5-year incidence of suicide-risk in youth: A gradient tree boosting and SHAP study.

BACKGROUND: Machine learning methods for suicidal behavior so far have failed to be implemented as a prediction tool. In order to use the capabilities of machine learning to model complex phenomenon, we assessed the predictors of suicide risk using state-of-the-art model explanation methods. METHODS: Prospective cohort study including a community sample of 1,560 young adults aged between 18 and 24. The first wave took place between 2007 and 2009, and the second wave took place between 2012 and 2014. Sociodemographic and clinical characteristics were assessed at baseline. Incidence of suicide risk at five-years of follow-up was the main outcome. The outcome was assessed using the Mini Neuropsychiatric Interview (MINI) at both waves. RESULTS: The risk factors for the incidence of suicide risk at follow-up were: female sex, lower socioeconomic status, older age, not studying, presence of common mental disorder symptoms, and poor quality of life. The interaction between overall health and socioeconomic status in relation to suicide risk was also captured and shows a shift from protection to risk by socioeconomic status as overall health increases. LIMITATIONS: Proximal factors associated with the incidence of suicide risk were not assessed. CONCLUSIONS: Our findings indicate that factors related to poor quality of life, not studying, and common mental disorder symptoms of young adults are already in place prior to suicide risk. Most factors present critical non-linear patterns that were identified. These findings are clinically relevant because they can help clinicians to early detect suicide risk.

Lifetime cocaine use is a potential predictor for conversion from major depressive disorder to bipolar disorder: A prospective study.

AIM: We aimed to identify whether lifetime cocaine use is a risk factor for conversion from major depressive disorder (MDD) to bipolar disorder (BD) in an outpatient sample of adults. METHODS: This prospective cohort study included 585 subjects aged 18 to 60 years who had been diagnosed with MDD as assessed by the Mini International Neuropsychiatric Interview (MINI-Plus) at baseline (2012-2015). Subjects were reassessed a mean of 3 years later (2017-2018) for potential conversion to BD as assessed by the MINI-Plus. Lifetime cocaine use was assessed using the Alcohol, Smoking, and Substance Involvement Screening Test. RESULTS: In the second wave, we had 117 (20%) losses, and 468 patients were reassessed. The rate of conversion from MDD to BD in 3 years was 12.4% (n = 58). A logistic regression analysis showed that the risk for conversion from MDD to BD was 3.41-fold higher (95% confidence interval, 1.11-10.43) in subjects who reported lifetime cocaine use at baseline as compared to individuals who did not report lifetime cocaine use at baseline, after adjusting for demographic and clinical confounders. CONCLUSION: These findings showed that lifetime cocaine use is a potential predictor of conversion to BD in an MDD cohort. Further studies are needed to assess the possible underlying mechanisms linking exposure to cocaine with BD conversion.

Serum level of nerve growth factor is a potential biomarker of conversion to bipolar disorder in women with major depressive disorder.

AIM: The aim of this study was to identify biomarkers associated with major depressive disorder (MDD) and conversion from MDD to bipolar disorder (BD) in an outpatient sample of women. METHODS: This was a longitudinal study including women diagnosed with MDD and aged 18 to 60 years. The follow-up was 3 years. The diagnosis was performed using the Mini International Neuropsychiatric Interview Plus. Blood collection was just performed in the first phase. Serum interleukin-6, tumor necrosis factor-α, brain-derived neurotrophic factor, glial cell-derived neurotrophic factor, and nerve growth factor (NGF) levels were measured using a commercial immunoassay kit. RESULTS: We included 156 women. The conversion rate from MDD to BD was 15.4% (n = 24). NGF serum levels were increased in patients who converted to BD compared to the remitted MDD group and current MDD group (P = 0.013). The Bonferroni post-hoc test for multiple comparisons revealed significant differences for higher NGF levels in patients who converted to BD compared to patients with current MDD (P = 0.037). Interleukin-6, tumor necrosis factor-α, brain-derived neurotrophic factor, and glial cell-derived neurotrophic factor serum levels did not differ among the groups. CONCLUSION: Our results suggest that NGF might be a useful biomarker associated with early detection of conversion to BD, helping clinicians in the clinical diagnosis.