RESUMO
OBJECTIVE: We set forth to build a prediction model of individuals who would develop bipolar disorder (BD) using machine learning techniques in a large birth cohort. METHODS: A total of 3748 subjects were studied at birth, 11, 15, 18, and 22 years of age in a community birth cohort. We used the elastic net algorithm with 10-fold cross-validation to predict which individuals would develop BD at endpoint (22 years) at each follow-up visit before diagnosis (from birth up to 18 years). Afterward, we used the best model to calculate the subgroups of subjects at higher and lower risk of developing BD and analyzed the clinical differences among them. RESULTS: A total of 107 (2.8%) individuals within the cohort presented with BD type I, 26 (0.6%) with BD type II, and 87 (2.3%) with BD not otherwise specified. Frequency of female individuals was 58.82% (n = 150) in the BD sample and 53.02% (n = 1868) among the unaffected population. The model with variables assessed at the 18-year follow-up visit achieved the best performance: AUC 0.82 (CI 0.75-0.88), balanced accuracy 0.75, sensitivity 0.72, and specificity 0.77. The most important variables to detect BD at the 18-year follow-up visit were suicide risk, generalized anxiety disorder, parental physical abuse, and financial problems. Additionally, the high-risk subgroup of BD showed a high frequency of drug use and depressive symptoms. CONCLUSIONS: We developed a risk calculator for BD incorporating both demographic and clinical variables from a 22-year birth cohort. Our findings support previous studies in high-risk samples showing the significance of suicide risk and generalized anxiety disorder prior to the onset of BD, and highlight the role of social factors and adverse life events.
Assuntos
Transtornos de Ansiedade/psicologia , Transtorno Bipolar/diagnóstico , Depressão/psicologia , Vigilância da População , Medição de Risco/métodos , Algoritmos , Transtornos de Ansiedade/epidemiologia , Transtorno Bipolar/epidemiologia , Transtorno Bipolar/psicologia , Estudos de Coortes , Depressão/epidemiologia , Feminino , Humanos , Aprendizado de Máquina , Masculino , Abuso Físico , Valor Preditivo dos Testes , Fatores Socioeconômicos , Transtornos Relacionados ao Uso de Substâncias/epidemiologia , Suicídio/estatística & dados numéricos , Adulto JovemRESUMO
OBJECTIVE: To identify factors associated with a history of suicide attempt in medical students. METHODS: A Web-based survey was sent out to a sample of medical students. A multi-predictor Poisson regression was performed to identify factors associated with a history of suicide attempt. In addition, an elastic net regularization was used to build a risk calculator to identify students at risk for attempted suicide. RESULTS: A total of 4,840 participants were included in the study. Prevalence of suicide attempts in the sample was 8.94%. Risk factors associated with past suicide attempt in the multi-predictor Poisson regression were as follows: female gender (P < 0.001); homosexuality (P < 0.001); low income (P = 0.026); bullying by university peers (P = 0.006); childhood (P = 0.001) or adult (P = 0.001) trauma; family history of suicide (P = 0.005); suicidal ideation within the last month (P < 0.001); daily tobacco use (P = 0.037); and being at severe risk for alcohol abuse (P = 0.023). Our elastic net model performed well with an AUC of 0.83. CONCLUSIONS: This study identifies a number of key factors associated with a history of suicide attempts among medical students. Future longitudinal studies should assess the causal relationship between these factors and suicide attempts. Additionally, these results demonstrate that current available data on suicide attempts among medical students can be used to develop an accurate risk algorithm.
Assuntos
Estudantes de Medicina/psicologia , Ideação Suicida , Tentativa de Suicídio/estatística & dados numéricos , Adolescente , Adulto , Brasil/epidemiologia , Bullying/estatística & dados numéricos , Feminino , Humanos , Masculino , Prevalência , Fatores de Risco , Fatores Sexuais , Inquéritos e Questionários , Adulto JovemRESUMO
AIM: Few personalised medicine investigations have been conducted for mental health. We aimed to generate and validate a risk tool that predicts adult attention-deficit/hyperactivity disorder (ADHD). METHODS: Using logistic regression models, we generated a risk tool in a representative population cohort (ALSPAC - UK, 5113 participants, followed from birth to age 17) using childhood clinical and sociodemographic data with internal validation. Predictors included sex, socioeconomic status, single-parent family, ADHD symptoms, comorbid disruptive disorders, childhood maltreatment, ADHD symptoms, depressive symptoms, mother's depression and intelligence quotient. The outcome was defined as a categorical diagnosis of ADHD in young adulthood without requiring age at onset criteria. We also tested Machine Learning approaches for developing the risk models: Random Forest, Stochastic Gradient Boosting and Artificial Neural Network. The risk tool was externally validated in the E-Risk cohort (UK, 2040 participants, birth to age 18), the 1993 Pelotas Birth Cohort (Brazil, 3911 participants, birth to age 18) and the MTA clinical sample (USA, 476 children with ADHD and 241 controls followed for 16 years from a minimum of 8 and a maximum of 26 years old). RESULTS: The overall prevalence of adult ADHD ranged from 8.1 to 12% in the population-based samples, and was 28.6% in the clinical sample. The internal performance of the model in the generating sample was good, with an area under the curve (AUC) for predicting adult ADHD of 0.82 (95% confidence interval (CI) 0.79-0.83). Calibration plots showed good agreement between predicted and observed event frequencies from 0 to 60% probability. In the UK birth cohort test sample, the AUC was 0.75 (95% CI 0.71-0.78). In the Brazilian birth cohort test sample, the AUC was significantly lower -0.57 (95% CI 0.54-0.60). In the clinical trial test sample, the AUC was 0.76 (95% CI 0.73-0.80). The risk model did not predict adult anxiety or major depressive disorder. Machine Learning approaches did not outperform logistic regression models. An open-source and free risk calculator was generated for clinical use and is available online at https://ufrgs.br/prodah/adhd-calculator/. CONCLUSIONS: The risk tool based on childhood characteristics specifically predicts adult ADHD in European and North-American population-based and clinical samples with comparable discrimination to commonly used clinical tools in internal medicine and higher than most previous attempts for mental and neurological disorders. However, its use in middle-income settings requires caution.
Assuntos
Transtorno do Deficit de Atenção com Hiperatividade/epidemiologia , Maus-Tratos Infantis/estatística & dados numéricos , Transtorno da Conduta/epidemiologia , Depressão/epidemiologia , Inteligência , Família Monoparental/estatística & dados numéricos , Classe Social , Adolescente , Área Sob a Curva , Transtorno do Deficit de Atenção com Hiperatividade/psicologia , Transtornos de Deficit da Atenção e do Comportamento Disruptivo/epidemiologia , Transtornos de Deficit da Atenção e do Comportamento Disruptivo/psicologia , Criança , Estudos de Coortes , Transtorno da Conduta/psicologia , Depressão/psicologia , Transtorno Depressivo , Feminino , Humanos , Testes de Inteligência , Modelos Logísticos , Masculino , Mães/psicologia , Estudos Prospectivos , Reprodutibilidade dos Testes , Medição de Risco , Fatores Sexuais , Reino Unido/epidemiologia , Adulto JovemRESUMO
OBJECTIVE: We aimed to review clinical features and biological underpinnings related to neuroprogression in bipolar disorder (BD). Also, we discussed areas of controversy and future research in the field. METHOD: We systematically reviewed the extant literature pertaining to neuroprogression and BD by searching PubMed and EMBASE for articles published up to March 2016. RESULTS: A total of 114 studies were included. Neuroimaging and clinical evidence from cross-sectional and longitudinal studies show that a subset of patients with BD presents a neuroprogressive course with brain changes and unfavorable outcomes. Risk factors associated with these unfavorable outcomes are number of mood episodes, early trauma, and psychiatric and clinical comorbidity. CONCLUSION: Illness trajectories are largely variable, and illness progression is not a general rule in BD. The number of manic episodes seems to be the clinical marker more robustly associated with neuroprogression in BD. However, the majority of the evidence came from cross-sectional studies that are prone to bias. Longitudinal studies may help to identify signatures of neuroprogression and integrate findings from the field of neuroimaging, neurocognition, and biomarkers.