A Machine Learning Approach to Identifying the Thought Markers of Suicidal Subjects: A Prospective Multicenter Trial

Death by suicide demonstrates profound personal suffering and societal failure. While basic sciences provide the opportunity to understand biological markers related to suicide, computer science provides opportunities to understand suicide thought markers. In this novel prospective, multimodal, multicenter, mixed demographic study, we used machine learning to measure and fuse two classes of suicidal thought markers: verbal and nonverbal. Machine learning algorithms were used with the subjects’ words and vocal characteristics to classify 379 subjects recruited from two academic medical centers and a rural community hospital into one of three groups: suicidal, mentally ill but not suicidal, or controls. By combining linguistic and acoustic characteristics, subjects could be classified into one of the three groups with up to 85% accuracy. The results provide insight into how advanced technology can be used for suicide assessment and prevention.     

Contracting for Catastrophe:Legitimizing Emergency Constitutions by Drawing on Social Contract Theory

Res Publica - States of emergency are declared frequently in all parts of the world. Their declaration routinely implies a suspension of basic constitutional rights. In the last half century, it...     

Cognitive-behavioral treatment for social phobia in Parkinson's disease: A single-case study

Individuals with Parkinson's disease often exhibit symptoms of social anxiety. However, they rarely meet criteria for social phobia due to the medical exclusion criteria of DSM-IV. The present study reports the case of a 60-year-old male with Parkinson's disease who also met criteria for social phobia. After receiving 12 weekly cognitive-behavioral group sessions for social phobia, clinician ratings and self-report measures at post-treatment and 6-month follow-up showed a significant short-term and long-term reduction of his social anxiety. These findings suggest that cognitive-behavior therapy may be an effective treatment for social anxiety, even if these symptoms are related to Parkinson's disease.     

Body Mass Index Is an Important Predictor for Suicide: Results from a Systematic Review and Meta‐Analysis

Public health concerns for the independent management of obesity and suicidal behavior are rising. Emerging evidence suggests body weight plays an important role in quantifying the risk of suicide. In light of these findings, we aimed to clarify the association between body mass index (BMI) and suicidal behavior by systematically reviewing and evaluating the literature. Studies were identified by searching MEDLINE, EMBASE, PsycINFO, and CINAHL from inception to January 2015, supplemented by hand and grey literature searches. Study screening, data extraction, and risk of bias assessment were conducted in duplicate. We included 38 observational studies. Meta‐analyses supported an inverse association between BMI and completed suicide. Pooled summary estimates demonstrated that underweight was significantly associated with an increased risk of completed suicide (HR = 1.21, 95% CI 1.07 to 1.36, p = .002), and obesity (HR = 0.71, 95% CI 0.56 to 0.89, p = .003) and overweight (HR = 0.78, 95% CI 0.75 to 0.82, p < .0001) were significantly associated with a decreased risk of completed suicide relative to normal weight. A qualitative summary of the literature demonstrated conflicting evidence regarding the association between BMI and attempted suicide and revealed no association between BMI and suicidal ideation. BMI may be used to aid the assessment of suicide risk, especially that of completed suicide. However, unmeasured confounders and systematic biases of individual studies limit the quality of evidence.