Search

Suicide attempts are a leading cause of injury globally. Accurate prediction of suicide attempts might offer opportunities for prevention. This case-cohort study used machine learning to examine sex-specific risk profiles for suicide attempts in Danish nationwide registry data. Cases were all persons who made a nonfatal suicide attempt between 1995 and 2015 (n = 22,974); the subcohort was a 5% random sample of the population at risk on January 1, 1995 (n = 265,183). We developed sex-stratified classification trees and random forests using 1,458 predictors, including demographic factors, family histories, psychiatric and physical health diagnoses, surgery, and prescribed medications. We found that substance use disorders/treatment, prescribed psychiatric medications, previous poisoning diagnoses, and stress disorders were important factors for predicting suicide attempts among men and women. Individuals in the top 5% of predicted risk accounted for 44.7% of all suicide attempts among men and 43.2% of all attempts among women. Our findings illuminate novel risk factors and interactions that are most predictive of nonfatal suicide attempts, while consistency between our findings and previous work in this area adds to the call to move machine learning suicide research toward the examination of high-risk subpopulations., (© The Author(s) 2021. Published by Oxford University Press on behalf of the Johns Hopkins Bloomberg School of Public Health. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

Machine learning is increasingly used in mental health research and has the potential to advance our understanding of how to characterize, predict, and treat mental disorders and associated adverse health outcomes (e.g., suicidal behavior). Machine learning offers new tools to overcome challenges for which traditional statistical methods are not well-suited. This paper provides an overview of machine learning with a specific focus on supervised learning (i.e., methods that are designed to predict or classify an outcome of interest). Several common supervised learning methods are described, along with applied examples from the published literature. We also provide an overview of supervised learning model building, validation, and performance evaluation. Finally, challenges in creating robust and generalizable machine learning algorithms are discussed., (Copyright © 2020. Published by Elsevier Ltd.)

Importance: Suicide is a public health problem, with multiple causes that are poorly understood. The increased focus on combining health care data with machine-learning approaches in psychiatry may help advance the understanding of suicide risk., Objective: To examine sex-specific risk profiles for death from suicide using machine-learning methods and data from the population of Denmark., Design, Setting, and Participants: A case-cohort study nested within 8 national Danish health and social registries was conducted from January 1, 1995, through December 31, 2015. The source population was all persons born or residing in Denmark as of January 1, 1995. Data were analyzed from November 5, 2018, through May 13, 2019., Exposures: Exposures included 1339 variables spanning domains of suicide risk factors., Main Outcomes and Measures: Death from suicide from the Danish cause of death registry., Results: A total of 14 103 individuals died by suicide between 1995 and 2015 (10 152 men [72.0%]; mean [SD] age, 43.5 [18.8] years and 3951 women [28.0%]; age, 47.6 [18.8] years). The comparison subcohort was a 5% random sample (n = 265 183) of living individuals in Denmark on January 1, 1995 (130 591 men [49.2%]; age, 37.4 [21.8] years and 134 592 women [50.8%]; age, 39.9 [23.4] years). With use of classification trees and random forests, sex-specific differences were noted in risk for suicide, with physical health more important to men's suicide risk than women's suicide risk. Psychiatric disorders and possibly associated medications were important to suicide risk, with specific results that may increase clarity in the literature. Generally, diagnoses and medications measured 48 months before suicide were more important indicators of suicide risk than when measured 6 months earlier. Individuals in the top 5% of predicted suicide risk appeared to account for 32.0% of all suicide cases in men and 53.4% of all cases in women., Conclusions and Relevance: Despite decades of research on suicide risk factors, understanding of suicide remains poor. In this study, the first to date to develop risk profiles for suicide based on data from a full population, apparent consistency with what is known about suicide risk was noted, as well as potentially important, understudied risk factors with evidence of unique suicide risk profiles among specific subpopulations.

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. [ABSTRACT FROM AUTHOR]

Structured diagnostic interviews involve significant respondent burden and clinician administration time. This study examined whether we can maintain diagnostic accuracy using fewer posttraumatic stress disorder (PTSD) assessment questions. Our study included 1,265 U.S. veterans of the Afghanistan and Iraq conflicts who were assessed for PTSD using the Structured Clinical Interview for the Diagnostic and Statistical Manual of Mental Disorders, fifth edition (SCID-5). We used random forests to assess the importance of each diagnostic item in predicting a SCID-5 PTSD diagnosis. We used variable importance to rank each item and removed the lowest ranking items while maintaining ≥90% accuracy (i.e., efficiency), sensitivity, and other metrics. We eliminated six diagnostic items among the overall sample, four items among male veterans, and six items among female veterans. Our findings demonstrate that we may shorten the SCID-5 PTSD module while maintaining excellent diagnostic performance. These findings have implications for potentially reducing patient and provider burden of PTSD diagnostic assessment. [ABSTRACT FROM AUTHOR]

Background and Aims: Persons with substance use disorders (SUDs) are at elevated risk of suicide death. We identified novel risk factors and interactions that predict suicide among men and women with SUD using machine learning. Design Case–cohort study. Setting: Denmark. Participants: The sample was restricted to persons with their first SUD diagnosis during 1995 to 2015. Cases were persons who died by suicide in Denmark during 1995 to 2015 (n = 2774) and the comparison subcohort was a 5% random sample of individuals in Denmark on 1 January 1995 (n = 13 179). Measurements Suicide death was recorded in the Danish Cause of Death Registry. Predictors included social and demographic information, mental and physical health diagnoses, surgeries, medications, and poisonings. Findings Persons among the highest risk for suicide, as identified by the classification trees, were men prescribed antidepressants in the 4 years before suicide and had a poisoning diagnosis in the 4 years before suicide; and women who were 30+ years old and had a poisoning diagnosis 4 years before and 12 months before suicide. Among men with SUD, the random forest identified five variables that were most important in predicting suicide; reaction to severe stress and adjustment disorders, drugs used to treat addictive disorders, age 30+ years, antidepressant use, and poisoning in the 4 prior years. Among women with SUD, the random forest found that the most important predictors of suicide were prior poisonings and reaction to severe stress and adjustment disorders. Individuals in the top 5% of predicted risk accounted for 15% of all suicide deaths among men and 24% of all suicides among women. Conclusions: In Denmark, prior poisoning and comorbid psychiatric disorders may be among the most important indicators of suicide risk among persons with substance use disorders, particularly among women. [ABSTRACT FROM AUTHOR]

Although variables are often measured with error, the impact of measurement error on machine-learning predictions is seldom quantified. The purpose of this study was to assess the impact of measurement error on the performance of random-forest models and variable importance. First, we assessed the impact of misclassification (i.e. measurement error of categorical variables) of predictors on random-forest model performance (e.g. accuracy, sensitivity) and variable importance (mean decrease in accuracy) using data from the National Comorbidity Survey Replication (2001–2003). Second, we created simulated data sets in which we knew the true model performance and variable importance measures and could verify that quantitative bias analysis was recovering the truth in misclassified versions of the data sets. Our findings showed that measurement error in the data used to construct random forests can distort model performance and variable importance measures and that bias analysis can recover the correct results. This study highlights the utility of applying quantitative bias analysis in machine learning to quantify the impact of measurement error on study results. [ABSTRACT FROM AUTHOR]

Background: Suicide risk is high in the 30 days after discharge from psychiatric hospital, but knowledge of the profiles of high-risk patients remains limited.Aims: To examine sex-specific risk profiles for suicide in the 30 days after discharge from psychiatric hospital, using machine learning and Danish registry data.Method: We conducted a case-cohort study capturing all suicide cases occurring in the 30 days after psychiatric hospital discharge in Denmark from 1 January 1995 to 31 December 2015 (n = 1205). The comparison subcohort was a 5% random sample of all persons born or residing in Denmark on 1 January 1995, and who had a first psychiatric hospital admission between 1995 and 2015 (n = 24 559). Predictors included diagnoses, surgeries, prescribed medications and demographic information. The outcome was suicide death recorded in the Danish Cause of Death Registry.Results: For men, prescriptions for anxiolytics and drugs used in addictive disorders interacted with other characteristics in the risk profiles (e.g. alcohol-related disorders, hypnotics and sedatives) that led to higher risk of postdischarge suicide. In women, there was interaction between recurrent major depression and other characteristics (e.g. poisoning, low income) that led to increased risk of suicide. Random forests identified important suicide predictors: alcohol-related disorders and nicotine dependence in men and poisoning in women.Conclusions: Our findings suggest that accurate prediction of suicide during the high-risk period immediately after psychiatric hospital discharge may require a complex evaluation of multiple factors for men and women. [ABSTRACT FROM AUTHOR]

Suicide rates among recent veterans have led to interest in risk identification. Evidence of gender-and trauma-specific predictors of suicidal ideation necessitates the use of advanced computational methods capable of elucidating these important and complex associations. In this study, we used machine learning to examine gender-specific associations between predeployment and military factors, traumatic deployment experiences, and psychopathology and suicidal ideation (SI) in a national sample of veterans deployed during the Iraq and Afghanistan conflicts (n = 2,244). Classification, regression tree analyses, and random forests were used to identify associations with SI and determine their classification accuracy. Findings converged on several associations for men that included depression, posttraumatic stress disorder (PTSD), and somatic complaints. Sexual harassment during deployment emerged as a key factor that interacted with PTSD and depression and demonstrated a stronger association with SI among women. Classification accuracy for SI presence or absence was good based on the receiver operating characteristic area under the curve, men = .91, women = .92. The risk for SI was classifiable with good accuracy, with associations that varied by gender. The use of machine learning analyses allowed for the discovery of rich, nuanced results that should be replicated in other samples and may eventually be a basis for the development of gender-specific actuarial tools to assess SI risk among veterans. [ABSTRACT FROM AUTHOR]

The article responds to comments on a 2021 study which show that psychiatric medications, and certain social variables and physical health diagnoses predict nonfatal suicide attempts. Topics covered include the balanced quality of the study's source population, the reasons for non-emphasis on positive predictive value (PPV) of risk classification, and the complex task of using machine learning methods in predicting suicidal behavior. Also noted is the need for wider studies on the subject.

Background: Risk for nonfatal suicide attempts is heightened in the month after psychiatric hospitalization discharge. Investigations of factors associated with such attempts are limited.Methods: We conducted a case-subcohort study using data from Danish medical, administrative, and social registries to develop sex-specific risk models using two machine learning methods: classification trees and random forests. Cases included individuals who received a diagnostic code for a nonfatal suicide attempt within 30 days of discharge following a psychiatric hospitalization between January 1, 1995 and December 31, 2015 (n = 3166, 56.5% female). The comparison subcohort consisted of a 5% random sample of individuals living in Denmark (n = 24,559, 51.3% female) on January 1, 1995 who had a psychiatric hospitalization during the study period.Results: Histories of self-poisoning, substance-related disorders, and eating disorders were important predictors of nonfatal suicide attempt among women, with notable interactions observed between age, self-poisoning history, and other characteristics (e.g., medication use). Self-poisoning, substance-related disorders, and severe stress reactions were among the most important variables for men, with key interactions noted between self-poisoning history, age, major depressive disorder diagnosis, and prescription classes.Limitations: Findings are based on Danish administrative data, which may be subject to inaccuracies, missingness, etc. It is unclear whether results would generalize to other populations.Conclusions: Markers of behavioral dysregulation were important predictors of nonfatal suicide attempts in the 30 days after psychiatric hospitalization discharge for both sexes. Examining risk markers for nonfatal suicide attempt following discharge is important to enhance support for this vulnerable population. [ABSTRACT FROM AUTHOR]

Accurate identification of persons at risk of suicide is challenging because suicide is a rare outcome with a multifactorial origin. The purpose of this study was to predict suicide among persons with depression using machine learning methods. A case-cohort study was conducted in Denmark between January 1, 1995 and December 31, 2015. Cases were all persons who died by suicide and had an incident depression diagnosis in Denmark (n = 2,774). The comparison subcohort was a 5% random sample of all individuals in Denmark at baseline, restricted to persons with an incident depression diagnosis during the study period (n = 11,963). Classification trees and random forests were used to predict suicide. In men with depression, there was a high risk of suicide among those who were prescribed other analgesics and antipyretics (i.e. , non-opioid analgesics such as acetaminophen), prescribed hypnotics and sedatives, and diagnosed with a poisoning (n = 96; risk = 81%). In women with depression, there was an elevated risk of suicide among those who were prescribed other analgesics and antipyretics, anxiolytics, and hypnotics and sedatives, but were not diagnosed with poisoning nor cerebrovascular diseases (n = 338; risk = 58%). Psychiatric disorders and their associated medications were strongly indicative of suicide risk. Notably, anti-inflammatory medications (e.g., acetaminophen) prescriptions, which are used to treat chronic pain and illnesses, were associated with suicide risk in persons with depression. Machine learning may advance our ability to predict suicide deaths. [ABSTRACT FROM AUTHOR]

Objective: Mental health problems (MHP) are a relatively common consequence of deployment to war zones. Early identification of those at risk of post-deployment MHP would improve prevention efforts. However, screening instruments based on linear models have not been successful. Machine learning (ML) has shown promise for providing the methodological frame for better prognostic models.Methods: The study population was all Danish military personnel deployed for the first time between January 1, 1992 and December 31, 2013. From extensive registry data, 21 pre- or at-deployment predictors comprising early adversity, social, clinical and demographic variables were used to predict psychiatric contacts (psychiatric diagnosis and/or use of psychotropic medicine) occurring within 6.5 years after homecoming. Four supervised ML methods (penalized logistic regression, random forests, support vector machines and gradient boosting machines) were compared in ability to classify those with high risk of post-deployment MHP and those without.Results: Of 27594 subjects, 2175 (8%) had a psychiatric contact. All four ML methods applied had performances well above chance (Area under the Receiver-operating Curve 0.62-0.68). Positive predictive value for the best model was 0.16. A range of pre-deployment factors were found to be predictive of post-deployment psychiatric contacts.Conclusions: ML methods can be useful in early identification of soldiers with high risk of MPH in the years following their first deployment. However, performances were modest and positive predictive values were low, limiting the applicability of the models for pre-deployment screening. Future studies should include neurobiological data and deployment experiences to increase accuracy of the models. [ABSTRACT FROM AUTHOR]

Cognitive Processing Therapy (CPT) is an effective treatment for posttraumatic stress disorder (PTSD); however, not every client achieves optimal outcomes. Data were pooled from four randomized trials in which female interpersonal trauma survivors completed CPT (N = 179). Random forests of classification trees were used to investigate the role of both baseline (e.g., demographics, trauma history, comorbid disorders) and session PTSD and depressive symptom scores on predicting trajectory and outcome. Of particular focus was whether those on track for poor outcome (e.g., non-response, partial treatment response) could be identified early in therapy. Results demonstrated inconsistent findings for discrimination between delayed responders (no early change but full response after 12 weeks of therapy) and those who either showed a partial response to treatment or did not respond at all; level of discrimination depended on the assessment point under study and the chosen comparison group. Those defined as clear and early responders , however, could be reliably differentiated from the other groups by session 4. Although it is possible to identify clients who will recover from PTSD by the middle of the CPT protocol, further work is needed to accurately identify those who will ultimately not recover from PTSD during a course of CPT. • Just over 50% of completers demonstrated early and sustained treatment response. • Early responders were differentiated from other groups by session 6. • Delayed versus poor response could not be reliably identified until after session 10. • Nonresponse to CPT cannot be identified in the early-to-middle stages of therapy. [ABSTRACT FROM AUTHOR]