance.

Conclusion

Studies combining biopsychosocial measures to predict suicide-related phenotypes are beginning to proliferate. This literature provides some early empirical evidence for the biopsychosocial model of suicide, though it is marred by harmonization challenges. For future studies, more specific definitions of suicide-related outcomes, inclusion of a greater breadth of biological data, and more diversity in study populations will be needed.