Predicting suicidal behaviours using clinical instruments: systematic review and meta-analysis of positive predictive values for risk scales

Collaboration matters: A randomized controlled trial of patient-clinician collaboration in suicide risk assessment and intervention

BACKGROUND

Clinician collaboration can help high-risk individuals to manage their suicidal crises. However, limited research has directly examined how higher patient-clinician collaboration during assessment and intervention can effectively reduce suicidal ideation. This novel randomized clinical trial compared a high vs. low level of patient-clinician collaboration by pairing commonly used assessment (Structured Interview vs. Narrative Assessment) and intervention approaches (Safety Planning Intervention vs. Crisis Response Planning). We hypothesized that the interventions involving higher (than lower) patient-clinician collaboration during assessment (Narrative Assessment) or intervention (Crisis Response Planning) would lead to larger reductions in suicidal ideation.

METHODS

Eighty-two participants with a history of suicide ideation and/or attempts were randomly assigned to one of the four interventions varying in patient-clinician collaboration. After attrition, sixty-six participants completed the study. Suicidal ideation via ecological momentary assessment was measured 14 days before and 14 days after treatment.

RESULTS

Although the severity of suicidal ideation decreased in all groups, the two groups that included highly collaborative assessment had larger pre-post reductions in suicidal ideation (Narrative Assessment+Safety Plan; dwithin = 0.26, and Narrative Assessment+Crisis Response Plan; dwithin = 0.19) than the groups that included a checklist-based assessment (Structured Interview).

LIMITATIONS

Longer follow-up periods with a larger sample would have provided an understanding of the durability of intervention effects.

CONCLUSION

Results suggest that the inclusion of higher patient-clinician collaboration techniques during suicide risk assessment can effectively reduce suicidal thoughts. Thus, clinician-led collaborative risk assessment approaches can enhance the effects of safety planning-type interventions among patients with elevated risk for suicide versus checklist-based assessment approaches.

Development and external validation of a logistic and a penalized logistic model using machine-learning techniques to predict suicide attempts: A multicenter prospective cohort study in Korea

Despite previous efforts to build statistical models for predicting the risk of suicidal behavior using machine-learning analysis, a high-accuracy model can lead to overfitting. Furthermore, internal validation cannot completely address this problem. In this study, we created models for predicting the occurrence of suicide attempts among Koreans at high risk of suicide, and we verified these models in an independent cohort. We performed logistic and penalized regression for suicide attempts within 6 months among suicidal ideators and attempters in The Korean Cohort for the Model Predicting a Suicide and Suicide-related Behavior (K-COMPASS). We then validated the models in a test cohort. Our findings indicated that several factors significantly predicted suicide attempts in the models, including young age, suicidal ideation, previous suicidal attempts, anxiety, alcohol abuse, stress, and impulsivity. The area under the curve and positive predictive values were 0.941 and 0.484 after variable selection and 0.751 and 0.084 in the test cohort. The corresponding values for the penalized regression model were 0.943 and 0.524 in the original training cohort and 0.794 and 0.115 in the test cohort. The prediction model constructed through a prospective cohort study of the suicide high-risk group showed satisfactory accuracy even in the test cohort. The accuracy with penalized regression was greater than that with the "classical" logistic model.

The association between ketamine and esketamine and suicidality: reports to the Food And Drug Administration Adverse Event Reporting System (FAERS)

INTRODUCTION

Replicated evidence indicates that ketamine and esketamine reduce measures of suicidality in persons with treatment-resistant depression (TRD). It remains uncertain whether individuals experience worsening of preexisting suicidality with either agent.

RESEARCH DESIGN AND METHODS

The Food and Drug Administration Adverse Event Reporting System (FAERS) database was searched from 1970 and 2019 to 30 September 2023 for reports of suicidal ideation, depression suicidal, suicidal behavior, suicidal attempt, and completed suicide in association with ketamine and esketamine exposure, respectively. We present reporting odds ratios (ROR) significance was determined when the lower limit of the 95% confidence interval (CI) exceeded 1.0. Lithium was used as the control agent.

RESULTS

Observed a higher ROR for suicidal ideation (ROR 7.58, 95% CI 6.34-9.07) and depression suicidal (ROR 14.19, 95% CI 1.80-112.07) with esketamine. Significantly lower RORs were observed for suicide attempt with ketamine (ROR 0.15, 95% CI 0.11-0.21) and esketamine (ROR 0.57, 95% CI 0.48-0.67).

CONCLUSIONS

Mixed RORs across aspects of suicidality were observed with ketamine and esketamine. Limitations of the FAERS database prevent any determination of causal effects new onset suicidality to either agent. The lower RORs for suicide attempt with ketamine and esketamine is noted but cannot be interpreted as a direct therapeutic effect.

Canadian Network for Mood and Anxiety Treatments (CANMAT) 2023 Update on Clinical Guidelines for Management of Major Depressive Disorder in Adults: Réseau canadien pour les traitements de l'humeur et de l'anxiété (CANMAT) 2023 : Mise à jour des lignes directrices cliniques pour la prise en charge du trouble dépressif majeur chez les adultes

BACKGROUND

The Canadian Network for Mood and Anxiety Treatments (CANMAT) last published clinical guidelines for the management of major depressive disorder (MDD) in 2016. Owing to advances in the field, an update was needed to incorporate new evidence and provide new and revised recommendations for the assessment and management of MDD in adults.

METHODS

CANMAT convened a guidelines editorial group comprised of academic clinicians and patient partners. A systematic literature review was conducted, focusing on systematic reviews and meta-analyses published since the 2016 guidelines. Recommendations were organized by lines of treatment, which were informed by CANMAT-defined levels of evidence and supplemented by clinical support (consisting of expert consensus on safety, tolerability, and feasibility). Drafts were revised based on review by patient partners, expert peer review, and a defined expert consensus process.

RESULTS

The updated guidelines comprise eight primary topics, in a question-and-answer format, that map a patient care journey from assessment to selection of evidence-based treatments, prevention of recurrence, and strategies for inadequate response. The guidelines adopt a personalized care approach that emphasizes shared decision-making that reflects the values, preferences, and treatment history of the patient with MDD. Tables provide new and updated recommendations for psychological, pharmacological, lifestyle, complementary and alternative medicine, digital health, and neuromodulation treatments. Caveats and limitations of the evidence are highlighted.

CONCLUSIONS

The CANMAT 2023 updated guidelines provide evidence-informed recommendations for the management of MDD, in a clinician-friendly format. These updated guidelines emphasize a collaborative, personalized, and systematic management approach that will help optimize outcomes for adults with MDD.

Prediction of suicidal ideation among preadolescent children with machine learning models: A longitudinal study

BACKGROUND

Machine learning (ML) has been widely used to predict suicidal ideation (SI) in adolescents and adults. Nevertheless, studies of accurate and efficient models of SI prediction with preadolescent children are still needed because SI is surprisingly prevalent during the transition into adolescence. This study aimed to explore the potential of ML models to predict SI among preadolescent children.

METHODS

A total of 4691 Chinese children (54.89 % boys, Mage = 10.92 at baseline) and their parents completed relevant measures at baseline and the children provided 6-month follow-up data for SI. The current study compared four ML models: Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), and Multilayer Perceptron (MLP), to predict SI and to identify variables with predictive value based on the best-performing model among Chinese preadolescent children.

RESULTS

The RF model achieved the highest discriminant performance with an AUC of 0.92, accuracy of 0.93 (balanced accuracy = 0.88). The factors of internalizing problems, externalizing problems, neuroticism, childhood maltreatment, and subjective well-being in school demonstrated the highest values in predicting SI.

CONCLUSION

The findings of this study suggested that ML models based on the observation and assessment of children's general characteristics and experiences in everyday life can serve as convenient screening and evaluation tools for suicide risk assessment among Chinese preadolescent children. The findings also provide insights for early intervention.

Alterations in performance and discriminating power of the death/suicide implicit association test across the lifespan

The Death/Suicide Implicit Association Test (d/s-IAT) has differentiated individuals with prior and prospective suicide attempts in previous studies, however, age effects on test results remains to be explored. A three-site study compared performance on the d/s-IAT among participants aged 16-80 years with depression and prior suicide attempt (n = 82), with depression and no attempts (n = 80), and healthy controls (n = 86). Outcome measures included the standard difference (D) score, median reaction times, and error rates. Higher D scores represent a stronger association between death/suicide and self, while lower scores represent a stronger association between life and self. The D scores differed significantly among groups overall. Participants with depression exhibited higher scores compared to healthy controls, but there was no difference between participants with and without prior suicide attempts(F[2,242]=8.76, p<.001). Response times for participants with prior attempts differed significantly from other groups, with no significant differences in error rates. The D score was significantly affected by age (β =-0.007, t = 3.65, p<.001), with slowing of response times in older ages. Results suggest reaction time d/s-IAT D scores may not distinguish implicit thinking about suicide as response times slow with age, but slowed response times may be sensitive to suicide risk potentially indicating basic information processing deficits.

Ethological Problems with the Interpersonal Theory of Suicide

Joiner and colleagues' Interpersonal Theory of Suicide (IPTS), a prominent "desire-capability" model of suicide-based on the common-sense idea that people take their own lives because they want to, and can-is critiqued from a biological perspective. Tinbergen's ethological "four questions" guide the analysis: evolution, survival value, ontogeny, and proximate causation, each addressing a different aspect of biological understanding. Problems for IPTS emerge with all four. As a parsimonious solution, the desire-capability hypothesis is reconceived as an ultimate, instead of proximate, mode of explanation. By this light, desire and capability for suicide combined in our species' ancestral past, thus making suicide a recurrent survival threat, and driving the evolution of special-purpose defensive adaptations. This stance tallies with the pain-brain theory of the evolution of suicide, and with Joiner and colleagues' own investigation into organismic anti-suicide defenses, which appears to conflict conceptually with IPTS. These defenses' evolved algorithm may make suicide an intrinsically aleatory phenomenon, opaque to usefully accurate prediction. Positive implications for prevention and research are proposed.

A systematic review of the studies testing the integrated motivational-volitional model of suicidal behaviour

Despite the influence of the integrated motivational-volitional (IMV)1 model on research and practice, the supporting literature has not been systematically synthesised. This systematic review aims to synthesise the literature testing the IMV model of suicidal behaviour. Using citation and database searching, PsycINFO, EMBASE, PubMed, Web of Science, and Google Scholar were searched for studies referencing the IMV model (last searched on 28th March 2023). Included studies empirically tested the hypotheses of the model. Quality assessment was conducted using the National Institute of Health tool. Findings from 98 records (100 studies, 138,365 participants) were narratively synthesised. Results from studies directly testing the hypothesised pathways of the model supported the defeat-entrapment-suicidal ideation pathway of the IMV model. Case-control studies comparing differences between control, ideation, and enactment groups were consistent with hypotheses in univariate and cross-sectional analyses. However, support for the model was mixed for case-control multivariate and prospective studies. Due to low overlap in variables studied, the role of specific pre-motivational phase variables and stage-specific moderators was inconclusive. The studies received overall good quality ratings. The IMV model presents a promising framework for understanding and preventing suicide. Defeat, entrapment, and key variables may be useful in informing suicide prevention measures.

Prevalence of suicidal ideation in German psychotherapy outpatients: A large multicenter assessment

BACKGROUND

Suicidal ideation is a major concern in clinical practice. Yet, little is known about prevalence rates of suicidal ideation in patients undergoing outpatient psychotherapeutic treatment. Therefore, the aim of the current study is to assess the prevalence of suicidal ideation in a large sample of psychotherapy outpatients in Germany. The data analyzed in this study is taken from the KODAP-project on the coordination of data collection and analysis at German university-based research and training outpatient clinics for psychotherapy.

METHODS

A total of N = 10,357 adult outpatients (64.4 % female; age: M(SD) = 35.94 (13.54), range: 18-92 years of age) starting cognitive-behavioral therapy at one of 27 outpatient clinics in Germany were included in the current study. Prevalence of suicidal ideation was assessed with the Suicide Item (Item 9) of the Beck-Depression Inventory II.

RESULTS

Suicidal ideation was reported by 36.7 % (n = 3795) of the participants. Borderline Personality Disorder, Posttraumatic Stress Disorder, and recurrent Major Depression were the diagnoses most strongly associated with the presence and severity of suicidal ideation.

LIMITATION

Suicide ideation was assessed only with the respective item of the Beck Depression Inventory II.

CONCLUSION

Suicidal ideation is very common among adult patients who start psychotherapy in Germany. A well-founded knowledge of risk assessment in suicidal patients and suicide-specific treatment options is therefore highly relevant.

Developing a risk prediction model for death at first suicide attempt-Identifying risk factors from Thailand's national suicide surveillance system data

More than 60% of suicides globally are estimated to take place in low- and middle-income nations. Prior research on suicide has indicated that over 50% of those who die by suicide do so on their first attempt. Nevertheless, there is a dearth of knowledge on the attributes of individuals who die on their first attempt and the factors that can predict mortality on the first attempt in these regions. The objective of this study was to create an individual-level risk-prediction model for mortality on the first suicide attempt. We analyzed records of individuals' first suicide attempts that occurred between May 1, 2017, and April 30, 2018, from the national suicide surveillance system, which includes all of the provinces of Thailand. Subsequently, a risk-prediction model for mortality on the first suicide attempt was constructed utilizing multivariable logistic regression and presented through a web-based application. The model's performance was assessed by calculating the area under the receiver operating curve (AUC), as well as measuring its sensitivity, specificity, and accuracy. Out of the 3,324 individuals who made their first suicide attempt, 50.5% of them died as a result of that effort. Nine out of the 21 potential predictors demonstrated the greatest predictive capability. These included male sex, age over 50 years old, unemployment, having a depressive disorder, having a psychotic illness, experiencing interpersonal problems such as being aggressively criticized or desiring plentiful attention, having suicidal intent, and displaying suicidal warning signals. The model demonstrated a good predictive capability, with an AUC of 0.902, a sensitivity of 84.65%, a specificity of 82.66%, and an accuracy of 83.63%. The implementation of this predictive model can assist physicians in conducting comprehensive evaluations of suicide risk in clinical settings and devising treatment plans for preventive intervention.

Development and evaluation of a predictive algorithm and telehealth intervention to reduce suicidal behavior among university students

BACKGROUND

Suicidal behaviors are prevalent among college students; however, students remain reluctant to seek support. We developed a predictive algorithm to identify students at risk of suicidal behavior and used telehealth to reduce subsequent risk.

METHODS

Data come from several waves of a prospective cohort study (2016-2022) of college students (n = 5454). All first-year students were invited to participate as volunteers. (Response rates range: 16.00-19.93%). A stepped-care approach was implemented: (i) all students received a comprehensive list of services; (ii) those reporting past 12-month suicidal ideation were directed to a safety planning application; (iii) those identified as high risk of suicidal behavior by the algorithm or reporting 12-month suicide attempt were contacted via telephone within 24-h of survey completion. Intervention focused on support/safety-planning, and referral to services for this high-risk group.

RESULTS

5454 students ranging in age from 17-36 (s.d. = 5.346) participated; 65% female. The algorithm identified 77% of students reporting subsequent suicidal behavior in the top 15% of predicted probabilities (Sensitivity = 26.26 [95% CI 17.93-36.07]; Specificity = 97.46 [95% CI 96.21-98.38], PPV = 53.06 [95% CI 40.16-65.56]; AUC range: 0.895 [95% CIs 0.872-0.917] to 0.966 [95% CIs 0.939-0.994]). High-risk students in the Intervention Cohort showed a 41.7% reduction in probability of suicidal behavior at 12-month follow-up compared to high-risk students in the Control Cohort.

CONCLUSIONS

Predictive risk algorithms embedded into universal screening, coupled with telehealth intervention, offer significant potential as a suicide prevention approach for students.

Developing a clinical decision support system software prototype that assists in the management of patients with self-harm in the emergency department: protocol of the PERMANENS project

BACKGROUND

Self-harm presents a significant public health challenge. Emergency departments (EDs) are crucial healthcare settings in managing self-harm, but clinician uncertainty in risk assessment may contribute to ineffective care. Clinical Decision Support Systems (CDSSs) show promise in enhancing care processes, but their effective implementation in self-harm management remains unexplored.

METHODS

PERMANENS comprises a combination of methodologies and study designs aimed at developing a CDSS prototype that assists clinicians in the personalized assessment and management of ED patients presenting with self-harm. Ensemble prediction models will be constructed by applying machine learning techniques on electronic registry data from four sites, i.e., Catalonia (Spain), Ireland, Norway, and Sweden. These models will predict key adverse outcomes including self-harm repetition, suicide, premature death, and lack of post-discharge care. Available registry data include routinely collected electronic health record data, mortality data, and administrative data, and will be harmonized using the OMOP Common Data Model, ensuring consistency in terminologies, vocabularies and coding schemes. A clinical knowledge base of effective suicide prevention interventions will be developed rooted in a systematic review of clinical practice guidelines, including quality assessment of guidelines using the AGREE II tool. The CDSS software prototype will include a backend that integrates the prediction models and the clinical knowledge base to enable accurate patient risk stratification and subsequent intervention allocation. The CDSS frontend will enable personalized risk assessment and will provide tailored treatment plans, following a tiered evidence-based approach. Implementation research will ensure the CDSS' practical functionality and feasibility, and will include periodic meetings with user-advisory groups, mixed-methods research to identify currently unmet needs in self-harm risk assessment, and small-scale usability testing of the CDSS prototype software.

DISCUSSION

Through the development of the proposed CDSS software prototype, PERMANENS aims to standardize care, enhance clinician confidence, improve patient satisfaction, and increase treatment compliance. The routine integration of CDSS for self-harm risk assessment within healthcare systems holds significant potential in effectively reducing suicide mortality rates by facilitating personalized and timely delivery of effective interventions on a large scale for individuals at risk of suicide.

Randomized Controlled Comparative Effectiveness Trial of Risk Model-Guided Clinical Decision Support for Suicide Screening

Suicide prevention requires risk identification, appropriate intervention, and follow-up. Traditional risk identification relies on patient self-reporting, support network reporting, or face-to-face screening with validated instruments or history and physical exam. In the last decade, statistical risk models have been studied and more recently deployed to augment clinical judgment. Models have generally been found to be low precision or problematic at scale due to low incidence. Few have been tested in clinical practice, and none have been tested in clinical trials to our knowledge.

Methods

We report the results of a pragmatic randomized controlled trial (RCT) in three outpatient adult Neurology clinic settings. This two-arm trial compared the effectiveness of Interruptive and Non-Interruptive Clinical Decision Support (CDS) to prompt further screening of suicidal ideation for those predicted to be high risk using a real-time, validated statistical risk model of suicide attempt risk, with the decision to screen as the primary end point. Secondary outcomes included rates of suicidal ideation and attempts in both arms. Manual chart review of every trial encounter was used to determine if suicide risk assessment was subsequently documented.

Results

From August 16, 2022, through February 16, 2023, our study randomized 596 patient encounters across 561 patients for providers to receive either Interruptive or Non-Interruptive CDS in a 1:1 ratio. Adjusting for provider cluster effects, Interruptive CDS led to significantly higher numbers of decisions to screen (42%=121/289 encounters) compared to Non-Interruptive CDS (4%=12/307) (odds ratio=17.7, p-value <0.001). Secondarily, no documented episodes of suicidal ideation or attempts occurred in either arm. While the proportion of documented assessments among those noting the decision to screen was higher for providers in the Non-Interruptive arm (92%=11/12) than in the Interruptive arm (52%=63/121), the interruptive CDS was associated with more frequent documentation of suicide risk assessment (63/289 encounters compared to 11/307, p-value<0.001).

Conclusions

In this pragmatic RCT of real-time predictive CDS to guide suicide risk assessment, Interruptive CDS led to higher numbers of decisions to screen and documented suicide risk assessments. Well-powered large-scale trials randomizing this type of CDS compared to standard of care are indicated to measure effectiveness in reducing suicidal self-harm. ClinicalTrials.gov Identifier: NCT05312437.

Neurological, Metabolic, and Psychopathological Correlates of Lifetime Suicidal Behaviour in Major Depressive Disorder without Current Suicide Ideation

INTRODUCTION

Suicidal behaviour (SB) has a complex aetiology. Although suicidal ideation (SI) is considered the most important risk factor for future attempts, many people who engage in SB do not report it.

METHODS

We investigated neurological, metabolic, and psychopathological correlates of lifetime SB in two independent groups of patients with major depression (sample 1: n = 230; age: 18-65 years; sample 2: n = 258; age >60 years) who did not report SI during an index episode.

RESULTS

Among adults (sample 1), SB was reported by 141 subjects (58.7%) and severe SB by 33 (15%). After controlling for interactions, four risk factors for SB emerged: male gender (OR 2.55; 95% CI: 1.06-6.12), negative self-perception (OR 1.76; 95% CI: 1.08-2.87), subthreshold hypomania (OR 4.50; 95% CI: 1.57-12.85), and sexual abuse (OR 3.09; 95% CI: 1.28-7.48). The presence of at least two of these factors had the best accuracy in predicting SB: sensitivity = 57.6% (39.2-74.5); specificity = 75.1% (68.5-82.0); PPV = 27.9% (20.9-37.2); NPV = 91.4% (87.6-94.1). In older patients (sample 2), 23 subjects (9%) reported previous suicide attempts, which were characterized by earlier onset (25 years: OR 0.95: 0.92-0.98), impaired verbal performance (verbal fluency: OR 0.95: 0.89-0.99), higher HDL cholesterol levels (OR 1.04: 1.00-1.07) and more dyskinesias (OR 2.86: 1.22-6.70).

CONCLUSION

Our findings suggest that SB is common in major depressive disorder, even when SI is not reported. In these individuals it is feasible and recommended to investigate both psychiatric and organic risk factors. The predictive power of models excluding SI is comparable to that of models including SI.

Analysis and evaluation of explainable artificial intelligence on suicide risk assessment

This study explores the effectiveness of Explainable Artificial Intelligence (XAI) for predicting suicide risk from medical tabular data. Given the common challenge of limited datasets in health-related Machine Learning (ML) applications, we use data augmentation in tandem with ML to enhance the identification of individuals at high risk of suicide. We use SHapley Additive exPlanations (SHAP) for XAI and traditional correlation analysis to rank feature importance, pinpointing primary factors influencing suicide risk and preventive measures. Experimental results show the Random Forest (RF) model is excelling in accuracy, F1 score, and AUC (>97% across metrics). According to SHAP, anger issues, depression, and social isolation emerge as top predictors of suicide risk, while individuals with high incomes, esteemed professions, and higher education present the lowest risk. Our findings underscore the effectiveness of ML and XAI in suicide risk assessment, offering valuable insights for psychiatrists and facilitating informed clinical decisions.

Suicide risk assessment tools and prediction models: new evidence, methodological innovations, outdated criticisms

The number of prediction models for suicide-related outcomes has grown substantially in recent years. These models aim to assist in stratifying risk, improve clinical decision-making, and facilitate a personalised medicine approach to the prevention of suicidal behaviour. However, there are contrasting views as to whether prediction models have potential to inform and improve assessment of suicide risk. In this perspective, we discuss common misconceptions that characterise criticisms of suicide risk prediction research. First, we discuss the limitations of a classification approach to risk assessment (eg, categorising individuals as low-risk vs high-risk), and highlight the benefits of probability estimation. Second, we argue that the preoccupation with classification measures (such as positive predictive value) when assessing a model's predictive performance is inappropriate, and discuss the importance of clinical context in determining the most appropriate risk threshold for a given model. Third, we highlight that adequate discriminative ability for a prediction model depends on the clinical area, and emphasise the importance of calibration, which is almost entirely overlooked in the suicide risk prediction literature. Finally, we point out that conclusions about the clinical utility and health-economic value of suicide prediction models should be based on appropriate measures (such as net benefit and decision-analytic modelling), and highlight the role of impact assessment studies. We conclude that the discussion around using suicide prediction models and risk assessment tools requires more nuance and statistical expertise, and that guidelines and suicide prevention strategies should be informed by the new and higher quality evidence in the field.

Unveiling Adolescent Suicidality: Holistic Analysis of Protective and Risk Factors Using Multiple Machine Learning Algorithms

Adolescent suicide attempts are on the rise, presenting a significant public health concern. Recent research aimed at improving risk assessment for adolescent suicide attempts has turned to machine learning. But no studies to date have examined the performance of stacked ensemble algorithms, which are more suitable for low-prevalence conditions. The existing machine learning-based research also lacks population-representative samples, overlooks protective factors and their interplay with risk factors, and neglects established theories on suicidal behavior in favor of purely algorithmic risk estimation. The present study overcomes these shortcomings by comparing the performance of a stacked ensemble algorithm with a diverse set of algorithms, performing a holistic item analysis to identify both risk and protective factors on a comprehensive data, and addressing the compatibility of these factors with two competing theories of suicide, namely, The Interpersonal Theory of Suicide and The Strain Theory of Suicide. A population-representative dataset of 173,664 Norwegian adolescents aged 13 to 18 years (mean = 15.14, SD = 1.58, 50.5% female) with a 4.65% rate of reported suicide attempt during the past 12 months was analyzed. Five machine learning algorithms were trained for suicide attempt risk assessment. The stacked ensemble model significantly outperformed other algorithms, achieving equal sensitivity and a specificity of 90.1%, AUC of 96.4%, and AUCPR of 67.5%. All algorithms found recent self-harm to be the most important indicator of adolescent suicide attempt. Exploratory factor analysis suggested five additional risk domains, which we labeled internalizing problems, sleep disturbance, disordered eating, lack of optimism regarding future education and career, and victimization. The identified factors provided stronger support for The Interpersonal Theory of Suicide than for The Strain Theory of Suicide. An enhancement to The Interpersonal Theory based on the risk and protective factors identified by holistic item analysis is presented.

Scoping Review of Postvention for Mental Health Providers Following Patient Suicide

INTRODUCTION

As suicides among military personnel continue to climb, we sought to determine best practices for supporting military mental health clinicians following patient suicide loss (i.e., postvention).

MATERIALS AND METHODS

We conducted a scoping review of the literature using Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines. Our initial search of academic databases generated 2,374 studies, of which 122 were included in our final review. We categorized postvention recommendations based on the socioecological model (i.e., recommendations at the individual provider, supervisory/managerial, organizational, and discipline levels) and analyzed them using a narrative synthesizing approach.

RESULTS

Extracted recommendations (N = 358) comprised those at the provider (n = 94), supervisory/managerial (n = 90), organization (n = 105), and discipline (n = 69) levels.

CONCLUSIONS

The literature converges on the need for formal postvention protocols that prioritize (1) training and education and (2) emotional and instrumental support for the clinician. Based on the scoped literature, we propose a simple postvention model for military mental health clinicians and recommend a controlled trial testing of its effectiveness.

ASSIP vs. Crisis Counseling for Preventing Suicide Re-attempts: Outcome Predictor Analysis of a Randomized Clinical Trial Data

OBJECTIVE

Knowledge of the effectiveness and limits of the suitability of brief interventions in suicide prevention is greatly needed. We investigated subgroup differences and predictors for suicide re-attempts within a clinical trial population recruited for a brief intervention to prevent re-attempts.

METHODS

Consenting adult patients receiving treatment for a suicide attempt in Helsinki City general hospital emergency rooms in 2016-2017 (n = 239) were randomly allocated to (a) the Attempted Suicide Short Intervention Program (ASSIP) or (b) Crisis Counseling (CC). Participants also received their usual treatment. Information on primary outcome repeat attempts and secondary outcomes was collected via telephone and from medical and psychiatric records for 2 years. As proportions of re-attempts did not differ significantly between ASSIP and CC (29.2 vs. 35.2%), patients were pooled and predictors for suicide re-attempts were analyzed using Kaplan-Meier and logistic regression analyses.

RESULTS

Re-attempts were predicted by participants' younger age (OR 0.965 [0.933-0.998]), previous suicide attempts (OR 2.437 [1.106-5.370]), psychiatric hospitalization in the year preceding baseline (OR 3.256 [1.422-7.458]), and clinical diagnosis of a personality disorder (OR 4.244 [1.923-9.370]), especially borderline personality disorder (OR 5.922 [2.558-13.709]).

CONCLUSIONS

Within a population of suicide attempters consenting to a brief intervention trial, the risk of re-attempt was strongly predicted by subjects' young age, history of previous attempts, psychiatric hospitalizations, and personality disorder, particularly borderline personality disorder. The composition of treated populations with regard to these characteristics may strongly influence the observed success of brief interventions. Their potential as moderators of treatment effectiveness and as indicators of the utility of brief interventions warrants further investigation.HIGHLIGHTSDuring the 2-year follow-up, 32% of trial participants reattempted suicide.Rates of reattempts varied and were strongly predicted by clinical subgroup.Subgroup composition may strongly influence brief interventions' observed outcome.

Factors within the clinical encounter that impact upon risk assessment within child and adolescent mental health services: a rapid realist synthesis

Background

Risk assessment is a key process when a child or adolescent presents at risk for self-harm or suicide in a mental health crisis or emergency. Risk assessment by a healthcare professional should be included within a biopsychosocial assessment. However, the predictive value of risk-screening tools for self-harm and suicide in children and adolescents is consistently challenged. A review is needed to explore how best to undertake risk assessment and the appropriate role for tools/checklists within the assessment pathway.

Aims

To map research relating to risk assessment for child and adolescent mental health and to identify features that relate to a successful risk assessment.

Objectives

To review factors within the clinical encounter that impact upon risk assessments for self-harm and suicide in children and adolescents: i. to conduct a realist synthesis to understand mechanisms for risk assessment, why they occur and how they vary by context ii. to conduct a mapping review of primary studies/reviews to describe available tools of applicability to the UK.

Data sources

Databases, including MEDLINE, PsycINFO®, EMBASE, CINAHL, HMIC, Science and Social Sciences Citation Index and the Cochrane Library, were searched (September 2021). Searches were also conducted for reports from websites.

Review methods

A resource-constrained realist synthesis was conducted exploring factors that impact upon risk assessments for self-harm and suicide. This was accompanied by a mapping review of primary studies/reviews describing risk-assessment tools and approaches used in UK child and adolescent mental health. Following piloting, four reviewers screened retrieved records. Items were coded for the mapping and/or for inclusion in the realist synthesis. The review team examined the validity and limitations of risk-screening tools. In addition, the team identified structured approaches to risk assessment. Reporting of the realist synthesis followed RAMESES guidelines.

Results

From 4084 unique citations, 249 papers were reviewed and 41 studies (49 tools) were included in the mapping review. Eight reviews were identified following full-text screening. Fifty-seven papers were identified for the realist review. Findings highlight 14 explanations (programme theories) for a successful risk assessment for self-harm and suicide. Forty-nine individual assessment tools/approaches were identified. Few tools were developed in the UK, specifically for children and adolescents. These lacked formal independent evaluation. No risk-screening tool is suitable for risk prediction; optimal approaches incorporate a relationship of trust, involvement of the family, where appropriate, and a patient-centred holistic approach. The objective of risk assessment should be elicitation of information to direct a risk formulation and care plan.

Limitations

Many identified tools are well-established but lack scientific validity, particularly predictive validity, or clinical utility. Programme theories were generated rapidly from a survey of risk assessment.

Conclusions

No single checklist/approach meets the needs of risk assessment for self-harm and suicide. A whole-system approach is required, informed by structured clinical judgement. Useful components include a holistic assessment within a climate of trust, facilitated by family involvement.

Study registration

This study is registered as PROSPERO CRD42021276671.

Funding

This award was funded by the National Institute for Health and Care Research (NIHR) Health and Social Care Delivery Research programme (NIHR award ref: NIHR135079) and is published in full in Health and Social Care Delivery Research; Vol. 12, No. 1. See the NIHR Funding and Awards website for further award information.

Validation and application of the Chinese version of the Columbia-Suicide Severity Rating Scale: Suicidality and cognitive deficits in patients with major depressive disorder

BACKGROUND

Depression is a significant risk factor for death by suicide. Additionally, patients with depression who have neurocognitive dysfunction are at a higher risk of exhibiting suicidal behaviors. We aimed to validate the Chinese version of the Columbia Suicide Severity Rating Scale (C-SSRS) and then employ it to examine the association between suicidality and cognitive deficits in patients with Major Depressive Disorder (MDD).

METHODS

Data from 456 patients with MDD who underwent baseline assessment and 3-month follow-up were used for psychometric validation of the C-SSRS. 430 patients were divided into a mild cognitive impairment group (N = 390) and a severe cognitive impairment group (N = 40) using cluster analysis and compared with healthy controls. The relationship between C-SSRS scores and the degree of cognitive impairment was analyzed.

RESULTS

1) The Chinese version of C-SSRS demonstrated good internal consistency (Cronbach's alpha = 0.884/0.842), convergent and divergent validity. 2) The severity of suicidal ideation (SI), the intensity of SI, and the lifetime history of suicide attempts were significant independent predictors of short-term suicide attempts. 3) Higher worst-point lifetime SI severity and intensity scores in patients with MDD were significantly associated with severe cognitive impairment.

LIMITATIONS

The analysis of cognition and suicide was based on cross-sectional studies. Hence, changes in SI and cognitive function over time could not be analyzed.

CONCLUSIONS

The Chinese C-SSRS is a reliable and valid assessment tool for suicidal ideation and behavior in patients with depression. Suicidal ideation in patients with MDD is associated with cognitive dysfunction. These findings provide a reference for suicide prevention in patients with depression.

Does Suicide Risk Screening Improve the Identification of Primary Care Patients Who Will Attempt Suicide Versus Depression Screening Alone?

OBJECTIVE

The effectiveness of suicide risk screening relative to depression screening alone among primary care patients has not been tested rigorously. This study compared the performance of multiple depression screening methods (Patient Health Questionnaire [PHQ]-2, PHQ-8, and PHQ-9) and multiple suicide risk screening methods (PHQ-9 item 9 and suicide-focused screening of "thoughts of killing yourself" during the entire lifespan, within the past month, and within the past week) in a convenience sample of primary care patients.

METHODS

A total of 2,744 patients (military personnel, family members, and retirees) from six military primary care clinics completed the PHQ-9 and screening for suicidal ideation (SI) during routine clinic visits. Follow-up phone interviews were conducted for one year post-baseline to assess the incidence of suicide attempts, the study's primary outcome. Sensitivity, specificity, accuracy, and F1 statistics were calculated for each screening method for identifying patients who attempted suicide.

RESULTS

More than 65% of patients who screened positive for SI also screened positive for depression on the PHQ-9. Depression screening with the PHQ-9 correctly identified more patients who attempted suicide during follow-up than the PHQ-2, past week SI, and past month SI. The PHQ-9 correctly identified more patients who attempted suicide within 3 months than lifetime SI, but lifetime SI correctly identified more patients who attempted suicide within 6 and 12 months.

CONCLUSION

Depression screening with the PHQ-9 was the most effective strategy for identifying patients who attempted suicide in the near term. Universal suicide risk screening is unlikely to meaningfully improve identification of higher-risk patients beyond PHQ-9 depression screening.

P4 suicidality screener: Literature synthesis and results from two randomized trials

OBJECTIVE

To synthesize the literature on use of the P4 suicidality screener since its introduction in 2010 and to summarize results from 2 randomized clinical trials.

METHOD

A PubMed search was conducted from 2010 to 2023 to retrieve studies reporting on use of the P4. Also, data was extracted from the CAMMPS and SCOPE trials in which the P4 was periodically administered over 12 months when the 9th item of the PHQ-9 was endorsed.

RESULTS

A total of 21 research studies using the P4 were found, of which 12 provided some data on P4 findings. Additionally, another 7 protocol papers reported intended use of the P4 as a study measure. In our 2 trials, the 9th item was endorsed 259 (12.5%) times in 2068 administrations of the PHQ-9. Higher risk suicidal ideation was identified in 4.1% (12/294) of CAMMPS participants and 2.8% (7/250) of SCOPE participants. No suicide attempts occurred over the 12 months in either trial.

CONCLUSIONS

The P4 has had moderate use as a brief suicidality screener and is an efficient way to identify the small proportion of depressed patients with higher risk suicidality. Studies comparing the P4 with other common suicidality screeners would further inform use.

Quantitative content analysis of Freedom of Information requests examining the extent and variations of tools and training for conducting suicide risk assessments in NHS Trusts across England

OBJECTIVES

Determining the risk for suicide is a difficult endeavour. Clinical guidance in the UK explicitly advises against using risk assessment tools and scales to determine suicide risk. Based on Freedom of Information (FoI) requests made to NHS Trusts in England, this study provides an overview of suicide risk assessment tools in use, training provided in how to use such assessments, and explores implementation of suicide risk assessment guidance in practice in English NHS Trusts.

DESIGN

A cross-sectional survey of suicide risk assessment tools and training gathered via FoI requests and subjected to a content analysis.

SETTING

FoI requests were submitted to NHS Trusts across England.

RESULTS

A wide variety of suicide risk assessments tools were identified as being used in practice, with several trusts reported using more than one tool to determine suicide risk. Forty-one trusts reported using locally developed, unvalidated, tools to assess risk of suicide and 18 stated they do not use a tool. Ten trusts stated they do not train their staff in suicide risk assessment while 13 reported use of specific suicide risk assessment training. Sixty-two trusts stated they do not centrally record the number of assessments conducted or how many individuals are identified as at risk. Content analysis indicated the frequent wider assessment of risk not restricted to suicide risk.

CONCLUSIONS

There is wide variation in suicide risk assessment tools being used in practice and some lack of specific training for healthcare staff in determining suicide risk. Few trusts routinely record the number of assessments being conducted or the number of individuals identified at high risk. Implementation of specific training is necessary for the suicide risk assessment process to identify patient needs and develop therapeutic engagement. Routinely recording how many assessments are conducted is a crucial step in improving suicide prevention.

Machine learning-based prediction for self-harm and suicide attempts in adolescents

This study aimed to use machine learning (ML) models to predict the risk of self-harm and suicide attempts in adolescents. We conducted secondary analysis of cross-sectional data from the Longitudinal Study of Australian Children dataset. Several key variables at the age of 14-15 years were used to predict self-harm or suicide attempt at 16-17 years. Random forest classification models were used to select the optimal subset of predictors and subsequently make predictions. Among 2809 participants, 296 (10.54%) reported an act of self-harm and 145 (5.16%) reported attempting suicide at least once in the past 12 months. The area under the receiver operating curve was fair for self-harm (0.7397) and suicide attempt (0.7220), which outperformed the prediction strategy solely based on prior suicide or self-harm attempt (AUC: 0.6). The most important factors identified were similar, and included depressed feelings, strengths and difficulties questionnaire scores, perceptions of self, and school- and parent-related factors. The random forest classification algorithm, an ML technique, can effectively select the optimal subset of predictors from hundreds of variables to forecast the risks of suicide and self-harm among adolescents. Further research is needed to validate the utility and scalability of ML techniques in mental health research.

Toward objective characterizations of suicide risk: A narrative review of laboratory-based cognitive and behavioral tasks

Although suicide is a leading cause of preventable death worldwide, current prevention efforts have failed to substantively mitigate suicide risk. Suicide research has traditionally relied on subjective reports that may not accurately differentiate those at high versus minimal risk. This narrative review supports the inclusion of objective task-based measures in suicide research to complement existing subjective batteries. The article: 1) outlines risk factors proposed by contemporary theories of suicide and highlights recent empirical findings supporting these theories; 2) discusses ongoing challenges associated with current risk assessment tools and their ability to accurately evaluate risk factors; and 3) analyzes objective laboratory measures that can be implemented alongside traditional measures to enhance the precision of risk assessment. To illustrate the potential of these methods to improve our understanding of suicide risk, the article reviews how acute stress responses in a laboratory setting can be modeled, given that stress is a major precipitant for suicidal behavior. More precise risk assessment strategies can emerge if objective measures are implemented in conjunction with traditional subjective measures.

Predicting suicide attempts among Norwegian adolescents without using suicide-related items: a machine learning approach

Introduction

Research on the classification models of suicide attempts has predominantly depended on the collection of sensitive data related to suicide. Gathering this type of information at the population level can be challenging, especially when it pertains to adolescents. We addressed two main objectives: (1) the feasibility of classifying adolescents at high risk of attempting suicide without relying on specific suicide-related survey items such as history of suicide attempts, suicide plan, or suicide ideation, and (2) identifying the most important predictors of suicide attempts among adolescents.

Methods

Nationwide survey data from 173,664 Norwegian adolescents (ages 13-18) were utilized to train a binary classification model, using 169 questionnaire items. The Extreme Gradient Boosting (XGBoost) algorithm was fine-tuned to classify adolescent suicide attempts, and the most important predictors were identified.

Results

XGBoost achieved a sensitivity of 77% with a specificity of 90%, and an AUC of 92.1% and an AUPRC of 47.1%. A coherent set of predictors in the domains of internalizing problems, substance use, interpersonal relationships, and victimization were pinpointed as the most important items related to recent suicide attempts.

Conclusion

This study underscores the potential of machine learning for screening adolescent suicide attempts on a population scale without requiring sensitive suicide-related survey items. Future research investigating the etiology of suicidal behavior may direct particular attention to internalizing problems, interpersonal relationships, victimization, and substance use.

Validation of the Farsi version of the Suicide Ideation and Behavior Scale

Objective

Suicide ideation and suicide attempts are prevalent in Farsi speaking populations. The present study aimed at validating the Farsi version of the Suicide Ideation and Behavior Scale (SIBS).

Methods

Reliability and validity of the Farsi version of the SIBS were established in a highly burdened Afghan student sample (N = 279). Internal consistency, convergent and discriminant validity were investigated, and confirmatory factor analysis was conducted.

Results

The Farsi version of the SIBS was shown to have a unidimensional structure with excellent internal consistency, as well as good convergent and divergent validity.

Discussion

The results suggest that the SIBS is a brief, reliable, and valid measure of current suicidal ideation and behavior that can be used in Farsi speaking populations.

The Columbia-suicide severity rating scale: validity and psychometric properties of an online Spanish-language version in a Mexican population sample

The aim of this study was to evaluate the validity and psychometric properties in a Mexican sample of a Spanish-language online version of the Columbia-Suicide Severity Rating Scale (C-SSRS). Data were collected between May and October 2021 from 3,645 participants aged 18 years and over, who agreed to complete the questionnaire. Reliability analysis, confirmatory factor analysis (CFA), and psychometric properties were calculated using a two-parameter model. The results showed a reasonable level of reliability with a Cronbach's alpha of 0.814, and evidence of unidimensionality, and construct validity for suicide risk at three risk levels: low, medium, and high. Analysis of the items suggests that they are consistent with the proposed theoretical model. Our results also demonstrate that the parameters are stable and able to efficiently discriminate individuals at high risk of suicide. We propose the use of this version of the C-SSRS in the Spanish-speaking population, since it is a multifactorial assessment of suicide risk and the inclusion of other clinical and risk factor assessments for a more comprehensive evaluation.

Folate and Its Significance in Depressive Disorders and Suicidality: A Comprehensive Narrative Review

Depressive disorders pose significant challenges to global public health, necessitating effective prevention and management strategies. Notably, the occurrence of suicide frequently coincides with depressive episodes. Suicide is as a paramount global health concern that demands efficacious preventive strategies. Current psychiatric approaches heavily rely on pharmacological interventions but have had limited success in addressing the global burden of mental health issues. Suboptimal nutrition, with its impact on the neuroendocrine system, has been implicated in the underlying pathology of depressive disorders. Folate, a group of water-soluble compounds, plays a crucial role in various central nervous system functions. Depressed individuals often exhibit low levels of serum and red blood cell folate. Multiple studies and systematic reviews have investigated the efficacy of folic acid and its derivative, L-methylfolate, which can cross the blood-brain barrier, as stand-alone or adjunct therapies for depression. Although findings have been mixed, the available evidence generally supports the use of these compounds in depressed individuals. Recent studies have established links between the one-carbon cycle, folate-homocysteine balance, immune system function, glutamate excitation via NMDA (N-methyl-D-aspartate) receptors, and gut microbiome eubiosis in mood regulation. These findings provide insights into the complex neurobiological mechanisms underlying the effects of folate and related compounds in depression. Through a comprehensive review of the existing literature, this study aims to advance our understanding of the therapeutic potential of folic acid and related compounds in depression treatment. It also seeks to explore their role in addressing suicidal tendencies and shed light on the neurobiological mechanisms involved, leveraging the latest discoveries in depression research.

Identification of young females at high risk of suicide following hospital-treated self-harm in Victoria, Australia

OBJECTIVE

We conducted a data linkage study in Victoria, Australia, to determine the proportion of young females who are treated in hospital for self-harm who go on to die by suicide within 5 years and to identify factors associated with increased suicide risk in this same cohort.

METHOD

We undertook a cohort study following 3689 female patients aged 10-24 years, who were initially treated in hospital for self-harm during the 2-year period January 2011 to December 2012. We followed each patient for 5 years unless they died first, in which case, they were followed until their date of death. We used inpatient admissions from the Victorian Admitted Episodes Dataset and emergency department presentations from the Victorian Emergency Minimum Dataset linked to death data from two sources, the Victorian Suicide Register and the National Death Index.

RESULTS

Twenty-eight individuals (0.76% of the total cohort) died by suicide within 5 years of their index admission. In multivariate survival analysis, only suicide ideation at the time of self-harm (hazard ratio = 4.59; 95% confidence interval: 1.70, 12.38) and a decreasing time between successive self-harm episodes (hazard ratio = 4.38; 95% confidence interval: 1.28, 15.00) were associated with increased suicide risk.

CONCLUSION

Although the vast majority of young females who present to hospital for self-harm do not die by suicide within 5 years, our results suggest young females expressing suicide ideation and those presenting frequently with decreasing time between successive episodes should be prioritised for suicide-prevention efforts.

Circadian Activity Rhythms and Psychopathology in Major Depressive Episodes

BACKGROUND

Identifying suicidal risk based on clinical assessment is challenging. Suicidal ideation fluctuates, can be downplayed or denied, and seems stigmatizing if divulged. In contrast, vitality is foundational to subjectivity in being immediately conscious before reflection. Including its assessment may improve detection of suicidal risk compared to relying on suicidal ideation alone. We hypothesized that objective motility measures would be associated with vitality and enhance assessment of suicidal risk.

METHODS

We evaluated 83 adult-psychiatric outpatients with a DSM-5 bipolar (BD) or major depressive disorder (MDD): BD-I (n = 48), BD-II (20), and MDD (15) during a major depressive episode. They were actigraphically monitored continuously over 3 weekdays and self-rated their subjective states at regular intervals. We applied cosinor analysis to actigraphic data and analyzed associations of subjective psychopathology measures with circadian activity parameters.

RESULTS

Actigraphic circadian mesor, amplitude, day- and nighttime activity were lower with BD versus MDD. Self-rated vitality (wish-to-live) was significantly lower, self-rated suicidality (wish-to-die) was higher, and their difference was lower, with BD versus MDD. There were no other significant diagnostic differences in actigraphic sleep parameters or in self-rated depression, dysphoria, or anxiety. By linear regression, the difference between vitality and passive suicidal ideation was strongly positively correlated with mesor (p < 0.0001), daytime activity (p < 0.0001), and amplitude (p = 0.001).

CONCLUSIONS

Higher circadian activity measures reflected enhanced levels of subjective vitality and were associated with lesser suicidal ideation. Current suicidal-risk assessment might usefully include monitoring of motility and vitality in addition to examining negative affects and suicidal thinking.

StackDPP: Stacking-Based Explainable Classifier for Depression Prediction and Finding the Risk Factors among Clinicians

Mental health is a major concern for all classes of people, but especially physicians in the present world. A challenging task is to identify the significant risk factors that are responsible for depression among physicians. To address this issue, the study aimed to build a machine learning-based predictive model that will be capable of predicting depression levels and finding associated risk factors. A raw dataset was collected to conduct this study and preprocessed as necessary. Then, the dataset was divided into 10 sub-datasets to determine the best possible set of attributes to predict depression. Seven different classification algorithms, KNN, DT, LGBM, GB, RF, ETC, and StackDPP, were applied to all the sub-datasets. StackDPP is a stacking-based ensemble classifier, which is proposed in this study. It was found that StackDPP outperformed on all the datasets. The findings indicate that the StackDPP with the sub-dataset with all the attributes gained the highest accuracy (0.962581), and the top 20 attributes were enough to gain 0.96129 accuracy by StackDPP, which was close to the performance of the dataset with all the attributes. In addition, risk factors were analyzed in this study to reveal the most significant risk factors that are responsible for depression among physicians. The findings of the study indicate that the proposed model is highly capable of predicting the level of depression, along with finding the most significant risk factors. The study will enable mental health professionals and psychiatrists to decide on treatment and therapy for physicians by analyzing the depression level and finding the most significant risk factors.

Evaluation of the Risk Identification for Suicide and Enhanced Care Model in a Native American Community

Importance

There are many prognostic models of suicide risk, but few have been prospectively evaluated, and none has been developed specifically for Native American populations.

Objective

To prospectively validate a statistical risk model implemented in a community setting and evaluate whether use of this model was associated with improved reach of evidence-based care and reduced subsequent suicide-related behavior among high-risk individuals.

Design, Setting, and Participants

This prognostic study, done in partnership with the White Mountain Apache Tribe, used data collected by the Apache Celebrating Life program for adults aged 25 years or older identified as at risk for suicide and/or self-harm from January 1, 2017, through August 31, 2022. Data were divided into 2 cohorts: (1) individuals and suicide-related events from the period prior to suicide risk alerts being active (February 29, 2020) and (2) individuals and events from the time after alerts were activated.

Main Outcomes and Measures

Aim 1 focused on a prospective validation of the risk model in cohort 1. Aim 2 compared the odds of repeated suicide-related events and the reach of brief contact interventions among high-risk cases between cohort 2 and cohort 1.

Results

Across both cohorts, a total of 400 individuals identified as at risk for suicide and/or self-harm (mean [SD] age, 36.5 [10.3] years; 210 females [52.5%]) had 781 suicide-related events. Cohort 1 included 256 individuals with index events prior to active notifications. Most index events (134 [52.5%]) were for binge substance use, followed by 101 (39.6%) for suicidal ideation, 28 (11.0%) for a suicide attempt, and 10 (3.9%) for self-injury. Among these individuals, 102 (39.5%) had subsequent suicidal behaviors. In cohort 1, the majority (220 [86.3%]) were classified as low risk, and 35 individuals (13.3%) were classified as high risk for suicidal attempt or death in the 12 months after their index event. Cohort 2 included 144 individuals with index events after notifications were activated. For aim 1, those classified as high risk had a greater odds of subsequent suicide-related events compared with those classified as low risk (odds ratio [OR], 3.47; 95% CI, 1.53-7.86; P = .003; area under the receiver operating characteristic curve, 0.65). For aim 2, which included 57 individuals classified as high risk across both cohorts, during the time when alerts were inactive, high-risk individuals were more likely to have subsequent suicidal behaviors compared with when alerts were active (OR, 9.14; 95% CI, 1.85-45.29; P = .007). Before the active alerts, only 1 of 35 (2.9%) individuals classified as high risk received a wellness check; after the alerts were activated, 11 of 22 (50.0%) individuals classified as high risk received 1 or more wellness checks.

Conclusions and Relevance

This study showed that a statistical model and associated care system developed in partnership with the White Mountain Apache Tribe enhanced identification of individuals at high risk for suicide and was associated with a reduced risk for subsequent suicidal behaviors and increased reach of care.

Virtually screening adults for depression, anxiety, and suicide risk using machine learning and language from an open-ended interview

Background

Current depression, anxiety, and suicide screening techniques rely on retrospective patient reported symptoms to standardized scales. A qualitative approach to screening combined with the innovation of natural language processing (NLP) and machine learning (ML) methods have shown promise to enhance person-centeredness while detecting depression, anxiety, and suicide risk from in-the-moment patient language derived from an open-ended brief interview.

Objective

To evaluate the performance of NLP/ML models to identify depression, anxiety, and suicide risk from a single 5-10-min semi-structured interview with a large, national sample.

Method

Two thousand four hundred sixteen interviews were conducted with 1,433 participants over a teleconference platform, with 861 (35.6%), 863 (35.7%), and 838 (34.7%) sessions screening positive for depression, anxiety, and suicide risk, respectively. Participants completed an interview over a teleconference platform to collect language about the participants' feelings and emotional state. Logistic regression (LR), support vector machine (SVM), and extreme gradient boosting (XGB) models were trained for each condition using term frequency-inverse document frequency features from the participants' language. Models were primarily evaluated with the area under the receiver operating characteristic curve (AUC).

Results

The best discriminative ability was found when identifying depression with an SVM model (AUC = 0.77; 95% CI = 0.75-0.79), followed by anxiety with an LR model (AUC = 0.74; 95% CI = 0.72-0.76), and an SVM for suicide risk (AUC = 0.70; 95% CI = 0.68-0.72). Model performance was generally best with more severe depression, anxiety, or suicide risk. Performance improved when individuals with lifetime but no suicide risk in the past 3 months were considered controls.

Conclusion

It is feasible to use a virtual platform to simultaneously screen for depression, anxiety, and suicide risk using a 5-to-10-min interview. The NLP/ML models performed with good discrimination in the identification of depression, anxiety, and suicide risk. Although the utility of suicide risk classification in clinical settings is still undetermined and suicide risk classification had the lowest performance, the result taken together with the qualitative responses from the interview can better inform clinical decision-making by providing additional drivers associated with suicide risk.

Predictive value of suicidal risk assessment using data from China's largest suicide prevention hotline

BACKGROUND

Suicide hotlines are widely used, with potential for identification of callers at especially high risk.

METHODS

This prospective study was conducted at the largest psychological support hotline in China. From 2015 to 2017, all distressed callers were consecutively included and assessed, using a standardized scale consisting of 12 elements, yielding scores of high risk (8-16), moderate risk (4-7), and low risk (0-3) for suicidal act. All high-risk and half of moderate- and low-risk callers were scheduled for a 12-month follow-up. Main outcomes were suicidal acts (nonlethal attempt, death) over follow-up.

RESULTS

Of 21,346 fully assessed callers, 5822, 11,791, and 3733 were classified as high-, moderate-, or low-risk for suicidal acts, with 8869 callers (4076 high-, 3258 moderate-, and 1535 low-risk) followed up over 12 months. Over follow-up, 802 (9.0 %) callers attempted suicide or died by suicide. The high-risk callers (15.1 %) had 3-fold higher risk for subsequent suicidal acts than moderate- (5.1 %) and 12-fold higher risk than low-risk callers (1.3 %). The weighted sensitivity, specificity, and positive predictive value of high risk scores were 56.4 %, 74.9 %, and 14.4 %.

LIMITATIONS

Assessed callers with different risk levels were followed disproportionally.

CONCLUSIONS

Suicidal risk assessment during a hotline call is both feasible and predictive of risk, guiding resource allocation to higher risk callers.

Are suicide risk scales sensitive to change? A scoping review

INTRODUCTION

Clinician- or self-administered scales are frequently used to assist in detecting risk of death by suicide and to determine the effectiveness of interventions. No recent review studies have examined whether these scales are sensitive to change. We conducted a scoping review to identify suicide risk scales that are sensitive to change.

MATERIAL AND METHODS

We searched Medline and Excerpta Medica Database from inception through March 17, 2022, to identify randomized trials, pooled analysis, quasi-experimental studies, and cohort studies reporting on sensitivity to change of suicide risk scales. We assessed sensitivity to change by examining internal and external responsiveness. Internal responsiveness evaluates whether the scale measures changes in suicide-related symptoms in response to an intervention while external responsiveness assess whether changes in the scale correspond to changes in risk of suicide. We summarized findings across studies using descriptive analysis.

RESULTS

Among 38 eligible scales, we identified 27 scales that included items that were modifiable to change. However, only 7 scales had been studied to determine their sensitivity to change based on internal or external responsiveness. While the results of studies suggested that 6 scales have internal responsiveness, none of the included studies confirmed that scales have external responsiveness.

DISCUSSION

A few suicide risk scales are internally responsive and may be useful in a clinical or research setting. It is unclear, however, whether changes in scores correspond to an actual change in suicide risk. Future research should confirm the external responsiveness of scales using robust metrics including suicide mortality.

Rapid intensification of suicide risk preceding suicidal behavior among primary care patients

BACKGROUND

Approximately half of those who attempt suicide report experiencing suicidal ideation and suicidal planning in advance; others deny these experiences. Some researchers have hypothesized that rapid intensification is due to past suicidal ideation and/or behaviors that are "mentally shelved" but remain available for rapid access later.

METHOD

To evaluate this hypothesis, we examined (a) temporal sequencing of suicidal ideation, suicidal planning, and suicidal behavior, and (b) speed of emergence of suicidal behavior in a prospective cohort study of 2744 primary care patients.

RESULTS

Of 52 patients reporting suicidal behavior during follow-up, 20 (38.5%) reported suicidal ideation and planning prior to their suicidal behavior, 23 (44.2%) reported suicidal ideation but not planning, and nine (17.3%) denied both suicidal ideation and planning. Over half (n = 30, 57.7%) reported the onset of suicidal ideation and/or planning on the same day as or after their suicidal behavior (i.e., rapid intensification). Rapid intensification was not associated with increased likelihood of reporting recent or past suicidal ideation, planning, or behaviors, suggesting rapid intensification does not depend on prior experience with suicidal ideation and/or behaviors.

CONCLUSION

Detecting primary care patients at risk for this form of suicidal behavior may be limited even with universal suicide risk screening.

Fusion of pain avoidance and the contingent negative variation induced by punitive condition predict suicide ideation in a college population

This study examined behavioral and ERP features involved in pain processing as predictors of suicide ideation. Twenty-seven depressed undergraduates with high suicide ideation (HSI), 23 depressed undergraduates with low suicide ideation (LSI), and 32 healthy controls (HCs) completed the clinical Scales. The amplitudes of LPP, P2, P3, CNV, FRN, power in the beta, theta, and delta bands in the SAID task were multimodal EEG features. A machine learning algorithm known as support vector machine was used to select optimal feature sets for predicting pain avoidance, depression, and suicide ideation. The accuracy of suicide ideation classification was significantly higher for multimodal features (78.16%) which pain avoidance ranked the first and the CNV ranked the fifth than a single ERP feature model (66.62%). Pain avoidance emerged as the most optimal feature of suicide ideation classification than depression. And the CNV elicited by punitive cues may be a biomarker in suicide ideation. Pain avoidance and its related EEG components may improve the efficacy of suicide ideation classification as compared to depression.

How is suicide risk assessed in healthcare settings in the UK? A systematic scoping review

A high proportion of people contact healthcare services in the 12 months prior to death by suicide. Identifying people at high-risk for suicide is therefore a key concern for healthcare services. Whilst there is extensive research on the validity and reliability of suicide risk assessment tools, there remains a lack of understanding of how suicide risk assessments are conducted by healthcare staff in practice. This scoping review examined the literature on how suicide risk assessments are conducted and experienced by healthcare practitioners, patients, carers, relatives, and friends of people who have died by suicide in the UK. Literature searches were conducted on key databases using a pre-defined search strategy pre-registered with the Open Science Framework and following the PRISMA extension for scoping reviews guidelines. Eligible for inclusion were original research, written in English, exploring how suicide risk is assessed in the UK, related to administering or undergoing risk assessment for suicide, key concepts relating to those experiences, or directly exploring the experiences of administering or undergoing assessment. Eighteen studies were included in the final sample. Information was charted including study setting and design, sampling strategy, sample characteristics, and findings. A narrative account of the literature is provided. There was considerable variation regarding how suicide risk assessments are conducted in practice. There was evidence of a lack of risk assessment training, low awareness of suicide prevention guidance, and a lack of evidence relating to patient perspectives of suicide risk assessments. Increased inclusion of patient perspectives of suicide risk assessment is needed to gain understanding of how the process can be improved. Limited time and difficulty in starting an open discussion about suicide with patients were noted as barriers to successful assessment. Implications for practice are discussed.

Suicide Prevention for International Students: A Scoping Review

International students are at risk of suicide and suicide prevention activities addressing their unique needs are required. However, no comprehensive review has been undertaken to identify effective suicide prevention approaches for international students. The current scoping review aimed to chart the extent, range, and nature of available evidence on the prevention strategies for international students. We systematically searched Medline, PsycInfo, ERIC, CINAHL, Proquest, and several gray literature databases to identify relevant peer-reviewed articles and gray literature. Eligible publications were those providing data or recommendations related to suicide prevention among international students; 15 peer-reviewed articles and 19 gray literature documents were included in the review. No studies of prevention programs or policies directly targeting suicidal ideation, suicide attempts, or suicide in international students were identified. A narrative synthesis of the suicide prevention recommendations for international students identified four categories: (1) cultural competency training on suicide and provision of culturally sensitive services; (2) improved and increased risk screening for suicide; (3) proactive intervention and engagement strategies; and (4) collaborative approaches to streamline service access and improve available support. These recommendations provide guidance on potential directions for international student suicide prevention. Research assessing the effectiveness of such recommendations will enable the development of novel evidence-based policies and interventions that reduce rates of suicide in international students.

Efficacy of the Crisis Risk Triage Scale in Inpatient Units Within the United States

ABSTRACT

Patient violence toward others, including doctors and nurses, is a serious concern worldwide. A wealth of literature supports the assertion that violent behavior can be prevented with proper screening and management policies. This project aimed to evaluate the Crisis Triage Rating Scale (CTRS) within a 12-hospital integrated healthcare delivery system located in the southeastern United States. An initial sample of 112,708 unique patient visits between January 2019 and December 2020 was included in this retrospective review of electronic health records. We found that the CTRS harm triage question and risk levels were significant predictors of harm to others. Consistent with previous literature, positive predictive values ranged between 0.025 and 0.070 and negative predictive values ranged between 0.991 and 0.995. Our results support the assertion that clinicians should make balanced judgments about using a positive risk score to allocate safety measures. Variations in practice were evident across our healthcare systems. Improving appropriate assessment procedures may improve the diagnostic tools and risk stratification. When documented correctly, the CTRS performed as expected in an environment where harm to others occurred infrequently.

Raising Suicide in Medical Appointments-Barriers and Facilitators Experienced by Young Adults and GPs: A Mixed-Methods Systematic Review

The aim of this review was to understand the barriers and facilitators facing GPs and young adults in raising and addressing suicide in medical appointments. A mixed-methods systematic review was conducted of qualitative and quantitative studies. The focus was papers that explored barriers and facilitators experienced by young adults aged 18 to 26, and GPs working in primary care environments. Nine studies met the inclusion criteria. Four studies provided information on young adults' views, four on GPs, and one considered both GP and young adults' viewpoints. Nine barrier and seven facilitator themes were identified. Unique to this review was the recognition that young adults want GPs to initiate the conversation about suicide. They see this as a GP's responsibility. This review further confirmed that GPs lack the confidence and skills to assess suicide risk in young adults. Both findings combined could explain previous results for reduced identification of suicide risk in this cohort. GP training needs considerable focus on addressing skill deficiencies and improving GP confidence to assess suicide risk. However, introducing suicide risk screening in primary care for young adults should be a priority as this will overcome the need for young adults to voluntarily disclose thoughts of suicide.

Detection of Suicide Risk Using Vocal Characteristics: Systematic Review

BACKGROUND

In an age when telehealth services are increasingly being used for forward triage, there is a need for accurate suicide risk detection. Vocal characteristics analyzed using artificial intelligence are now proving capable of detecting suicide risk with accuracies superior to traditional survey-based approaches, suggesting an efficient and economical approach to ensuring ongoing patient safety.

OBJECTIVE

This systematic review aimed to identify which vocal characteristics perform best at differentiating between patients with an elevated risk of suicide in comparison with other cohorts and identify the methodological specifications of the systems used to derive each feature and the accuracies of classification that result.

METHODS

A search of MEDLINE via Ovid, Scopus, Computers and Applied Science Complete, CADTH, Web of Science, ProQuest Dissertations and Theses A&I, Australian Policy Online, and Mednar was conducted between 1995 and 2020 and updated in 2021. The inclusion criteria were human participants with no language, age, or setting restrictions applied; randomized controlled studies, observational cohort studies, and theses; studies that used some measure of vocal quality; and individuals assessed as being at high risk of suicide compared with other individuals at lower risk using a validated measure of suicide risk. Risk of bias was assessed using the Risk of Bias in Non-randomized Studies tool. A random-effects model meta-analysis was used wherever mean measures of vocal quality were reported.

RESULTS

The search yielded 1074 unique citations, of which 30 (2.79%) were screened via full text. A total of 21 studies involving 1734 participants met all inclusion criteria. Most studies (15/21, 71%) sourced participants via either the Vanderbilt II database of recordings (8/21, 38%) or the Silverman and Silverman perceptual study recording database (7/21, 33%). Candidate vocal characteristics that performed best at differentiating between high risk of suicide and comparison cohorts included timing patterns of speech (median accuracy 95%), power spectral density sub-bands (median accuracy 90.3%), and mel-frequency cepstral coefficients (median accuracy 80%). A random-effects meta-analysis was used to compare 22 characteristics nested within 14% (3/21) of the studies, which demonstrated significant standardized mean differences for frequencies within the first and second formants (standardized mean difference ranged between -1.07 and -2.56) and jitter values (standardized mean difference=1.47). In 43% (9/21) of the studies, risk of bias was assessed as moderate, whereas in the remaining studies (12/21, 57%), the risk of bias was assessed as high.

CONCLUSIONS

Although several key methodological issues prevailed among the studies reviewed, there is promise in the use of vocal characteristics to detect elevations in suicide risk, particularly in novel settings such as telehealth or conversational agents.

TRIAL REGISTRATION

PROSPERO International Prospective Register of Systematic Reviews CRD420200167413; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42020167413.

Suicide risk assessments: Why are we still relying on these a decade after the evidence showed they perform poorly?

Suicide deaths have a profound impact on whānau and community and are a tragic loss. However, from a statistical point of view, suicide is a relatively rare event. Predicting rare events is difficult, and the implications for suicide prevention were highlighted in an important editorial in this journal more than a decade ago, yet little seems to have changed. Risk assessment that focuses on accurate prediction of suicide in real-world contexts is given a great deal of attention in mental health services, despite the fact that current scientific knowledge and best practice guidelines in this area highlight that it is unlikely to be a good basis on which to provide access to treatment. It is our view that we have a good enough understanding of the common conditions people who struggle with suicidal distress experience and energy is better directed at acting to reduce exposure to these conditions and providing treatment for those who seek it. Blueprints for successful suicide prevention exist. If we lessen the focus on prediction, we will have greater resources to focus on treatment and prevention.