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.     

Using Structured Telephone Follow‐up Assessments to Improve Suicide‐Related Adverse Event Detection

Adverse event (AE) detection and reporting practices were compared during the first phase of the Emergency Department Safety Assessment and Follow‐up Evaluation (ED‐SAFE), a suicide intervention study. Data were collected using a combination of chart reviews and structured telephone follow‐up assessments postenrollment. Beyond chart reviews, structured telephone follow‐up assessments identified 45% of the total AEs in our study. Notably, detection of suicide attempts significantly varied by approach with 53 (18%) detected by chart review, 173 (59%) by structured telephone follow‐up assessments, and 69 (23%) marked as duplicates. Findings provide support for utilizing multiple methods for more robust AE detection in suicide research.     

Perceived Racism and Suicide Ideation: Mediating Role of Depression but Moderating Role of Religiosity among African American Adults

Suicide is a public health problem for African Americans who are young and of working age. The purpose of this study was to examine mediated and moderated effects of perceived racism on suicide ideation in a community sample of 236 African American men and women. Measures of suicide ideation, depression symptoms, intrinsic/extrinsic religiosity, and perceived racism were administered. Perceived racial discrimination was directly and indirectly associated with suicide ideation. For participants who reported low levels of extrinsic religiosity, the mediated effect of perceived racism (via depression symptoms) was significant. These findings provide some insight into suicide vulnerability for specific subgroups of African Americans.     

Self‐Efficacy to Avoid Suicidal Action: Factor Structure and Convergent Validity among Adults in Substance Use Disorder Treatment

Individuals with substance use disorders (SUDs) are at high risk of suicidal behaviors, highlighting the need for an improved understanding of potentially influential factors. One such domain is self‐efficacy to manage suicidal thoughts and impulses. Psychometric data about the Self‐Efficacy to Avoid Suicidal Action (SEASA) Scale within a sample of adults seeking SUD treatment (N = 464) is provided. Exploratory factor analysis supported a single self‐efficacy construct. Lower SEASA scores, or lower self‐efficacy, were reported in those with more severe suicidal ideation and those with more suicide attempts, providing evidence for convergent validity. Implications of measuring self‐efficacy in the context of suicide risk assessment are discussed.     

Drug Ingestions in Children 10–14 Years Old: An Old Problem Revisited

To determine changes in rates of drug ingestions in 10–14 year old children in our country, a retrospective chart review of 10–14 year olds hospitalized for drug ingestion between 1993–1995 and 2000–2004 was performed. Odds ratios and Chi‐square were used for analyses. From 1993–1995 there were 92.8 ingestions/100,000 children/year; from 2000–2004 there were 63.3 ingestions/100,000 children/year. More males ingested in 2000–2004 than 1993–1995 (26.3% vs. 14.2% O.R. 2.15 [1.19, 3.92]). More patients took psychiatric medications in 2000–2004 than 1993–1995 (38.9% vs. 27.0%, O.R. 1.72 [1.06, 2.80]). More patients ingested SSRIs in 2000–2004 than 1993–1995; fewer ingested tricyclics. Hospitalization rates for drug ingestions have decreased. There has been a change in drug ingested, and more males are ingesting drugs.     

Demographic,Clinical, and Service Utilization Factors Associated with Suicide‐Related Visits among Alaska Native and American Indian Adults

Alaska Native and American Indian people (AN/AIs) are disproportionately affected by suicide. Within a large AN/AI health service organization, demographic, clinical, and service utilization factors were compared between those with a suicide‐related health visit and those without. Cases had higher odds of a behavioral health diagnosis, treatment for an injury, behavioral health specialty care visits, and opioid medication dispensation in the year prior to a suicide‐related visit compared to gender‐, age‐, and residence‐ (urban versus rural) matched controls. Odds of a suicide‐related visit were lower among those with private insurance and those with non‐primary care ambulatory clinic visits.     

Identification,Response, and Referral of Suicidal Youth Following Applied Suicide Intervention Skills Training

Gatekeeper training is a public health approach to suicide prevention that encourages community members to identify those at risk for suicide, respond appropriately, and refer for clinical services. Despite widespread use, few studies have examined whether training results in behavior change in participants. This study employed a naturalistic pre–post design to follow 434 participants in Applied Suicide Intervention Skills Training, finding small but significant increases in self‐reported identification of at‐risk youth, some helpful responses to youth, and numbers of youth referred to treatment from pre‐test to 6‐ to 9‐month follow‐up. Changes in active listening and helping behaviors meant to support treatment referrals (such as convincing a youth to seek treatment) were not observed over time. Additional analyses explored predictors of self‐reported skill utilization including identification as a “natural helper” and attitudes about suicide prevention.     

Paradoxes of qualitative research

In qualitative research paradoxes abound in research design, sampling, generalisation, ethics and the behaviour of the researcher. The ultimate paradox is that qualitative inquiry is impossible — both conceptually and practically — yet it still goes on. It must do so if the professions of counselling and psychotherapy are to advance.     

Self-guided behavioral skills training: A public health approach to promoting nurturing care environments

The World Health Organization identified the promotion of “Nurturing Care Environments” as a global health priority. Responsive caregiving, 1 of 5 domains describing nurturing care, is critical for healthy child development. Relatively little research has evaluated population-level interventions aimed to increase responsive caregiving during the first 1,000 days of an infant's life. In this pilot study, we evaluated an intervention designed for population-level dissemination that targeted responsive caregiving. The self-guided behavioral skills training aimed to teach mothers to imitate infant vocalizations. The intervention was delivered within an on-line asynchronous training. All 3 mothers increased vocal imitative behavior following training without receiving coaching or behavior-specific feedback from an implementer. The results offer a preliminary proof of concept with implications for population-level intervention design and evaluation.