Predicting Sex-Specific Nonfatal Suicide Attempt Risk Using Machine Learning and Data From Danish National Registries.
Ontology highlight
ABSTRACT:
SUBMITTER: Gradus JL
PROVIDER: S-EPMC8796814 | biostudies-literature | 2021 Dec
REPOSITORIES: biostudies-literature
Publications
Predicting Sex-Specific Nonfatal Suicide Attempt Risk Using Machine Learning and Data From Danish National Registries.
Gradus Jaimie L JL Rosellini Anthony J AJ Horváth-Puhó Erzsébet E Jiang Tammy T Street Amy E AE Galatzer-Levy Isaac I Lash Timothy L TL Sørensen Henrik T HT
American journal of epidemiology 20211201 12
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 c ...[more]
Similar Datasets
Project description: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.
| S-EPMC7647056 | biostudies-literature
Project description:ImportanceBecause more than one-third of people making nonfatal suicide attempts do not receive mental health treatment, it is essential to extend suicide attempt risk factors beyond high-risk clinical populations to the general adult population.ObjectiveTo identify future suicide attempt risk factors in the general population using a data-driven machine learning approach including more than 2500 questions from a large, nationally representative survey of US adults.Design, setting, and participantsData came from wave 1 (2001 to 2002) and wave 2 (2004 to 2005) of the National Epidemiologic Survey on Alcohol and Related Conditions (NESARC). NESARC is a face-to-face longitudinal survey conducted with a national representative sample of noninstitutionalized civilian population 18 years and older in the US. The cumulative response rate across both waves was 70.2% resulting in 34 653 wave 2 interviews. A balanced random forest was trained using cross-validation to develop a suicide attempt risk model. Out-of-fold model prediction was used to assess model performance, including the area under the receiver operator curve, sensitivity, and specificity. Survey design and nonresponse weights allowed estimates to be representative of the US civilian population based on the 2000 census. Analyses were performed between May 15, 2019, and June 10, 2020.Main outcomes and measuresAttempted suicide in the 3 years between wave 1 and wave 2 interviews.ResultsOf 34 653 participants, 20 089 were female (weighted proportion, 52.1%). The weighted mean (SD) age was 45.1 (17.3) years at wave 1 and 48.2 (17.3) years at wave 2. Attempted suicide during the 3 years between wave 1 and wave 2 interviews was self-reported by 222 of 34 653 participants (0.6%). Using survey questions measured at wave 1, the suicide attempt risk model yielded a cross-validated area under the receiver operator characteristic curve of 0.857 with a sensitivity of 85.3% (95% CI, 79.8-89.7) and a specificity of 73.3% (95% CI, 72.8-73.8) at an optimized threshold. The model identified 1.8% of the US population to be at a 10% or greater risk of suicide attempt. The most important risk factors were 3 questions about previous suicidal ideation or behavior; 3 items from the 12-Item Short Form Health Survey, namely feeling downhearted, doing activities less carefully, or accomplishing less because of emotional problems; younger age; lower educational achievement; and recent financial crisis.Conclusions and relevanceIn this study, after searching through more than 2500 survey questions, several well-known risk factors of suicide attempt were confirmed, such as previous suicidal behaviors and ideation, and new risks were identified, including functional impairment resulting from mental disorders and socioeconomic disadvantage. These results may help guide future clinical assessment and the development of new suicide risk scales.
| S-EPMC7788508 | biostudies-literature
Project description:ImportanceAlthough longitudinal studies have reported associations between early life factors (ie, in-utero/perinatal/infancy) and long-term suicidal behavior, they have concentrated on 1 or few selected factors, and established associations, but did not investigate if early-life factors predict suicidal behavior.ObjectiveTo identify and evaluate the ability of early-life factors to predict suicide attempt in adolescents and young adults from the general population.Design, setting, and participantsThis prognostic study used data from the Québec Longitudinal Study of Child Development, a population-based longitudinal study from Québec province, Canada. Participants were followed-up from birth to age 20 years. Random forest classification algorithms were developed to predict suicide attempt. To avoid overfitting, prediction performance indices were assessed across 50 randomly split subsamples, and then the mean was calculated. Data were analyzed from November 2019 to June 2020.ExposuresFactors considered in the analysis included 150 variables, spanning virtually all early life domains, including pregnancy and birth information; child, parents, and neighborhood characteristics; parenting and family functioning; parents' mental health; and child temperament, as assessed by mothers, fathers, and hospital birth records.Main outcomes and measuresThe main outcome was self-reported suicide attempt by age 20 years.ResultsAmong 1623 included youths aged 20 years, 845 (52.1%) were female and 778 (47.9%) were male. Models show moderate prediction performance. The areas under the curve for the prediction of suicide attempt were 0.72 (95% CI, 0.71-0.73) for females and 0.62 (95% CI, 0.60-0.62) for males. The models showed low sensitivity (females, 0.50; males, 0.32), moderate positive predictive values (females, 0.60; males, 0.62), and good specificity (females, 0.76; males, 0.82) and negative predicted values (females, 0.75; males, 0.71). The most important factors contributing to the prediction included socioeconomic and demographic characteristics of the family (eg, mother and father education and age, socioeconomic status, neighborhood characteristics), parents' psychological state (specifically parents' antisocial behaviors) and parenting practices. Birth-related variables also contributed to the prediction of suicidal behavior (eg, prematurity). Sex differences were also identified, with family-related socioeconomic and demographic characteristics being the top factors for females and parents' antisocial behavior being the top factor for males.Conclusions and relevanceThese findings suggest that early life factors contributed modestly to the prediction of suicidal behavior in adolescence and young adulthood. Although these factors may inform the understanding of the etiological processes of suicide, their utility in the long-term prediction of suicide attempt was limited.
| S-EPMC7955274 | biostudies-literature
Project description:BackgroundSuicidal ideation due to abortion has been used to justify restrictive US abortion policies. Much research examining abortion and mental health has relied on self-report, has had low participation rates, and did not consider confounding factors. In the present study, we used data that do not rely on self-report and are not affected by low participation rates to examine the association between abortion and non-fatal suicide attempts, adjusting for confounding factors.MethodsIn this longitudinal cohort study of Danish population registries, we linked data on a cohort of women born in Denmark between Jan 1, 1980, and Dec 30, 1998, who did not die or emigrate from Denmark before their 18th birthday or before study entry. Follow-up started on the woman's 18th birthday or Jan 1, 2000, whichever came last. Follow-up ended at the date of first suicide attempt, date of emigration from Denmark, date of death, or Dec 31, 2016, whichever came first. Women were between the ages of 18 and 36 years during the study period. We used a survival analysis to examine the risk of first suicide attempts or self-harm associated with a first abortion compared with no abortion, in the complete study cohort. To examine incidence rate ratios (IRRs) associated with abortion, we used Poisson regression with the logarithm of woman-years at risk as an offset. We also examined whether the risk of suicide attempts changed before and after the abortion, adjusting for age, calendar year, socioeconomic status, and history of childbirth, mental health, parental mental health, and physical health.FindingsData on 523 280 women were included in this study. Of these, 48 990 (9·4%) women had a record of at least one first-trimester abortion, and 10 216 (2·0%) had a suicide attempt during the study period. Among 48 990 women who had an abortion, 1402 (2·9%) had a first suicide attempt after the first abortion. In our fully-adjusted model which adjusted for all covariates, the risk of first-time non-fatal suicide attempts was similar in the year before an abortion (IRR 2·46 [95% CI 2·22-2·72]) and the year after an abortion (IRR 2·54 [2·29-2·81], p=0·509) compared with women who had not had an abortion, and decreased with increasing time since the abortion (1-5 years IRR 1·90 [1·75-2·06]; ≥5 years IRR 1·73 [1·53-1·96]).InterpretationWe found that women who had abortions had a higher risk of non-fatal suicide attempts compared with women who did not have an abortion. However, because the increased risk was the same both the year before and after the abortion, it is not attributable to the abortion. Thus, policies based on the notion that abortion increases women's risk of suicide attempts are misinformed.FundingSociety of Family Planning, American Foundation for Suicide Prevention, and The Lundbeck Foundation Initiative for Integrative Psychiatric Research.
| S-EPMC7437954 | biostudies-literature
Project description:BackgroundHow does genetic liability to suicide attempt (SA), suicide death (SD), major depression (MD), bipolar disorder (BD), schizophrenia (SZ), alcohol use disorder (AUD), and drug use disorder (DUD) impact on risk for SA and SD?MethodsIn the Swedish general population born 1932-1995 and followed through 2017 (n = 7 661 519), we calculate family genetic risk scores (FGRS) for SA, SD, MD, BD, SZ, AUD, and DUD. Registration for SA and SD was assessed from Swedish national registers.ResultsIn univariate and multivariate models predicting SA, FGRS were highest for SA, AUD, DUD, and MD. In univariate models predicting SD, the strongest FGRS were AUD, DUD, SA, and SD. In multivariate models, the FGRS for SA and AUD were higher in predicting SA while the FGRS for SD, BD, and SZ were higher in predicting SD. Higher FGRS for all disorders significantly predicted both younger age at first SA and frequency of attempts. For SD, higher FGRS for MD, AUD, and SD predicted later age at SD. Mediation of FGRS effects on SA and SD was more pronounced for SD than SA, strongest for AUD, DUD, and SZ FGRS and weakest for MD.ConclusionsFGRS for both SA and SD and for our five psychiatric disorders impact on risk for SA and SD in a complex manner. While some of the impact of genetic risk factors for psychiatric disorders on risk for SA and SD is mediated through developing the disorders, these risks also predispose directly to suicidal behaviors.
| S-EPMC10916711 | biostudies-literature
Project description:BackgroundSuicide prevention is a public health priority, but risk factors for suicide after medical hospitalization remain understudied. This problem is critical for women, for whom suicide rates in the United States are disproportionately increasing.ObjectiveTo differentiate the risk of suicide attempt and self-harm following general medical hospitalization among women with depression, bipolar disorder, and chronic psychosis.MethodsWe developed a machine learning algorithm that identified risk factors of suicide attempt and self-harm after general hospitalization using electronic health record data from 1628 women in the University of California Los Angeles Integrated Clinical and Research Data Repository. To assess replicability, we applied the algorithm to a larger sample of 140,848 women in the New York City Clinical Data Research Network.ResultsThe classification tree algorithm identified risk groups in University of California Los Angeles Integrated Clinical and Research Data Repository (area under the curve 0.73, sensitivity 73.4, specificity 84.1, accuracy 0.84), and predictor combinations characterizing key risk groups were replicated in New York City Clinical Data Research Network (area under the curve 0.71, sensitivity 83.3, specificity 82.2, and accuracy 0.84). Predictors included medical comorbidity, history of pregnancy-related mental illness, age, and history of suicide-related behavior. Women with antecedent medical illness and history of pregnancy-related mental illness were at high risk (6.9%-17.2% readmitted for suicide-related behavior), as were women below 55 years old without antecedent medical illness (4.0%-7.5% readmitted).ConclusionsPrevention of suicide attempt and self-harm among women following acute medical illness may be improved by screening for sex-specific predictors including perinatal mental health history.
| S-EPMC7810157 | biostudies-literature
Project description:BackgroundAlthough machine learning (ML) algorithms have been applied to point-of-care sepsis prognostication, ML has not been used to predict sepsis mortality in an administrative database. Therefore, we examined the performance of common ML algorithms in predicting sepsis mortality in adult patients with sepsis and compared it with that of the conventional context knowledge-based logistic regression approach.ObjectiveThe aim of this study is to examine the performance of common ML algorithms in predicting sepsis mortality in adult patients with sepsis and compare it with that of the conventional context knowledge-based logistic regression approach.MethodsWe examined inpatient admissions for sepsis in the US National Inpatient Sample using hospitalizations in 2010-2013 as the training data set. We developed four ML models to predict in-hospital mortality: logistic regression with least absolute shrinkage and selection operator regularization, random forest, gradient-boosted decision tree, and deep neural network. To estimate their performance, we compared our models with the Super Learner model. Using hospitalizations in 2014 as the testing data set, we examined the models' area under the receiver operating characteristic curve (AUC), confusion matrix results, and net reclassification improvement.ResultsHospitalizations of 923,759 adults were included in the analysis. Compared with the reference logistic regression (AUC: 0.786, 95% CI 0.783-0.788), all ML models showed superior discriminative ability (P<.001), including logistic regression with least absolute shrinkage and selection operator regularization (AUC: 0.878, 95% CI 0.876-0.879), random forest (AUC: 0.878, 95% CI 0.877-0.880), xgboost (AUC: 0.888, 95% CI 0.886-0.889), and neural network (AUC: 0.893, 95% CI 0.891-0.895). All 4 ML models showed higher sensitivity, specificity, positive predictive value, and negative predictive value compared with the reference logistic regression model (P<.001). We obtained similar results from the Super Learner model (AUC: 0.883, 95% CI 0.881-0.885).ConclusionsML approaches can improve sensitivity, specificity, positive predictive value, negative predictive value, discrimination, and calibration in predicting in-hospital mortality in patients hospitalized with sepsis in the United States. These models need further validation and could be applied to develop more accurate models to compare risk-standardized mortality rates across hospitals and geographic regions, paving the way for research and policy initiatives studying disparities in sepsis care.
| S-EPMC9047761 | biostudies-literature
Project description:Prior studies have suggested that physical trauma might be associated with the development of amyotrophic lateral sclerosis (ALS). We conducted a population-based, individually matched case-control study in Denmark to assess whether hospitalization for trauma is associated with a higher risk of developing ALS. There were 3,650 incident cases of ALS in the Danish National Patient Register from 1982 to 2009. We used risk-set sampling to match each case to 100 age- and sex-matched population controls alive on the date of the case's diagnosis. Odds ratios and 95% confidence intervals were calculated using a conditional logistic regression model. History of trauma diagnosis was also obtained from the Danish Patient Register. When traumas in the 5 years prior to the index date were excluded, there was a borderline association between any trauma and ALS (odds ratio (OR) = 1.09, 95% confidence interval (CI): 0.99, 1.19). A first trauma before age 55 years was associated with ALS (OR = 1.22, 95% CI: 1.08, 1.37), whereas first traumas at older ages were not (OR = 0.97, 95% CI: 0.85, 1.10). Our data suggest that physical trauma at earlier ages is associated with ALS risk. Age at first trauma could help explain discrepancies in results of past studies of trauma and ALS.
| S-EPMC4753279 | biostudies-literature
Project description:BackgroundThe ability to accurately predict survival in older adults is crucial as it guides clinical decision making. The added value of using health care usage for predicting mortality remains unexplored. The aim of this study was to investigate if temporal patterns of healthcare expenditures, can improve the predictive performance for mortality, in spousal bereaved older adults, next to other widely used sociodemographic variables.MethodsThis is a population-based cohort study of 48,944 Danish citizens 65 years of age and older suffering bereavement within 2013-2016. Individuals were followed from date of spousal loss until death from all causes or 31st of December 2016, whichever came first. Healthcare expenditures were available on weekly basis for each person during the follow-up and used as predictors for mortality risk in Extreme Gradient Boosting models. The extent to which medical spending trajectories improved mortality predictions compared to models with sociodemographics, was assessed with respect to discrimination (AUC), overall prediction error (Brier score), calibration, and clinical benefit (decision curve analysis).ResultsThe AUC of age and sex for mortality the year after spousal loss was 70.8% [95% CI 68.8, 72.8]. The addition of sociodemographic variables led to an increase of AUC ranging from 0.9% to 3.1% but did not significantly reduce the overall prediction error. The AUC of the model combining the variables above plus medical spending usage was 80.8% [79.3, 82.4] also exhibiting smaller Brier score and better calibration. Overall, patterns of healthcare expenditures improved mortality predictions the most, also exhibiting the highest clinical benefit among the rest of the models.ConclusionTemporal patterns of medical spending have the potential to significantly improve our assessment on who is at high risk of dying after suffering spousal loss. The proposed methodology can assist in a more efficient risk profiling and prognosis of bereaved individuals.
| S-EPMC10406307 | biostudies-literature
Project description:ObjectiveSeveral prognostic models of suicide risk have been published; however, few have been implemented in Japan using longitudinal cohort data. The aim of this study was to identify suicide risk factors for suicidal ideation in the Japanese population and to develop a machine-learning model to predict suicide risk in Japan.Materials and methodsData was obtained from Wave1 Time 1 (November 2016) and Time 2 (March 2017) of the National Survey for Stress and Health in Japan, were incorporated into a suicide risk prediction machine-learning model, trained using 65 items related to trauma and stress. The study included 3,090 and 2,163 survey respondents >18 years old at Time 1 and Time 2, respectively. The mean (standard deviation, SD) age was 44.9 (10.9) years at Time 1 and 46.0 (10.7) years at Time 2. We analyzed the participants with increased suicide risk at Time 2 survey. Model performance, including the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, were also analyzed.ResultsThe model showed a good performance (AUC = 0.830, 95% confidence interval = 0.795-0.866). Overall, the model achieved an accuracy of 78.8%, sensitivity of 75.4%, specificity of 80.4%, positive predictive value of 63.4%, and negative predictive value of 87.9%. The most important risk factor for suicide risk was the participants' Suicidal Ideation Attributes Scale score, followed by the Sheehan Disability Scale score, Patient Health Questionnaire-9 scores, Cross-Cutting Symptom Measure (CCSM-suicidal ideation domain, Dissociation Experience Scale score, history of self-harm, Generalized Anxiety Disorder-7 score, Post-Traumatic Stress Disorder check list-5 score, CCSM-dissociation domain, and Impact of Event Scale-Revised scores at Time 1.ConclusionsThis prognostic study suggests the ability to identify patients at a high risk of suicide using an online survey method. In addition to confirming several well-known risk factors of suicide, new risk measures related to trauma and trauma-related experiences were also identified, which may help guide future clinical assessments and early intervention approaches.
| S-EPMC9387201 | biostudies-literature