Identifying a clinical signature of suicidality among patients with mood disorders: A pilot study using a machine learning approach

• Published in: Journal of affective disorders Vol. 193; pp. 109 - 116
• Main Authors: Passos, Ives Cavalcante, Mwangi, Benson, Cao, Bo, Hamilton, Jane E, Wu, Mon-Ju, Zhang, Xiang Yang, Zunta-Soares, Giovana B, Quevedo, Joao, Kauer-Sant’Anna, Marcia, Kapczinski, Flávio, Soares, Jair C
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 15-03-2016
• Subjects: Adolescent; Adult; Aged; Algorithms; Big data; Bipolar disorder; Comorbidity; Depression; Female; Humans; Machine Learning; Male; Middle Aged; Models, Statistical; Mood Disorders - epidemiology; Mood Disorders - psychology; Personalized medicine; Pilot Projects; Psychiatry; Reproducibility of Results; Risk Assessment - methods; Risk Factors; Suicide; Suicide - prevention & control; Suicide, Attempted - statistics & numerical data; Young Adult; Bipolar disorder; Depression; Big data; Suicide; Personalized medicine; Machine learning
• ISSN: 0165-0327; 1573-2517
• DOI: 10.1016/j.jad.2015.12.066

Abstract Objective A growing body of evidence has put forward clinical risk factors associated with patients with mood disorders that attempt suicide. However, what is not known is how to integrate clinical variables into a clinically useful tool in order to estimate the probability of an individual patient attempting suicide. Method A total of 144 patients with mood disorders were included. Clinical variables associated with suicide attempts among patients with mood disorders and demographic variables were used to ‘train’ a machine learning algorithm. The resulting algorithm was utilized in identifying novel or ‘unseen’ individual subjects as either suicide attempters or non-attempters. Three machine learning algorithms were implemented and evaluated. Results All algorithms distinguished individual suicide attempters from non-attempters with prediction accuracy ranging between 65% and 72% ( p <0.05). In particular, the relevance vector machine (RVM) algorithm correctly predicted 103 out of 144 subjects translating into 72% accuracy (72.1% sensitivity and 71.3% specificity) and an area under the curve of 0.77 ( p <0.0001). The most relevant predictor variables in distinguishing attempters from non-attempters included previous hospitalizations for depression, a history of psychosis, cocaine dependence and post-traumatic stress disorder (PTSD) comorbidity. Conclusion Risk for suicide attempt among patients with mood disorders can be estimated at an individual subject level by incorporating both demographic and clinical variables. Future studies should examine the performance of this model in other populations and its subsequent utility in facilitating selection of interventions to prevent suicide.