Predicting Suicide Attempts and Suicide Deaths Following Outpatient Visits Using Electronic Health Records

Accuracy and transportability of machine learning models for adolescent suicide prediction with longitudinal clinical records

Machine Learning models trained from real-world data have demonstrated promise in predicting suicide attempts in adolescents. However, their transportability, namely the performance of a model trained on one dataset and applied to different data, is largely unknown, hindering the clinical adoption of these models. Here we developed different machine learning-based suicide prediction models based on real-world data collected in different contexts (inpatient, outpatient, and all encounters) with varying purposes (administrative claims and electronic health records), and compared their cross-data performance. The three datasets used were the All-Payer Claims Database in Connecticut, the Hospital Inpatient Discharge Database in Connecticut, and the Electronic Health Records data provided by the Kansas Health Information Network. We included 285,320 patients among whom we identified 3389 (1.2%) suicide attempters and 66% of the suicide attempters were female. Different machine learning models were evaluated on source datasets where models were trained and then applied to target datasets. More complex models, particularly deep long short-term memory neural network models, did not outperform simpler regularized logistic regression models in terms of both local and transported performance. Transported models exhibited varying performance, showing drops or even improvements compared to their source performance. While they can achieve satisfactory transported performance, they are usually upper-bounded by the best performance of locally developed models, and they can identify additional new cases in target data. Our study uncovers complex transportability patterns and could facilitate the development of suicide prediction models with better performance and generalizability.

Validation of a Multivariable Model to Predict Suicide Attempt in a Mental Health Intake Sample

Importance

Given that suicide rates have been increasing over the past decade and the demand for mental health care is at an all-time high, targeted prevention efforts are needed to identify individuals seeking to initiate mental health outpatient services who are at high risk for suicide. Suicide prediction models have been developed using outpatient mental health encounters, but their performance among intake appointments has not been directly examined.

Objective

To assess the performance of a predictive model of suicide attempts among individuals seeking to initiate an episode of outpatient mental health care.

Design, Setting, and Participants

This prognostic study tested the performance of a previously developed machine learning model designed to predict suicide attempts within 90 days of any mental health outpatient visit. All mental health intake appointments scheduled between January 1, 2012, and April 1, 2022, at Kaiser Permanente Northern California, a large integrated health care delivery system serving over 4.5 million patients, were included. Data were extracted and analyzed from August 9, 2022, to July 31, 2023.

Main Outcome and Measures

Suicide attempts (including completed suicides) within 90 days of the appointment, determined by diagnostic codes and government databases. All predictors were extracted from electronic health records.

Results

The study included 1 623 232 scheduled appointments from 835 616 unique patients. There were 2800 scheduled appointments (0.17%) followed by a suicide attempt within 90 days. The mean (SD) age across appointments was 39.7 (15.8) years, and most appointments were for women (1 103 184 [68.0%]). The model had an area under the receiver operating characteristic curve of 0.77 (95% CI, 0.76-0.78), an area under the precision-recall curve of 0.02 (95% CI, 0.02-0.02), an expected calibration error of 0.0012 (95% CI, 0.0011-0.0013), and sensitivities of 37.2% (95% CI, 35.5%-38.9%) and 18.8% (95% CI, 17.3%-20.2%) at specificities of 95% and 99%, respectively. The 10% of appointments at the highest risk level accounted for 48.8% (95% CI, 47.0%-50.6%) of the appointments followed by a suicide attempt.

Conclusions and Relevance

In this prognostic study involving mental health intakes, a previously developed machine learning model of suicide attempts showed good overall classification performance. Implementation research is needed to determine appropriate thresholds and interventions for applying the model in an intake setting to target high-risk cases in a manner that is acceptable to patients and clinicians.

Adolescents Who Do Not Endorse Risk via the Patient Health Questionnaire Before Self-Harm or Suicide

Importance

Given that the Patient Health Questionnaire (PHQ) item 9 is commonly used to screen for risk of self-harm and suicide, it is important that clinicians recognize circumstances when at-risk adolescents may go undetected.

Objective

To understand characteristics of adolescents with a history of depression who do not endorse the PHQ item 9 before a near-term intentional self-harm event or suicide.

Design, Setting, and Participants

This was a retrospective cohort study design using electronic health record and claims data from January 2009 through September 2017. Settings included primary care and mental health specialty clinics across 7 integrated US health care systems. Included in the study were adolescents aged 13 to 17 years with history of depression who completed the PHQ item 9 within 30 or 90 days before self-harm or suicide. Study data were analyzed September 2022 to April 2023.

Exposures

Demographic, diagnostic, treatment, and health care utilization characteristics.

Main Outcome(s) and Measure(s)

Responded "not at all" (score = 0) to PHQ item 9 regarding thoughts of death or self-harm within 30 or 90 days before self-harm or suicide.

Results

The study included 691 adolescents (mean [SD] age, 15.3 [1.3] years; 541 female [78.3%]) in the 30-day cohort and 1024 adolescents (mean [SD] age, 15.3 [1.3] years; 791 female [77.2%]) in the 90-day cohort. A total of 197 of 691 adolescents (29%) and 330 of 1024 adolescents (32%), respectively, scored 0 before self-harm or suicide on the PHQ item 9 in the 30- and 90-day cohorts. Adolescents seen in primary care (odds ratio [OR], 1.5; 95% CI, 1.0-2.1; P = .03) and older adolescents (OR, 1.2; 95% CI, 1.0-1.3; P = .02) had increased odds of scoring 0 within 90 days of a self-harm event or suicide, and adolescents with a history of inpatient hospitalization and a mental health diagnosis had twice the odds (OR, 2.0; 95% CI, 1.3-3.0; P = .001) of scoring 0 within 30 days. Conversely, adolescents with diagnoses of eating disorders were significantly less likely to score 0 on item 9 (OR, 0.4; 95% CI, 0.2-0.8; P = .007) within 90 days.

Conclusions and Relevance

Study results suggest that older age, history of an inpatient mental health encounter, or being screened in primary care were associated with at-risk adolescents being less likely to endorse having thoughts of death and self-harm on the PHQ item 9 before a self-harm event or suicide death. As use of the PHQ becomes more widespread in practice, additional research is needed for understanding reasons why many at-risk adolescents do not endorse thoughts of death and self-harm.

Association between Services to Address Adverse Social Determinants of Health and Suicide Mortality among Veterans with Indicators of Housing Instability, Unemployment, and Justice Involvement

Suicide among Veterans continues to be a priority issue addressed by the U.S. Department of Veterans Affairs (VA). In addition to a variety of services specifically intended to prevent suicide, VA also offers a number of services to address Veterans' social determinants of health (SDH), several of which may be associated with elevated risk for suicide. For the present study, we assessed whether participation in services to address adverse SDH is associated with a reduction in risk of suicide mortality among Veterans using secondary data from VA datasets (1/1/2014-12/31/2019) for Veterans with an indicator of housing instability, unemployment, or justice involvement. Logistic regressions modeled suicide mortality; use of services to address SDH was the primary predictor. There was not a statistically significant association between services use and suicide mortality; significant correlates included race other than African American, low or no compensation related to disability incurred during military service, and suicidal ideation/attempt during observation period. Suicide is a complex outcome, difficult to predict, and likely the result of many factors; while there is not a consistent association between services use related to adverse SDH and suicide mortality, providers should intervene with Veterans who do not engage in SDH-focused services but have risk factors for suicide mortality.

Suicide Death Prediction Using the Maryland Suicide Data Warehouse: A Sensitivity Analysis

OBJECTIVE

Nearly 50,000 Americans die each year from suicide, despite suicide death being a rare event in the context of health risk assessment and modeling. Prior research has underscored the need for contextualizing suicide risk models in terms of their potential uses and generalizability. This sensitivity analysis makes use of the Maryland Suicide Data Warehouse (MSDW) and illustrates how results inform clinical decision support.

METHOD

A cohort of 1 million living control patients were extracted from the MSDW in addition to 1,667 patients who had died by suicide between the years 2016 and 2019 according to the Maryland Office of the Medical Examiner (OCME). Data were extracted and aggregated as part of a 4-year retrospective design. Binary logistic and two penalized regression models were deployed in a repeated fivefold cross-validation. Model performances were evaluated using sensitivity, positive predictive value (PPV), and F1, and model coefficients were ranked according to coefficient size.

RESULTS

Several features were significantly associated with patients having died by suicide, including male sex, depressive and anxiety disorder diagnoses, social needs, and prior suicidal ideation and suicide attempt. Cross-validated binary logistic regression outperformed either ridge or LASSO (least absolute shrinkage and selection operator) models but generally achieved low-to-moderate PPV and sensitivity across most thresholds and a peak F1 of 0.323.

CONCLUSIONS

Suicide death prediction is constrained by the context of use, which determines the best balance of precision and recall. Predictive models must be evaluated close to the level of intervention. They may not hold up to different needs at different levels of care.

Absence of nonfatal suicidal behavior preceding suicide death reveals differences in clinical risks

Nonfatal suicidality is the most robust predictor of suicide death. However, only ~10% of those who survive an attempt go on to die by suicide. Moreover, ~50% of suicide deaths occur in the absence of prior known attempts, suggesting risks other than nonfatal suicide attempt need to be identified. We studied data from 4,000 population-ascertained suicide deaths and 26,191 population controls to improve understanding of risks leading to suicide death. This study included 2,253 suicide deaths and 3,375 controls with evidence of nonfatal suicidality (SUI_SI/SB and CTL_SI/SB) from diagnostic codes and natural language processing of electronic health records notes. Characteristics of these groups were compared to 1,669 suicides with no prior nonfatal SI/SB (SUI_None) and 22,816 controls with no lifetime suicidality (CTL_None). The SUI_None and CTL_None groups had fewer diagnoses and were older than SUI_SI/SB and CTL_SI/SB. Mental health diagnoses were far less common in both the SUI_None and CTL_None groups; mental health problems were less associated with suicide death than with presence of SI/SB. Physical health diagnoses were conversely more often associated with risk of suicide death than with presence of SI/SB. Pending replication, results indicate highly significant clinical differences among suicide deaths with versus without prior nonfatal SI/SB.

Prediction of suicide attempts among persons with depression: a population-based case cohort study

Studies have highlighted the potential importance of modeling interactions for suicide attempt prediction. This case-cohort study identified risk factors for suicide attempts among persons with depression in Denmark using statistical approaches that do (random forests) or do not (least absolute shrinkage and selection operator regression [LASSO]) model interactions. Cases made a nonfatal suicide attempt (n = 6032) between 1995 and 2015. The comparison subcohort was a 5% random sample of all persons in Denmark on January 1, 1995 (n = 11 963). We used random forests and LASSO for sex-stratified prediction of suicide attempts from demographic variables, psychiatric and somatic diagnoses, and treatments. Poisonings, psychiatric disorders, and medications were important predictors for both sexes. Area under the receiver-operating characteristic curve (AUC) values were higher in LASSO models (in men, 0.85, 95% CI, 0.84-0.86; in women, 0.89, 95% C, 0.88-0.90) than random forests (in men, 0.76, 95% CI, 0.74-0.78; in women, 0.79, 95% CI = 0.78-0.81). Automatic detection of interactions via random forests did not result in better model performance than LASSO models that did not model interactions. Due to the complex nature of psychiatric comorbidity and suicide, modeling interactions may not always be the optimal statistical approach to enhancing suicide attempt prediction in high-risk samples. This article is part of a Special Collection on Mental Health.

The rapid shift to virtual mental health care: Examining psychotherapy disruption by rurality status

BACKGROUND

Given the low usage of virtual health care prior to the COVID-19 pandemic, it was unclear whether those living in rural locations would benefit from increased availability of virtual mental health care. The rapid transition to virtual services during the COVID-19 pandemic allowed for a unique opportunity to examine how the transition to virtual mental health care impacted psychotherapy disruption (i.e., 45+ days between appointments) among individuals living in rural locations compared with those living in nonrural locations.

METHODS

Electronic health record and insurance claims data were collected from three health care systems in the United States including rurality status and psychotherapy disruption. Psychotherapy disruption was measured before and after the COVID-19 pandemic onset.

RESULTS

Both the nonrural and rural cohorts had significant decreases in the rates of psychotherapy disruption from pre- to post-COVID-19 onset (32.5-16.0% and 44.7-24.8%, respectively, p < 0.001). The nonrural cohort had a greater reduction of in-person visits compared with the rural cohort (96.6-45.0 vs. 98.0-66.2%, respectively, p < 0.001). Among the rural cohort, those who were younger and those with lower education had greater reductions in psychotherapy disruption rates from pre- to post-COVID-19 onset. Several mental health disorders were associated with experiencing psychotherapy disruption.

CONCLUSIONS

Though the rapid transition to virtual mental health care decreased the rate of psychotherapy disruption for those living in rural locations, the reduction was less compared with nonrural locations. Other strategies are needed to improve psychotherapy disruption, especially among rural locations (i.e., telephone visits).

Predicting Outcomes of Antidepressant Treatment in Community Practice Settings

OBJECTIVE

The authors examined whether machine-learning models could be used to analyze data from electronic health records (EHRs) to predict patients' responses to antidepressant medications.

METHODS

EHR data from a Washington State health system identified patients ages ≥13 years who started an antidepressant medication in 2016 in a community practice setting and had a baseline Patient Health Questionnaire-9 (PHQ-9) score of ≥10 and at least one PHQ-9 score recorded 14-180 days later. Potential predictors of a response to antidepressants were extracted from the EHR and included demographic characteristics, psychiatric and substance use diagnoses, past psychiatric medication use, mental health service use, and past PHQ-9 scores. Random-forest and penalized regression analyses were used to build models predicting follow-up PHQ-9 score and a favorable treatment response (≥50% improvement in score).

RESULTS

Among 2,469 patients starting antidepressant medication treatment, the mean±SD baseline PHQ-9 score was 17.3±4.5, and the mean lowest follow-up score was 9.2±5.9. Outcome data were available for 72% of the patients. About 48% of the patients had a favorable treatment response. The best-fitting random-forest models yielded a correlation between predicted and observed follow-up scores of 0.38 (95% CI=0.32-0.45) and an area under the receiver operating characteristic curve for a favorable response of 0.57 (95% CI=0.52-0.61). Results were similar for penalized regression models and for models predicting last PHQ-9 score during follow-up.

CONCLUSIONS

Prediction models using EHR data were not accurate enough to inform recommendations for or against starting antidepressant medication. Personalization of depression treatment should instead rely on systematic assessment of early outcomes.

Clarifying the relationship between physical injuries and risk for suicide attempt in a Swedish national sample

INTRODUCTION

The Interpersonal-Psychological Theory of Suicide proposes that capability for suicide is acquired through exposure to painful and provocative events (PPEs). Although there is robust evidence for a positive association between aggregate measures of PPEs and risk for suicidal behavior, little is known about the contributions of physical injuries. The present study investigated the relationship between injuries and risk of subsequent suicide attempt (SA).

METHODS

Data were from Swedish population-based registers. All individuals born in Sweden between 1970 and 1990 were included (N = 1,011,725 females and 1,067,709 males). We used Cox regression models to test associations between 10 types of injuries (eye injury; fracture; dislocation/sprain/strain; injury to nerves and spinal cord; injury to blood vessels; intracranial injury; crushing injury; internal injury; traumatic amputation; and other or unspecified injuries) and risk for later SA. Analyses were stratified by sex and adjusted for year of birth and parental education. Additional models tested for differences in the pattern of associations based on age group and genetic liability for SA. In co-relative models, we tested the association between each injury type and risk for SA in relative pairs of varying genetic relatedness to control for unmeasured familial confounders.

RESULTS

All 10 injury types were associated with elevated risk for SA (hazard ratios [HRs] = 1.2-7.0). Associations were stronger in the first year following an injury (HRs = 1.8-7.0), but HRs remained above 1 more than 1 year after injury exposure (HRs = 1.2-2.6). The strength of associations varied across injury type, sex, age, and genetic liability for SA. For example, the magnitude of the association between crushing injury and risk for SA was larger in females than males, whereas other injuries showed a similar pattern of associations across sex. Moreover, there was evidence to support positive additive interaction effects between several injury types and aggregate genetic liability for SA (relative excess risk due to interaction [RERI] = 0.1-0.3), but the majority of these interactions became non-significant or changed direction after accounting for comorbid psychiatric and substance use disorders. In co-relative models, the pattern of associations differed by injury type, such that there was evidence to support a potential causal effect of eye injury, fracture, dislocation/sprain/strain, intracranial injury, and other and unspecified injuries on risk for SA. For the remaining injury types, HRs were not significantly different from 1 in monozygotic twins, which is consistent with confounding by familial factors.

CONCLUSIONS

Injuries are associated with increased risk for subsequent SA, particularly in the first year following an injury. While genetic and familial environmental factors may partly explain these associations, there is also evidence to support a potential causal effect of several injury types on future risk for SA.

Emergency Department Use in Adolescent and Young Adult Cancer Early Survivors from 2006 to 2020

Purpose: Understanding emergency department (ED) use in adolescent and young adult (AYA) survivors could identify gaps in AYA survivorship. Methods: We conducted a cohort study of 7925 AYA survivors (aged 15-39 years at diagnosis) who were 2-5 years from diagnosis in 2006-2020 at Kaiser Permanente Southern California. We calculated ED utilization rates overall and by indication of the encounter (headache, cardiac issues, and suicide attempts). We estimated rate changes by survivorship year and patient factors associated with ED visit using a Poisson model. Results: Cohort was 65.4% women, 45.8% Hispanic, with mean age at diagnosis at 31.3 years. Overall, 38% of AYA survivors had ≥1 ED visit (95th percentile: 5 ED visits). Unadjusted ED rates declined from 374.2/1000 person-years (PY) in Y2 to 327.2 in Y5 (p change < 0.001). Unadjusted rates declined for headache, cardiac issues, and suicide attempts. Factors associated with increased ED use included: age 20-24 at diagnosis [relative risk (RR) = 1.30, 95% CI 1.09-1.56 vs. 35-39 years]; female (RR = 1.27, 95% CI 1.11-1.47 vs. male); non-Hispanic Black race/ethnicity (RR 1.64, 95% CI 1.38-1.95 vs. non-Hispanic white); comorbidity (RR = 1.34, 95% CI 1.16-1.55 for 1 and RR 1.80, 95% CI 1.40-2.30 for 2+ vs. none); and public insurance (RR = 1.99, 95% CI 1.70-2.32 vs. private). Compared with thyroid cancer, cancers associated with increased ED use were breast (RR = 1.45, 95% CI 1.24-1.70), cervical (RR = 2.18, 95% CI 1.76-2.71), colorectal (RR = 2.34, 95% CI 1.94-2.81), and sarcoma (RR = 1.39, 95% CI 1.03-1.88). Conclusion: ED utilization declined as time from diagnosis elapsed, but higher utilization was associated with social determinants of health and cancer types.

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.

Suicidal ideation in Chinese patients with advanced breast cancer: a multi-center mediation model study

PURPOSE

The pathways underpinning suicide ideation (SI) and certain physical and psychological factors in patients with advanced breast cancer remain unclear. This study develops and validates a mediation model that delineates the associations between several multidimensional variables and SI in Chinese patients with advanced breast cancer.

METHODS

Patients with advanced breast cancer (n = 509) were recruited as study participants from 10 regional cancer centers across China from August 2019 to December 2020. Participants were required to complete five questionnaires using an electronic patient-reported outcomes (ePRO) system: 9 item- Patient Health Questionnaire (PHQ-9), Hospital Anxiety and Depression Scale (HADS), Insomnia Severity Index (ISI), 5-level EQ-5D (EQ-5D-5L), and MD Anderson Symptom Inventory (MDASI). Risk factors for SI were identified using multivariable logistic regression, and inputted into serial multiple mediation models to elucidate the pathways linking the risk factors to SI.

RESULTS

SI prevalence was 22.8% (116/509). After adjusting for covariates, depression (odds ratio [OR] = 1.384), emotional distress (OR = 1.107), upset (OR = 0.842), and forgetfulness (OR = 1.236) were identified as significant independent risk factors (all p < 0.05). The ORs indicate that depression and distress have the strongest associations with SI. Health status has a significant indirect effect (OR=-0.044, p = 0.005) and a strong total effect (OR=-0.485, p < 0.001) on SI, mediated by insomnia severity and emotional distress.

CONCLUSIONS

There is a high SI prevalence among Chinese patients with advanced breast cancer. Our analysis revealed predictive pathways from poor health to heightened SI, mediated by emotional distress and insomnia. Regular management of distress and insomnia can decrease suicide risk in this vulnerable population.

The use of machine learning on administrative and survey data to predict suicidal thoughts and behaviors: a systematic review

Background

Machine learning is a promising tool in the area of suicide prevention due to its ability to combine the effects of multiple risk factors and complex interactions. The power of machine learning has led to an influx of studies on suicide prediction, as well as a few recent reviews. Our study distinguished between data sources and reported the most important predictors of suicide outcomes identified in the literature.

Objective

Our study aimed to identify studies that applied machine learning techniques to administrative and survey data, summarize performance metrics reported in those studies, and enumerate the important risk factors of suicidal thoughts and behaviors identified.

Methods

A systematic literature search of PubMed, Medline, Embase, PsycINFO, Web of Science, Cumulative Index to Nursing and Allied Health Literature (CINAHL), and Allied and Complementary Medicine Database (AMED) to identify all studies that have used machine learning to predict suicidal thoughts and behaviors using administrative and survey data was performed. The search was conducted for articles published between January 1, 2019 and May 11, 2022. In addition, all articles identified in three recently published systematic reviews (the last of which included studies up until January 1, 2019) were retained if they met our inclusion criteria. The predictive power of machine learning methods in predicting suicidal thoughts and behaviors was explored using box plots to summarize the distribution of the area under the receiver operating characteristic curve (AUC) values by machine learning method and suicide outcome (i.e., suicidal thoughts, suicide attempt, and death by suicide). Mean AUCs with 95% confidence intervals (CIs) were computed for each suicide outcome by study design, data source, total sample size, sample size of cases, and machine learning methods employed. The most important risk factors were listed.

Results

The search strategy identified 2,200 unique records, of which 104 articles met the inclusion criteria. Machine learning algorithms achieved good prediction of suicidal thoughts and behaviors (i.e., an AUC between 0.80 and 0.89); however, their predictive power appears to differ across suicide outcomes. The boosting algorithms achieved good prediction of suicidal thoughts, death by suicide, and all suicide outcomes combined, while neural network algorithms achieved good prediction of suicide attempts. The risk factors for suicidal thoughts and behaviors differed depending on the data source and the population under study.

Conclusion

The predictive utility of machine learning for suicidal thoughts and behaviors largely depends on the approach used. The findings of the current review should prove helpful in preparing future machine learning models using administrative and survey data.

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022333454 identifier CRD42022333454.

Predicting suicide death after emergency department visits with mental health or self-harm diagnoses

OBJECTIVE

Use health records data to predict suicide death following emergency department visits.

METHODS

Electronic health records and insurance claims from seven health systems were used to: identify emergency department visits with mental health or self-harm diagnoses by members aged 11 or older; extract approximately 2500 potential predictors including demographic, historical, and baseline clinical characteristics; and ascertain subsequent deaths by self-harm. Logistic regression with lasso and random forest models predicted self-harm death over 90 days after each visit.

RESULTS

Records identified 2,069,170 eligible visits, 899 followed by suicide death within 90 days. The best-fitting logistic regression with lasso model yielded an area under the receiver operating curve of 0.823 (95% CI 0.810-0.836). Visits above the 95th percentile of predicted risk included 34.8% (95% CI 31.1-38.7) of subsequent suicide deaths and had a 0.303% (95% CI 0.261-0.346) suicide death rate over the following 90 days. Model performance was similar across subgroups defined by age, sex, race, and ethnicity.

CONCLUSIONS

Machine learning models using coded data from health records have moderate performance in predicting suicide death following emergency department visits for mental health or self-harm diagnosis and could be used to identify patients needing more systematic follow-up.

Continuous-Time and Dynamic Suicide Attempt Risk Prediction with Neural Ordinary Differential Equations

Suicide is one of the leading causes of death in the US, and the number of attributable deaths continues to increase. Risk of suicide-related behaviors (SRBs) is dynamic, and SRBs can occur across a continuum of time and locations. However, current SRB risk assessment methods, whether conducted by clinicians or through machine learning models, treat SRB risk as static and are confined to specific times and locations, such as following a hospital visit. Such a paradigm is unrealistic as SRB risk fluctuates and creates time gaps in the availability of risk scores. Here, we develop two closely related model classes, Event-GRU-ODE and Event-GRU-Discretized, that can predict the dynamic risk of events as a continuous trajectory based on Neural ODEs, an advanced AI model class for time series prediction. As such, these models can estimate changes in risk across the continuum of future time points, even without new observations, and can update these estimations as new data becomes available. We train and validate these models for SRB prediction using a large electronic health records database. Both models demonstrated high discrimination performance for SRB prediction (e.g., AUROC > 0.92 in the full, general cohort), serving as an initial step toward developing novel and comprehensive suicide prevention strategies based on dynamic changes in risk.

Stability of Suicide Risk Prediction Models During Changes in Health Care Delivery

OBJECTIVE

The authors aimed to use health records data to examine how the accuracy of statistical models predicting self-harm or suicide changed between 2015 and 2019, as health systems implemented suicide prevention programs.

METHODS

Data from four large health systems were used to identify specialty mental health visits by patients ages ≥11 years, assess 311 potential predictors of self-harm (including demographic characteristics, historical risk factors, and index visit characteristics), and ascertain fatal or nonfatal self-harm events over 90 days after each visit. New prediction models were developed with logistic regression with LASSO (least absolute shrinkage and selection operator) in random samples of visits (65%) from each calendar year and were validated in the remaining portion of the sample (35%).

RESULTS

A model developed for visits from 2009 to mid-2015 showed similar classification performance and calibration accuracy in a new sample of about 13.1 million visits from late 2015 to 2019. Area under the receiver operating characteristic curve (AUC) ranged from 0.840 to 0.849 in the new sample, compared with 0.851 in the original sample. New models developed for each year for 2015-2019 had classification performance (AUC range 0.790-0.853), sensitivity, and positive predictive value similar to those of the previously developed model. Models selected similar predictors from 2015 to 2019, except for more frequent selection of depression questionnaire data in later years, when questionnaires were more frequently recorded.

CONCLUSIONS

A self-harm prediction model developed with 2009-2015 visit data performed similarly when applied to 2015-2019 visits. New models did not yield superior performance or identify different predictors.

A Randomized Control Trial of a Digital Health Tool for Safer Firearm and Medication Storage for Patients with Suicide Risk

Most patients with suicide risk do not receive recommendations to reduce access to lethal means due to a variety of barriers (e.g., lack of provider time, training). Determine if highly efficient population-based EHR messaging to visit the Lock to Live (L2L) decision aid impacts patient-reported storage behaviors. Randomized trial. Integrated health care system serving Denver, CO. Served by primary care or mental health specialty clinic in the 75-99.5th risk percentile on a suicide attempt or death prediction model. Lock to Live (L2L) is a web-based decision aid that incorporates patients' values into recommendations for safe storage of lethal means, including firearms and medications. Anonymous survey that determined readiness to change: pre-contemplative (do not believe in safe storage), contemplative (believe in safe storage but not doing it), preparation (planning storage changes) or action (safely storing). There were 21,131 patients randomized over a 6-month period with a 27% survey response rate. Many (44%) had access to a firearm, but most of these (81%) did not use any safe firearm storage behaviors. Intervention patients were more likely to be categorized as preparation or action compared to controls for firearm storage (OR = 1.30 (1.07-1.58)). When examining action alone, there were no group differences. There were no statistically significant differences for any medication storage behaviors. Selection bias in those who responded to survey. Efficiently sending an EHR invitation message to visit L2L encouraged patients with suicide risk to consider safer firearm storage practices, but a stronger intervention is needed to change storage behaviors. Future studies should evaluate whether combining EHR messaging with provider nudges (e.g., brief clinician counseling) changes storage behavior.ClinicalTrials.gov: NCT05288517.

Development of a 3-Step theory of suicide ontology to facilitate 3ST factor extraction from clinical progress notes

OBJECTIVE

Suicide risk prediction algorithms at the Veterans Health Administration (VHA) do not include predictors based on the 3-Step Theory of suicide (3ST), which builds on hopelessness, psychological pain, connectedness, and capacity for suicide. These four factors are not available from structured fields in VHA electronic health records, but they are found in unstructured clinical text. An ontology and controlled vocabulary that maps psychosocial and behavioral terms to these factors does not exist. The objectives of this study were 1) to develop an ontology with a controlled vocabulary of terms that map onto classes that represent the 3ST factors as identified within electronic clinical progress notes, and 2) to determine the accuracy of automated extractions based on terms in the controlled vocabulary.

METHODS

A team of four annotators did linguistic annotation of 30,000 clinical progress notes from 231 Veterans in VHA electronic health records who attempted suicide or who died by suicide for terms relating to the 3ST factors. Annotation involved manually assigning a label to words or phrases that indicated presence or absence of the factor (polarity). These words and phrases were entered into a controlled vocabulary that was then used by our computational system to tag 14 million clinical progress notes from Veterans who attempted or died by suicide after 2013. Tagged text was extracted and machine-labelled for presence or absence of the 3ST factors. Accuracy of these machine-labels was determined for 1000 randomly selected extractions for each factor against a ground truth created by our annotators.

RESULTS

Linguistic annotation identified 8486 terms that related to 33 subclasses across the four factors and polarities. Precision of machine-labeled extractions ranged from 0.73 to 1.00 for most factor-polarity combinations, whereas recall was somewhat lower 0.65-0.91.

CONCLUSION

The ontology that was developed consists of classes that represent each of the four 3ST factors, subclasses, relationships, and terms that map onto those classes which are stored in a controlled vocabulary (https://bioportal.bioontology.org/ontologies/THREE-ST). The use case that we present shows how scores based on clinical notes tagged for terms in the controlled vocabulary capture meaningful change in the 3ST factors during weeks preceding a suicidal event.

High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning

We present an ensemble transfer learning method to predict suicide from Veterans Affairs (VA) electronic medical records (EMR). A diverse set of base models was trained to predict a binary outcome constructed from reported suicide, suicide attempt, and overdose diagnoses with varying choices of study design and prediction methodology. Each model used twenty cross-sectional and 190 longitudinal variables observed in eight time intervals covering 7.5 years prior to the time of prediction. Ensembles of seven base models were created and fine-tuned with ten variables expected to change with study design and outcome definition in order to predict suicide and combined outcome in a prospective cohort. The ensemble models achieved c-statistics of 0.73 on 2-year suicide risk and 0.83 on the combined outcome when predicting on a prospective cohort of [Formula: see text] 4.2 M veterans. The ensembles rely on nonlinear base models trained using a matched retrospective nested case-control (Rcc) study cohort and show good calibration across a diversity of subgroups, including risk strata, age, sex, race, and level of healthcare utilization. In addition, a linear Rcc base model provided a rich set of biological predictors, including indicators of suicide, substance use disorder, mental health diagnoses and treatments, hypoxia and vascular damage, and demographics.

Applying contrastive pre-training for depression and anxiety risk prediction in type 2 diabetes patients based on heterogeneous electronic health records: a primary healthcare case study

OBJECTIVE

Due to heterogeneity and limited medical data in primary healthcare services (PHS), assessing the psychological risk of type 2 diabetes mellitus (T2DM) patients in PHS is difficult. Using unsupervised contrastive pre-training, we proposed a deep learning framework named depression and anxiety prediction (DAP) to predict depression and anxiety in T2DM patients.

MATERIALS AND METHODS

The DAP model consists of two sub-models. Firstly, the pre-trained model of DAP used unlabeled discharge records of 85 085 T2DM patients from the First Affiliated Hospital of Nanjing Medical University for unsupervised contrastive learning on heterogeneous electronic health records (EHRs). Secondly, the fine-tuned model of DAP used case-control cohorts (17 491 patients) selected from 149 596 T2DM patients' EHRs in the Nanjing Health Information Platform (NHIP). The DAP model was validated in 1028 patients from PHS in NHIP. Evaluation included receiver operating characteristic area under the curve (ROC-AUC) and precision-recall area under the curve (PR-AUC), and decision curve analysis (DCA).

RESULTS

The pre-training step allowed the DAP model to converge at a faster rate. The fine-tuned DAP model significantly outperformed the baseline models (logistic regression, extreme gradient boosting, and random forest) with ROC-AUC of 0.91±0.028 and PR-AUC of 0.80±0.067 in 10-fold internal validation, and with ROC-AUC of 0.75 ± 0.045 and PR-AUC of 0.47 ± 0.081 in external validation. The DCA indicate the clinical potential of the DAP model.

CONCLUSION

The DAP model effectively predicted post-discharge depression and anxiety in T2DM patients from PHS, reducing data fragmentation and limitations. This study highlights the DAP model's potential for early detection and intervention in depression and anxiety, improving outcomes for diabetes patients.

Embers of the Past: Early Childhood Traumas Interact with Variation in P2RX7 Gene Implicated in Neuroinflammation on Markers of Current Suicide Risk

Both early childhood traumatic experiences and current stress increase the risk of suicidal behaviour, in which immune activation might play a role. Previous research suggests an association between mood disorders and P2RX7 gene encoding P2X7 receptors, which stimulate neuroinflammation. We investigated the effect of P2RX7 variation in interaction with early childhood adversities and traumas and recent stressors on lifetime suicide attempts and current suicide risk markers. Overall, 1644 participants completed questionnaires assessing childhood adversities, recent negative life events, and provided information about previous suicide attempts and current suicide risk-related markers, including thoughts of ending their life, death, and hopelessness. Subjects were genotyped for 681 SNPs in the P2RX7 gene, 335 of which passed quality control and were entered into logistic and linear regression models, followed by a clumping procedure to identify clumps of SNPs with a significant main and interaction effect. We identified two significant clumps with a main effect on current suicidal ideation with top SNPs rs641940 and rs1653613. In interaction with childhood trauma, we identified a clump with top SNP psy_rs11615992 and another clump on hopelessness containing rs78473339 as index SNP. Our results suggest that P2RX7 variation may mediate the effect of early childhood adversities and traumas on later emergence of suicide risk.

Determining Distinct Suicide Attempts From Recurrent Electronic Health Record Codes: Classification Study

BACKGROUND

Prior suicide attempts are a relatively strong risk factor for future suicide attempts. There is growing interest in using longitudinal electronic health record (EHR) data to derive statistical risk prediction models for future suicide attempts and other suicidal behavior outcomes. However, model performance may be inflated by a largely unrecognized form of "data leakage" during model training: diagnostic codes for suicide attempt outcomes may refer to prior attempts that are also included in the model as predictors.

OBJECTIVE

We aimed to develop an automated rule for determining when documented suicide attempt diagnostic codes identify distinct suicide attempt events.

METHODS

From a large health care system's EHR, we randomly sampled suicide attempt codes for 300 patients with at least one pair of suicide attempt codes documented at least one but no more than 90 days apart. Supervised chart reviewers assigned the clinical settings (ie, emergency department [ED] versus non-ED), methods of suicide attempt, and intercode interval (number of days). The probability (or positive predictive value) that the second suicide attempt code in a given pair of codes referred to a distinct suicide attempt event from its preceding suicide attempt code was calculated by clinical setting, method, and intercode interval.

RESULTS

Of 1015 code pairs reviewed, 835 (82.3%) were nonindependent (ie, the 2 codes referred to the same suicide attempt event). When the second code in a pair was documented in a clinical setting other than the ED, it represented a distinct suicide attempt 3.3% of the time. The more time elapsed between codes, the more likely the second code in a pair referred to a distinct suicide attempt event from its preceding code. Code pairs in which the second suicide attempt code was assigned in an ED at least 5 days after its preceding suicide attempt code had a positive predictive value of 0.90.

CONCLUSIONS

EHR-based suicide risk prediction models that include International Classification of Diseases codes for prior suicide attempts as a predictor may be highly susceptible to bias due to data leakage in model training. We derived a simple rule to distinguish codes that reflect new, independent suicide attempts: suicide attempt codes documented in an ED setting at least 5 days after a preceding suicide attempt code can be confidently treated as new events in EHR-based suicide risk prediction models. This rule has the potential to minimize upward bias in model performance when prior suicide attempts are included as predictors in EHR-based suicide risk prediction models.

Adolescent, parent, and provider attitudes toward a machine learning based clinical decision support system for selecting treatment for youth depression

BACKGROUND

Machine learning based clinical decision support systems (CDSSs) have been proposed as a means of advancing personalized treatment planning for disorders, such as depression, that have a multifaceted etiology, course, and symptom profile. However, machine learning based models for treatment selection are rare in the field of psychiatry. They have also not yet been translated for use in clinical practice. Understanding key stakeholder attitudes toward machine learning based CDSSs is critical for developing plans for their implementation that promote uptake by both providers and families.

METHODS

In Study 1, a prototype machine learning based Clinical Decision Support System for Youth Depression (CDSS-YD) was demonstrated to focus groups of adolescents with a diagnosis of depression (n = 9), parents (n = 11), and behavioral health providers (n = 8). Qualitative analysis was used to assess their attitudes towards the CDSS-YD. In Study 2, behavioral health providers were trained in the use of the CDSS-YD and they utilized the CDSS-YD in a clinical encounter with 6 adolescents and their parents as part of their treatment planning discussion. Following the appointment, providers, parents, and adolescents completed a survey about their attitudes regarding the use of the CDSS-YD.

RESULTS

All stakeholder groups viewed the CDSS-YD as an easy to understand and useful tool for making personalized treatment decisions, and families and providers were able to successfully use the CDSS-YD in clinical encounters. Parents and adolescents viewed their providers as having a critical role in the use the CDSS-YD, and this had implications for the perceived trustworthiness of the CDSS-YD. Providers reported that clinic productivity metrics would be the primary barrier to CDSS-YD implementation, with the creation of protected time for training, preparation, and use as a key facilitator.

CONCLUSIONS

Machine learning based CDSSs, if proven effective, have the potential to be widely accepted tools for personalized treatment planning. Successful implementation will require addressing the system-level barrier of having sufficient time and energy to integrate it into practice.

Predicting risk of suicidal behavior from insurance claims data vs. linked data from insurance claims and electronic health records

PURPOSE

Observational studies assessing effects of medical products on suicidal behavior often rely on health record data to account for pre-existing risk. We assess whether high-dimensional models predicting suicide risk using data derived from insurance claims and electronic health records (EHRs) are superior to models using data from insurance claims alone.

METHODS

Data were from seven large health systems identified outpatient mental health visits by patients aged 11 or older between 1/1/2009 and 9/30/2017. Data for the 5 years prior to each visit identified potential predictors of suicidal behavior typically available from insurance claims (e.g., mental health diagnoses, procedure codes, medication dispensings) and additional potential predictors available from EHRs (self-reported race and ethnicity, responses to Patient Health Questionnaire or PHQ-9 depression questionnaires). Nonfatal self-harm events following each visit were identified from insurance claims data and fatal self-harm events were identified by linkage to state mortality records. Random forest models predicting nonfatal or fatal self-harm over 90 days following each visit were developed in a 70% random sample of visits and validated in a held-out sample of 30%. Performance of models using linked claims and EHR data was compared to models using claims data only.

RESULTS

Among 15 845 047 encounters by 1 574 612 patients, 99 098 (0.6%) were followed by a self-harm event within 90 days. Overall classification performance did not differ between the best-fitting model using all data (area under the receiver operating curve or AUC = 0.846, 95% CI 0.839-0.854) and the best-fitting model limited to data available from insurance claims (AUC = 0.846, 95% CI 0.838-0.853). Competing models showed similar classification performance across a range of cut-points and similar calibration performance across a range of risk strata. Results were similar when the sample was limited to health systems and time periods where PHQ-9 depression questionnaires were recorded more frequently.

CONCLUSION

Investigators using health record data to account for pre-existing risk in observational studies of suicidal behavior need not limit that research to databases including linked EHR data.

How Can Digital Mental Health Enhance Psychiatry?

The use of digital technologies is constantly growing around the world. The wider-spread adoption of digital technologies and solutions in the daily clinical practice in psychiatry seems to be a question of when, not if. We propose a synthesis of the scientific literature on digital technologies in psychiatry and discuss the main aspects of its possible uses and interests in psychiatry according to three domains of influence that appeared to us: 1) assist and improve current care: digital psychiatry allows for more people to have access to care by simply being more accessible but also by being less stigmatized and more convenient; 2) develop new treatments: digital psychiatry allows for new treatments to be distributed via apps, and practical guidelines can reduce ethical challenges and increase the efficacy of digital tools; and 3) produce scientific and medical knowledge: digital technologies offer larger and more objective data collection, allowing for more detection and prevention of symptoms. Finally, ethical and efficacy issues remain, and some guidelines have been put forth on how to safely use these solutions and prepare for the future.

Suicide attempts after bariatric surgery: comparison to a nonsurgical cohort of individuals with severe obesity

BACKGROUND

The rate of suicide is higher among individuals following bariatric surgery compared with the general population; however, it is not clear whether risk is associated with bariatric surgery beyond having severe obesity.

OBJECTIVE

To compare the risk of a suicide attempt among those who had bariatric surgery versus a nonsurgical cohort with severe obesity.

SETTING

Aggregate count data were collected from 5 healthcare systems.

METHODS

Individuals were identified in the surgical cohort if they underwent bariatric surgery between 2009 and 2017 (n = 35,522) and then were compared with a cohort of individuals with severe obesity who never had bariatric surgery (n = 691,752). Suicide attempts were identified after study enrollment date using International Classification of Diseases, Ninth and Tenth Editions (ICD-9 and ICD-10) diagnosis codes from 2009 to 2021.

RESULTS

The relative risk of a suicide attempt was 64% higher in the cohort with bariatric surgery than that of the nonsurgical cohort (2.2% versus 1.3%; relative risk = 1.64; 95% CI, 1.53-1.76). Within the cohort with bariatric surgery, suicide attempts were more common among the 18- to 39-year age group (P < .001), women (P = .002), Hawaiian-Pacific Islanders (P < .001), those with Medicaid insurance (P < .001), and those with a documented mental health condition at baseline (in the previous 2 years; P < .001).

CONCLUSIONS

The relative risk of suicide attempts was higher among those who underwent bariatric surgery compared with a nonsurgical cohort, though absolute risk remained low. Providers should be aware of this increased risk. Screening for suicide risk after bariatric surgery may be useful to identify high-risk individuals.

TransformEHR: transformer-based encoder-decoder generative model to enhance prediction of disease outcomes using electronic health records

Deep learning transformer-based models using longitudinal electronic health records (EHRs) have shown a great success in prediction of clinical diseases or outcomes. Pretraining on a large dataset can help such models map the input space better and boost their performance on relevant tasks through finetuning with limited data. In this study, we present TransformEHR, a generative encoder-decoder model with transformer that is pretrained using a new pretraining objective-predicting all diseases and outcomes of a patient at a future visit from previous visits. TransformEHR's encoder-decoder framework, paired with the novel pretraining objective, helps it achieve the new state-of-the-art performance on multiple clinical prediction tasks. Comparing with the previous model, TransformEHR improves area under the precision-recall curve by 2% (p < 0.001) for pancreatic cancer onset and by 24% (p = 0.007) for intentional self-harm in patients with post-traumatic stress disorder. The high performance in predicting intentional self-harm shows the potential of TransformEHR in building effective clinical intervention systems. TransformEHR is also generalizable and can be easily finetuned for clinical prediction tasks with limited data.

Managed care updates of subscriber jail release to prompt community suicide prevention: clinical trial protocol

BACKGROUND

Recent jail detention is a marker for trait and state suicide risk in community-based populations. However, healthcare providers are typically unaware that their client was in jail and few post-release suicide prevention efforts exist. This protocol paper describes an effectiveness-implementation trial evaluating community suicide prevention practices triggered by advances in informatics that alert CareSource, a large managed care organization (MCO), when a subscriber is released from jail.

METHODS

This randomized controlled trial investigates two evidence-based suicide prevention practices triggered by CareSource's jail detention/release notifications, in a partial factorial design. The first phase randomizes ~ 43,000 CareSource subscribers who pass through any Ohio jail to receive Caring Contact letters sent by CareSource or to Usual Care after jail release. The second phase (running simultaneously) involves a subset of ~ 6,000 of the 43,000 subscribers passing through jail who have been seen in one of 12 contracted behavioral health agencies in the 6 months prior to incarceration in a stepped-wedge design. Agencies will receive: (a) notifications of the client's jail detention/release, (b) instructions for re-engaging these clients, and (c) training in suicide risk assessment and the Safety Planning Intervention for use at re-engagement. We will track suicide-related and service linkage outcomes 6 months following jail release using claims data.

CONCLUSIONS

This design allows us to rigorously test two intervention main effects and their interaction. It also provides valuable information on the effects of system-level change and the scalability of interventions using big data from a MCO to flag jail release and suicide risk.

TRIAL REGISTRATION

The trial is registered at clinicaltrials.gov (NCT05579600). Registered 27 June, 2023.

Views on sharing mental health data for research purposes: qualitative analysis of interviews with people with mental illness

BACKGROUND

Improving the ways in which routinely-collected mental health data are shared could facilitate substantial advances in research and treatment. However, this process should only be undertaken in partnership with those who provide such data. Despite relatively widespread investigation of public perspectives on health data sharing more generally, there is a lack of research on the views of people with mental illness.

METHODS

Twelve people with lived experience of mental illness took part in semi-structured interviews via online video software. Participants had experience of a broad range of mental health conditions including anxiety, depression, schizophrenia, eating disorders and addiction. Interview questions sought to establish how participants felt about the use of routinely-collected health data for research purposes, covering different types of health data, what health data should be used for, and any concerns around its use.

RESULTS

Thematic analysis identified four overarching themes: benefits of sharing mental health data, concerns about sharing mental health data, safeguards, and data types. Participants were clear that health data sharing should facilitate improved scientific knowledge and better treatments for mental illness. There were concerns that data misuse could become another way in which individuals and society discriminate against people with mental illness, for example through insurance premiums or employment decisions. Despite this there was a generally positive attitude to sharing mental health data as long as appropriate safeguards were in place.

CONCLUSIONS

There was notable strength of feeling across participants that more should be done to reduce the suffering caused by mental illness, and that this could be partly facilitated by well-managed sharing of health data. The mental health research community could build on this generally positive attitude to mental health data sharing by following rigorous best practice tailored to the specific concerns of people with mental illness.

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.

External Validation and Updating of a Statistical Civilian-Based Suicide Risk Model in US Naval Primary Care

Importance

Suicide remains an ongoing concern in the US military. Statistical models have not been broadly disseminated for US Navy service members.

Objective

To externally validate and update a statistical suicide risk model initially developed in a civilian setting with an emphasis on primary care.

Design, Setting, and Participants

This retrospective cohort study used data collected from 2007 through 2017 among active-duty US Navy service members. The external civilian model was applied to every visit at Naval Medical Center Portsmouth (NMCP), its NMCP Naval Branch Health Clinics (NBHCs), and TRICARE Prime Clinics (TPCs) that fall within the NMCP area. The model was retrained and recalibrated using visits to NBHCs and TPCs and updated using Department of Defense (DoD)-specific billing codes and demographic characteristics, including expanded race and ethnicity categories. Domain and temporal analyses were performed with bootstrap validation. Data analysis was performed from September 2020 to December 2022.

Exposure

Visit to US NMCP.

Main Outcomes and Measures

Recorded suicidal behavior on the day of or within 30 days of a visit. Performance was assessed using area under the receiver operating curve (AUROC), area under the precision recall curve (AUPRC), Brier score, and Spiegelhalter z-test statistic.

Results

Of the 260 583 service members, 6529 (2.5%) had a recorded suicidal behavior, 206 412 (79.2%) were male; 104 835 (40.2%) were aged 20 to 24 years; and 9458 (3.6%) were Asian, 56 715 (21.8%) were Black or African American, and 158 277 (60.7%) were White. Applying the civilian-trained model resulted in an AUROC of 0.77 (95% CI, 0.74-0.79) and an AUPRC of 0.004 (95% CI, 0.003-0.005) at NBHCs with poor calibration (Spiegelhalter P < .001). Retraining the algorithm improved AUROC to 0.92 (95% CI, 0.91-0.93) and AUPRC to 0.66 (95% CI, 0.63-0.68). Number needed to screen in the top risk tiers was 366 for the external model and 200 for the retrained model; the lower number indicates better performance. Domain validation showed AUROC of 0.90 (95% CI, 0.90-0.91) and AUPRC of 0.01 (95% CI, 0.01-0.01), and temporal validation showed AUROC of 0.75 (95% CI, 0.72-0.78) and AUPRC of 0.003 (95% CI, 0.003-0.005).

Conclusions and Relevance

In this cohort study of active-duty Navy service members, a civilian suicide attempt risk model was externally validated. Retraining and updating with DoD-specific variables improved performance. Domain and temporal validation results were similar to external validation, suggesting that implementing an external model in US Navy primary care clinics may bypass the need for costly internal development and expedite the automation of suicide prevention in these clinics.

Association Between Adverse Social Determinants of Health and Suicide Death

OBJECTIVE

The aim of this study was to identify adverse social determinants of health (SDoH) International Statistical Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) code prevalence among individuals who died by suicide and to examine associations between documented adverse SDoH and suicide.

RESEARCH DESIGN

A case-control study using linked medical record, insurance claim, and mortality data from 2000 to 2015 obtained from 9 Mental Health Research Network-affiliated health systems. We included 3330 individuals who died by suicide and 333,000 randomly selected controls matched on index year and health system location. All individuals in the study (cases and controls) had at least 10 months of enrollment before the study index date. The index date for the study for each case and their matched controls was the suicide date for that given case.

RESULTS

Adverse SDoH documentation was low; only 6.6% of cases had ≥1 documented adverse SDoH in the year before suicide. Any documented SDoH and several specific adverse SDoH categories were more frequent among cases than controls. Any documented adverse SDoH was associated with higher suicide odds [adjusted odds ratio (aOR)=2.76; 95% CI: 2.38-3.20], as was family alcoholism/drug addiction (aOR=18.23; 95% CI: 8.54-38.92), being an abuse victim/perpetrator (aOR=2.53; 95% CI: 1.99-3.21), other primary support group problems (aOR=1.91; 95% CI: 1.32-2.75), employment/occupational maladjustment problems (aOR=8.83; 95% CI: 5.62-13.87), housing/economic problems (aOR: 6.41; 95% CI: 4.47-9.19), legal problems (aOR=27.30; 95% CI: 12.35-60.33), and other psychosocial problems (aOR=2.58; 95% CI: 1.98-3.36).

CONCLUSIONS

Although documented SDoH prevalence was low, several adverse SDoH were associated with increased suicide odds, supporting calls to increase SDoH documentation in medical records. This will improve understanding of SDoH prevalence and assist in identification and intervention among individuals at high suicide risk.

Effect of selective serotonin reuptake inhibitor treatment following diagnosis of depression on suicidal behaviour risk: a target trial emulation

There is concern regarding the impact of selective serotonin reuptake inhibitors (SSRIs) on suicidal behaviour. Using the target trial framework, we investigated the effect on suicidal behaviour of SSRI treatment following a depression diagnosis. We identified 162,267 individuals receiving a depression diagnosis aged 6-59 years during 2006-2018 in Stockholm County, Sweden, after at least 1 year without antidepressant dispensation. Individuals who initiated an SSRI within 28 days of the diagnosis were assigned as SSRI initiators, others as non-initiators. Intention-to-treat and per-protocol effects were estimated; for the latter, individuals were censored when they ceased adhering to their assigned treatment strategy. We applied inverse probability weighting (IPW) to account for baseline confounding in the intention-to-treat analysis, and additionally for treatment non-adherence and time-varying confounding in the per-protocol analysis. The suicidal behaviour risk difference (RD), and risk ratio (RR) between SSRI initiators and non-initiators were estimated at 12 weeks. In the overall cohort, we found an increased risk of suicidal behaviour among SSRI initiators (intention-to-treat RR = 1.50, 95% CI = 1.25, 1.80; per-protocol RR = 1.69, 95% CI = 1.20, 2.36). In age strata, we only found evidence of an increased risk among individuals under age 25, with the greatest risk among 6-17-year-olds (intention-to-treat RR = 2.90, 95% CI = 1.72, 4.91; per-protocol RR = 3.34, 95% CI = 1.59, 7.00). Our finding of an increased suicidal behaviour risk among individuals under age 25 reflects evidence from RCTs. We found no evidence of an effect in the high-risk group of individuals with past suicidal behaviour. Further studies with information on a wider array of confounders are called for.

Effects of Geography on Risk for Future Suicidal Ideation and Attempts Among Children and Youth

Objective

Geography may influence the relationships of predictors for suicidal ideation (SI) and suicide attempts (SA) in children and youth.

Method

This is a nationwide retrospective cohort study of 124,424 individuals less than 25 years of age using commercial claims data (2011-2015) from the Health Care Cost Institute. Outcomes were time to SI or SA within 3 months after the indexed mental health or substance use disorder (MH/SUD) outpatient visit. Predictors included sociodemographic and clinical characteristics up to 3 years before the index event.

Results

At each follow-up time period, rates of SI and SA varied by the US geographic division (p < .001), and the Mountain Division consistently had the highest rates for both SI and SA (5.44%-10.26% for SI; 0.70%-2.82% for SA). Having MH emergency department (ED) visits in the past year increased the risk of SI by 28% to 65% for individuals residing in the New England, Mid-Atlantic, East North Central, West North Central, and East South Central Divisions. The main effects of geographic divisions were significant for SA (p<0.001). Risk of SA was lower in New England, Mid-Atlantic, South Atlantic, and Pacific (hazard ratios = 0.57, 0.51, 0.67, and 0.79, respectively) and higher in the Mountain Division (hazard ratio = 1.46).

Conclusion

To understand the underlying mechanisms driving the high prevalence of SI and SA in the Mountain Division and the elevated risk of SI after having MH ED visits, future research examining regional differences in risks for SI and SA should include indicators of access to MH ED care and other social determinants of health.

Adolescent, parent, and provider attitudes toward a machine-learning based clinical decision support system for selecting treatment for youth depression

Background

Machine-learning based clinical decision support systems (CDSSs) have been proposed as a means of advancing personalized treatment planning for disorders, such as depression, that have a multifaceted etiology, course, and symptom profile. However, machine-learning based models for treatment selection are rare in the field of psychiatry. They have also not yet been translated for use in clinical practice. Understanding key stakeholder attitudes toward machine learning-based CDSSs is critical for developing plans for their implementation that promote uptake by both providers and families.

Methods

In Study 1, a machine-learning based Clinical Decision Support System for Youth Depression (CDSS-YD) was demonstrated to focus groups of adolescents with a diagnosis of depression (n = 9), parents (n = 11), and behavioral health providers (n = 8). Qualitative analysis was used to assess their attitudes towards the CDSS-YD. In Study 2, behavioral health providers were trained in the use of the CDSS-YD and they utilized the CDSS-YD in a clinical encounter with 6 adolescents and their parents as part of their treatment planning discussion. Following the appointment, providers, parents, and adolescents completed a survey about their attitudes regarding the use of the CDSS-YD.

Results

All stakeholder groups viewed the CDSS-YD as an easy to understand and useful tool for making personalized treatment decisions, and families and providers were able to successfully use the CDSS-YD in clinical encounters. Parents and adolescents viewed their providers as having a critical role in the use the CDSS-YD, and this had implications for the perceived trustworthiness of the CDSS-YD. Providers reported that clinic productivity metrics would be the primary barrier to CDSS-YD implementation, with the creation of protected time for training, preparation, and use as a key facilitator.

Conclusions

The CDSS-YD has the potential to be a widely accepted and useful tool for personalized treatment planning. Successful implementation will require addressing the system-level barrier of having sufficient time and energy to integrate it into practice.

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.

Harnessing Artificial Intelligence: Strategies for Mental Health Nurses in Optimizing Psychiatric Patient Care

This narrative review explores the transformative impact of Artificial Intelligence (AI) on mental health nursing, particularly in enhancing psychiatric patient care. AI technologies present new strategies for early detection, risk assessment, and improving treatment adherence in mental health. They also facilitate remote patient monitoring, bridge geographical gaps, and support clinical decision-making. The evolution of virtual mental health assistants and AI-enhanced therapeutic interventions are also discussed. These technological advancements reshape the nurse-patient interactions while ensuring personalized, efficient, and high-quality care. The review also addresses AI's ethical and responsible use in mental health nursing, emphasizing patient privacy, data security, and the balance between human interaction and AI tools. As AI applications in mental health care continue to evolve, this review encourages continued innovation while advocating for responsible implementation, thereby optimally leveraging the potential of AI in mental health nursing.

Managed Care Updates of Subscriber Jail Release to Prompt Community Suicide Prevention: Clinical Trial Protocol

Background

Recent jail detention is a marker for trait and state suicide risk in community-based populations. However, healthcare providers are typically unaware that their client was in jail and few post-release suicide prevention efforts exist. This protocol paper describes an effectiveness-implementation trial evaluating community suicide prevention practices triggered by advances in informatics that alert CareSource, a large managed care organization (MCO), when a subscriber is released from jail.

Methods

This randomized controlled trial investigates two evidence-based suicide prevention practices triggered by CareSource's jail detention/release notifications, in a partial factorial design. The first phase randomizes ~43,000 CareSource subscribers who pass through any Ohio jail to receive Caring Contact letters sent by CareSource or to Usual Care after jail release. The second phase (running simultaneously) involves a subset of ~6,000 of the 43,000 subscribers passing through jail who have been seen in one of 12 contracted behavioral health agencies in the 6 months prior to incarceration in a stepped-wedge design. Agencies will receive: (a) notifications of the client's jail detention/release, (b) instructions for re-engaging these clients, and (c) training in suicide risk assessment and the Safety Planning Intervention for use at re-engagement. We will track suicide-related and service linkage outcomes 6 months following jail release using claims data.

Conclusions

This design allows us to rigorously test two intervention main effects and their interaction. It also provides valuable information on the effects of system-level change and the scalability of interventions using big data from a MCO to flag jail release and suicide risk.

Trial Registration

The trial is registered at clinicaltrials.gov (NCT05579600). Registered 27 June, 2023, https://beta.clinicaltrials.gov/study/NCT05579600?cond=Suicide&term=Managed%20Care&rank=1.

Electronic health records identify timely trends in childhood mental health conditions

BACKGROUND

Electronic health records (EHRs) data provide an opportunity to collect patient information rapidly, efficiently and at scale. National collaborative research networks, such as PEDSnet, aggregate EHRs data across institutions, enabling rapid identification of pediatric disease cohorts and generating new knowledge for medical conditions. To date, aggregation of EHR data has had limited applications in advancing our understanding of mental health (MH) conditions, in part due to the limited research in clinical informatics, necessary for the translation of EHR data to child mental health research.

METHODS

In this cohort study, a comprehensive EHR-based typology was developed by an interdisciplinary team, with expertise in informatics and child and adolescent psychiatry, to query aggregated, standardized EHR data for the full spectrum of MH conditions (disorders/symptoms and exposure to adverse childhood experiences (ACEs), across 13 years (2010-2023), from 9 PEDSnet centers. Patients with and without MH disorders/symptoms (without ACEs), were compared by age, gender, race/ethnicity, insurance, and chronic physical conditions. Patients with ACEs alone were compared with those that also had MH disorders/symptoms. Prevalence estimates for patients with 1+ disorder/symptoms and for specific disorders/symptoms and exposure to ACEs were calculated, as well as risk for developing MH disorder/symptoms.

RESULTS

The EHR study data set included 7,852,081 patients < 21 years of age, of which 52.1% were male. Of this group, 1,552,726 (19.8%), without exposure to ACEs, had a lifetime MH disorders/symptoms, 56.5% being male. Annual prevalence estimates of MH disorders/symptoms (without exposure to ACEs) rose from 10.6% to 2010 to 15.1% in 2023, a 44% relative increase, peaking to 15.4% in 2019, prior to the Covid-19 pandemic. MH categories with the largest increases between 2010 and 2023 were exposure to ACEs (1.7, 95% CI 1.6-1.8), anxiety disorders (2.8, 95% CI 2.8-2.9), eating/feeding disorders (2.1, 95% CI 2.1-2.2), gender dysphoria/sexual dysfunction (43.6, 95% CI 35.8-53.0), and intentional self-harm/suicidality (3.3, 95% CI 3.2-3.5). White youths had the highest rates in most categories, except for disruptive behavior disorders, elimination disorders, psychotic disorders, and standalone symptoms which Black youths had higher rates. Median age of detection was 8.1 years (IQR 3.5-13.5) with all standalone symptoms recorded earlier than the corresponding MH disorder categories.

CONCLUSIONS

These results support EHRs' capability in capturing the full spectrum of MH disorders/symptoms and exposure to ACEs, identifying the proportion of patients and groups at risk, and detecting trends throughout a 13-year period that included the Covid-19 pandemic. Standardized EHR data, which capture MH conditions is critical for health systems to examine past and current trends for future surveillance. Our publicly available EHR-mental health typology codes can be used in other studies to further advance research in this area.

Suicide-specific mortality among patients with treatment-resistant major depressive disorder, major depressive disorder with prior suicidal ideation or suicide attempts, or major depressive disorder alone

BACKGROUND

The impact of treatment-resistant depression (TRD) or prior suicidal ideation/suicide attempt (SI/SA) on mortality by suicide among patients with major depressive disorder (MDD) is not well known. This retrospective, observational, descriptive cohort study characterized real-world rates of suicide-specific mortality among patients with MDD with or without TRD or SI/SA.

METHODS

Adult patients with MDD among commercially insured and Medicare enrollees in Optum Research Database were included and assigned to three cohorts: those with treatment-resistant MDD (TRD), those with MDD and SI/SA (MDD+SI/SA), and those with MDD without TRD or SI/SA (MDD alone). Suicide-specific mortality was obtained from the National Death Index. The effects of demographic characteristics and SI/SA in the year prior to the end of observation on suicide-specific mortality were assessed.

RESULTS

For the 139,753 TRD, 85,602 MDD+SI/SA, and 572,098 MDD alone cohort patients, mean age ranged from 55 to 59 years and the majority were female. At baseline, anxiety disorders were present in 53.92%, 44.11%, and 21.72% of patients with TRD, MDD+SI/SA, and MDD alone, respectively. Suicide-mortality rates in the three cohorts were 0.14/100 person-years for TRD, 0.27/100 person-years for MDD+SI/SA, and 0.04/100 person-years for MDD alone. SI/SA during the year prior to the end of observation, younger age, and male sex were associated with increased suicide risk.

CONCLUSIONS

Patients with TRD and MDD+SI/SA have a heightened risk of mortality by suicide compared with patients with MDD alone. Suicide rates were higher in patients with recent history versus older or no history of SI/SA, men versus women, and those of young age versus older age.

Intentional Self-Harm Among US Veterans With Traumatic Brain Injury or Posttraumatic Stress Disorder: Retrospective Cohort Study From 2008 to 2017

BACKGROUND

Veterans with a history of traumatic brain injury (TBI) and/or posttraumatic stress disorder (PTSD) may be at increased risk of suicide attempts and other forms of intentional self-harm as compared to veterans without TBI or PTSD.

OBJECTIVE

Using administrative data from the US Veterans Health Administration (VHA), we studied associations between TBI and PTSD diagnoses, and subsequent diagnoses of intentional self-harm among US veterans who used VHA health care between 2008 and 2017.

METHODS

All veterans with encounters or hospitalizations for intentional self-harm were assigned "index dates" corresponding to the date of the first related visit; among those without intentional self-harm, we randomly selected a date from among the veteran's health care encounters to match the distribution of case index dates over the 10-year period. We then examined the prevalence of TBI and PTSD diagnoses within the 5-year period prior to veterans' index dates. TBI, PTSD, and intentional self-harm were identified using International Classification of Diseases diagnosis and external cause of injury codes from inpatient and outpatient VHA encounters. We stratified analyses by veterans' average yearly VHA utilization in the 5-year period before their index date (low, medium, or high). Variations in prevalence and odds of intentional self-harm diagnoses were compared by veterans' prior TBI and PTSD diagnosis status (TBI only, PTSD only, and comorbid TBI/PTSD) for each VHA utilization stratum. Multivariable models adjusted for age, sex, race, ethnicity, marital status, Department of Veterans Affairs service-connection status, and Charlson Comorbidity Index scores.

RESULTS

About 6.7 million veterans with at least two VHA visits in the 5-year period before their index dates were included in the analyses; 86,644 had at least one intentional self-harm diagnosis during the study period. During the periods prior to veterans' index dates, 93,866 were diagnosed with TBI only; 892,420 with PTSD only; and 102,549 with comorbid TBI/PTSD. Across all three VHA utilization strata, the prevalence of intentional self-harm diagnoses was higher among veterans diagnosed with TBI, PTSD, or TBI/PTSD than among veterans with neither diagnosis. The observed difference was most pronounced among veterans in the high VHA utilization stratum. The prevalence of intentional self-harm was six times higher among those with comorbid TBI/PTSD (6778/58,295, 11.63%) than among veterans with neither TBI nor PTSD (21,979/1,144,991, 1.92%). Adjusted odds ratios suggested that, after accounting for potential confounders, veterans with TBI, PTSD, or comorbid TBI/PTSD had higher odds of self-harm compared to veterans without these diagnoses. Among veterans with high VHA utilization, those with comorbid TBI/PTSD were 4.26 (95% CI 4.15-4.38) times more likely to receive diagnoses for intentional self-harm than veterans with neither diagnosis. This pattern was similar for veterans with low and medium VHA utilization.

CONCLUSIONS

Veterans with TBI and/or PTSD diagnoses, compared to those with neither diagnosis, were substantially more likely to be subsequently diagnosed with intentional self-harm between 2008 and 2017. These associations were most pronounced among veterans who used VHA health care most frequently. These findings suggest a need for suicide prevention efforts targeted at veterans with these diagnoses.

Cross-phenotype relationship between opioid use disorder and suicide attempts: new evidence from polygenic association and Mendelian randomization analyses

Clinical epidemiological studies have found high co-occurrence between suicide attempts (SA) and opioid use disorder (OUD). However, the patterns of correlation and causation between them are still not clear due to psychiatric confounding. To investigate their cross-phenotype relationship, we utilized raw phenotypes and genotypes from >150,000 UK Biobank samples, and genome-wide association summary statistics from >600,000 individuals with European ancestry. Pairwise association and a potential bidirectional relationship between OUD and SA were evaluated with and without controlling for major psychiatric disease status (e.g., schizophrenia, major depressive disorder, and alcohol use disorder). Multiple statistical and genetics tools were used to perform epidemiological association, genetic correlation, polygenic risk score prediction, and Mendelian randomizations (MR) analyses. Strong associations between OUD and SA were observed at both the phenotypic level (overall samples [OR = 2.94, P = 1.59 ×10-14]; non-psychiatric subgroup [OR = 2.15, P = 1.07 ×10-3]) and the genetic level (genetic correlation rg = 0.38 and 0.5 with or without conditioning on psychiatric traits, respectively). Consistently, increasing polygenic susceptibility to SA is associated with increasing risk of OUD (OR = 1.08, false discovery rate [FDR] =1.71 ×10-3), and similarly, increasing polygenic susceptibility to OUD is associated with increasing risk of SA (OR = 1.09, FDR = 1.73 ×10-6). However, these polygenic associations were much attenuated after controlling for comorbid psychiatric diseases. A combination of MR analyses suggested a possible causal association from genetic liability for SA to OUD risk (2-sample univariable MR: OR = 1.14, P = 0.001; multivariable MR: OR = 1.08, P = 0.001). This study provided new genetic evidence to explain the observed OUD-SA comorbidity. Future prevention strategies for each phenotype needs to take into consideration of screening for the other one.

Physical injuries as triggers for self-harm: a within-individual study of nearly 250 000 injured people with a major psychiatric disorder

BACKGROUND

Although there is robust evidence for several factors which may precipitate self-harm, the contributions of different physical injuries are largely unknown.

OBJECTIVE

To examine whether specific physical injuries are associated with risks of self-harm in people with psychiatric disorders.

METHODS

By using population and secondary care registers, we identified all people born in Finland (1955-2000) and Sweden (1948-1993) with schizophrenia-spectrum disorder (n=136 182), bipolar disorder (n=68 437) or depression (n=461 071). Falls, transport-related injury, traumatic brain injury and injury from interpersonal assault were identified within these subsamples. We used conditional logistic regression models adjusted for age and calendar month to compare self-harm risk in the week after each injury to earlier weekly control periods, which allowed us to account for unmeasured confounders, including genetics and early environments.

FINDINGS

A total of 249 210 individuals had been diagnosed with a psychiatric disorder and a physical injury during the follow-up. The absolute risk of self-harm after a physical injury ranged between transport-related injury and injury from interpersonal assault (averaging 17.4-37.0 events per 10 000 person-weeks). Risk of self-harm increased by a factor of two to three (adjusted OR: 2.0-2.9) in the week following a physical injury, as compared with earlier, unexposed periods for the same individuals.

CONCLUSIONS

Physical injuries are important proximal risk factors for self-harm in people with psychiatric disorders.

CLINICAL IMPLICATIONS

Mechanisms underlying the associations could provide treatment targets. When treating patients with psychiatric illnesses, emergency and trauma medical services should actively work in liaison with psychiatric services to implement self-harm prevention strategies.

Health Service Protection vis-à-vis the Detection of Psychosocial Risks of Suicide during the Years 2019-2021

Health services are especially relevant in suicide prevention and intervention, representing a favourable environment in which to implement specific strategies to detect and address suicidal behaviours. Indeed, a significant proportion of people who die by suicide (DBS) present at primary care and mental health services during the last year, month, or even days before committing suicide. The objective of this descriptive and cross-sectional study of all registered cases of death by suicide (N = 265) in Extremadura (Spain) was to determine which of those people who died by suicide had mental health problems (MHP) and what type of assistance they had requested. Diagnoses, previous suicide attempts, type of health service, and last visit before death were explored with univariate analyses and logistic regressions. The proportion of people without MHP was found to be high, and these people had hardly visited the health services at all in their last year. People with MHP, between the ages of 40 and 69, and with previous suicide attempts were more likely to have visited the mental health service in the three months prior to their death. It is, thus, necessary to provide health professionals with tools and training in the prevention of and approach to suicide. Efforts must be directed towards effectively assessing mental health and the risk of suicide since a large proportion of people who die by suicide may go unnoticed.

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.

An efficient landmark model for prediction of suicide attempts in multiple clinical settings

Growing evidence has shown that applying machine learning models to large clinical data sources may exceed clinician performance in suicide risk stratification. However, many existing prediction models either suffer from "temporal bias" (a bias that stems from using case-control sampling) or require training on all available patient visit data. Here, we adopt a "landmark model" framework that aligns with clinical practice for prediction of suicide-related behaviors (SRBs) using a large electronic health record database. Using the landmark approach, we developed models for SRB prediction (regularized Cox regression and random survival forest) that establish a time-point (e.g., clinical visit) from which predictions are made over user-specified prediction windows using historical information up to that point. We applied this approach to cohorts from three clinical settings: general outpatient, psychiatric emergency department, and psychiatric inpatients, for varying prediction windows and lengths of historical data. Models achieved high discriminative performance (area under the Receiver Operating Characteristic curve 0.74-0.93 for the Cox model) across different prediction windows and settings, even with relatively short periods of historical data. In short, we developed accurate, dynamic SRB risk prediction models with the landmark approach that reduce bias and enhance the reliability and portability of suicide risk prediction models.