Prediction of Sex-Specific Suicide Risk Using Machine Learning and Single-Payer Health Care Registry Data From Denmark

Gradus, Jaimie L.; Rosellini, Anthony J.; Horváth‐Puhó, Erzsébet; Street, Amy E.; Galatzer‐Levy, Isaac R.; Jiang, Tammy; Lash, Timothy L.; Sørensen, Henrik Toft

doi:10.1001/jamapsychiatry.2019.2905

Cited by 107 publications

(118 citation statements)

References 61 publications

(117 reference statements)

Supporting

Mentioning

113

Contrasting

Unclassified

Order By: Relevance

“…60,61 Still other machine-learning studies developed a large number of synthetic or compound potential suicide risk factors (for example alcohol use by various age and gender groups) increasing the risk of chance associations. 46,97 We conclude that the case for machine learning as a statistically superior method of suicide prediction model is not yet conclusive.…”

Section: Discussionmentioning

confidence: 89%

Meta-analysis of the strength of exploratory suicide prediction models; from clinicians to computers

et al. 2021

View full text Add to dashboard Cite

Background Suicide prediction models have been formulated in a variety of ways and are heterogeneous in the strength of their predictions. Machine learning has been a proposed as a way of improving suicide predictions by incorporating more suicide risk factors. Aims To determine whether machine learning and the number of suicide risk factors included in suicide prediction models are associated with the strength of the resulting predictions. Method Random-effect meta-analysis of exploratory suicide prediction models constructed by combining two or more suicide risk factors or using clinical judgement (Prospero Registration CRD42017059665). Studies were located by searching for papers indexed in PubMed before 15 August 2020 with the term suicid* in the title. Results In total, 86 papers reported 102 suicide prediction models and included 20 210 411 people and 106 902 suicides. The pooled odds ratio was 7.7 (95% CI 6.7–8.8) with high between-study heterogeneity (I2 = 99.5). Machine learning was associated with a non-significantly higher odds ratio of 11.6 (95% CI 6.0–22.3) and clinical judgement with a non-significantly lower odds ratio of 4.7 (95% CI 2.1–10.9). Models including a larger number of suicide risk factors had a higher odds ratio when machine-learning studies were included (P = 0.02). Among non-machine-learning studies, suicide prediction models including fewer risk factors performed just as well as those including more risk factors. Conclusions Machine learning might have the potential to improve the performance of suicide prediction models by increasing the number of included suicide risk factors but its superiority over other methods is unproven.

show abstract

Section: Discussionmentioning

confidence: 89%

Meta-analysis of the strength of exploratory suicide prediction models; from clinicians to computers

et al. 2021

View full text Add to dashboard Cite

show abstract

“…These results call for more research in the timing of diagnoses of psychiatric disorders and the use of psychotropic medications in relation to suicidal behavior. Using the Danish registry data, a recent study predicting sex-specific suicide risk reported that diagnoses occurring long (e.g., 48 months) before suicide were more important for suicide prediction than diagnoses occurring shortly (e.g., 6 months) before suicide [ 41 ]. Since the authors defined the predictors using time of suicide, which could not be known beforehand, the models would not be implementable in clinical systems.…”

Section: Discussionmentioning

confidence: 99%

Predicting suicide attempt or suicide death following a visit to psychiatric specialty care: A machine learning study using Swedish national registry data

et al. 2020

View full text Add to dashboard Cite

Background Suicide is a major public health concern globally. Accurately predicting suicidal behavior remains challenging. This study aimed to use machine learning approaches to examine the potential of the Swedish national registry data for prediction of suicidal behavior. Methods and findings The study sample consisted of 541,300 inpatient and outpatient visits by 126,205 Sweden-born patients (54% female and 46% male) aged 18 to 39 (mean age at the visit: 27.3) years to psychiatric specialty care in Sweden between January 1, 2011 and December 31, 2012. The most common psychiatric diagnoses at the visit were anxiety disorders (20.0%), major depressive disorder (16.9%), and substance use disorders (13.6%). A total of 425 candidate predictors covering demographic characteristics, socioeconomic status (SES), electronic medical records, criminality, as well as family history of disease and crime were extracted from the Swedish registry data. The sample was randomly split into an 80% training set containing 433,024 visits and a 20% test set containing 108,276 visits. Models were trained separately for suicide attempt/death within 90 and 30 days following a visit using multiple machine learning algorithms. Model discrimination and calibration were both evaluated. Among all eligible visits, 3.5% (18,682) were followed by a suicide attempt/death within 90 days and 1.7% (9,099) within 30 days. The final models were based on ensemble learning that combined predictions from elastic net penalized logistic regression, random forest, gradient boosting, and a neural network. The area under the receiver operating characteristic (ROC) curves (AUCs) on the test set were 0.88 (95% confidence interval [CI] = 0.87–0.89) and 0.89 (95% CI = 0.88–0.90) for the outcome within 90 days and 30 days, respectively, both being significantly better than chance (i.e., AUC = 0.50) (p < 0.01). Sensitivity, specificity, and predictive values were reported at different risk thresholds. A limitation of our study is that our models have not yet been externally validated, and thus, the generalizability of the models to other populations remains unknown. Conclusions By combining the ensemble method of multiple machine learning algorithms and high-quality data solely from the Swedish registers, we developed prognostic models to predict short-term suicide attempt/death with good discrimination and calibration. Whether novel predictors can improve predictive performance requires further investigation.

show abstract

“…Previous studies have shown that 47% of crack-cocaine users had a current suicide risk [14], and a prevalence of suicidal behaviors of 30% in crack-cocaine addicts, in Brazil. The subject of suicide has been the focus of studies in psychiatry in the last decades, but the understanding about this behavior remains insufficient [15]. Moreover, the predictive factors in this vulnerable population were not well explored yet.…”

Section: Introductionmentioning

confidence: 99%

Prediction of attempted suicide in men and women with crack-cocaine use disorder in Brazil

et al. 2020

View full text Add to dashboard Cite

Background Suicide is a severe health problem, with high rates in individuals with addiction. Considering the lack of studies exploring suicide predictors in this population, we aimed to investigate factors associated with attempted suicide in inpatients diagnosed with cocaine use disorder using two analytical approaches. Methods This is a cross-sectional study using a secondary database with 247 men and 442 women hospitalized for cocaine use disorder. Clinical assessment included the Addiction Severity Index, the Childhood Trauma Questionnaire, and the Structured Clinical Interview for the Diagnostic and Statistical Manual of Mental Disorders, totalling 58 variables. Descriptive Poisson regression and predictive Random Forest algorithm were used complementarily to estimate prevalence ratios and to build prediction models, respectively. All analyses were stratified by gender. Results The prevalence of attempted suicide was 34% for men and 50% for women. In both genders, depression (PR M = 1.56, PR W = 1.27) and hallucinations (PR M = 1.80, PR W = 1.39) were factors associated with attempted suicide. Other specific factors were found for men and women, such as childhood trauma, aggression, and drug use severity. The men's predictive model had prediction statistics of AUC = 0.68, Acc. = 0.66, Sens. = 0.82, Spec. = 0.50, PPV = 0.47 and NPV = 0.84. This model identified several variables as important

show abstract

Prediction of Sex-Specific Suicide Risk Using Machine Learning and Single-Payer Health Care Registry Data From Denmark

Cited by 107 publications

References 61 publications

Meta-analysis of the strength of exploratory suicide prediction models; from clinicians to computers

Meta-analysis of the strength of exploratory suicide prediction models; from clinicians to computers

Predicting suicide attempt or suicide death following a visit to psychiatric specialty care: A machine learning study using Swedish national registry data

Prediction of attempted suicide in men and women with crack-cocaine use disorder in Brazil

Contact Info

Product

Resources

About