Dataset Information

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

ABSTRACT: OBJECTIVE:The authors sought to develop and validate models using electronic health records to predict suicide attempt and suicide death following an outpatient visit. METHOD:Across seven health systems, 2,960,929 patients age 13 or older (mean age, 46 years; 62% female) made 10,275,853 specialty mental health visits and 9,685,206 primary care visits with mental health diagnoses between Jan. 1, 2009, and June 30, 2015. Health system records and state death certificate data identified suicide attempts (N=24,133) and suicide deaths (N=1,240) over 90 days following each visit. Potential predictors included 313 demographic and clinical characteristics extracted from records for up to 5 years before each visit: prior suicide attempts, mental health and substance use diagnoses, medical diagnoses, psychiatric medications dispensed, inpatient or emergency department care, and routinely administered depression questionnaires. Logistic regression models predicting suicide attempt and death were developed using penalized LASSO (least absolute shrinkage and selection operator) variable selection in a random sample of 65% of the visits and validated in the remaining 35%. RESULTS:Mental health specialty visits with risk scores in the top 5% accounted for 43% of subsequent suicide attempts and 48% of suicide deaths. Of patients scoring in the top 5%, 5.4% attempted suicide and 0.26% died by suicide within 90 days. C-statistics (equivalent to area under the curve) for prediction of suicide attempt and suicide death were 0.851 (95% CI=0.848, 0.853) and 0.861 (95% CI=0.848, 0.875), respectively. Primary care visits with scores in the top 5% accounted for 48% of subsequent suicide attempts and 43% of suicide deaths. C-statistics for prediction of suicide attempt and suicide death were 0.853 (95% CI=0.849, 0.857) and 0.833 (95% CI=0.813, 0.853), respectively. CONCLUSIONS:Prediction models incorporating both health record data and responses to self-report questionnaires substantially outperform existing suicide risk prediction tools.

SUBMITTER: Simon GE

PROVIDER: S-EPMC6167136 | biostudies-literature | 2018 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Simon Gregory E GE Johnson Eric E Lawrence Jean M JM Rossom Rebecca C RC Ahmedani Brian B Lynch Frances L FL Beck Arne A Waitzfelder Beth B Ziebell Rebecca R Penfold Robert B RB Shortreed Susan M SM

The American journal of psychiatry 20180524 10

<h4>Objective</h4>The authors sought to develop and validate models using electronic health records to predict suicide attempt and suicide death following an outpatient visit.<h4>Method</h4>Across seven health systems, 2,960,929 patients age 13 or older (mean age, 46 years; 62% female) made 10,275,853 specialty mental health visits and 9,685,206 primary care visits with mental health diagnoses between Jan. 1, 2009, and June 30, 2015. Health system records and state death certificate data identif ...[more]

PMID: 29792051

Similar Datasets

Project description:ObjectivePatients with fibromyalgia (FM) are 10 times more likely to die by suicide than the general population. The purpose of this study was to externally validate published models predicting suicidal ideation and suicide attempts in patients with FM and to identify interpretable risk and protective factors for suicidality unique to FM.MethodsThis was a case-control study of large-scale electronic health record data collected from 1998 to 2017, identifying FM cases with validated Phenotype KnowledgeBase criteria. Model performance was measured through discrimination, including the receiver operating area under the curve (AUC), sensitivity, and specificity, and through calibration, including calibration plots. Risk factors were selected by L1 penalized regression with bootstrapping for both outcomes. Secondary utilization analyses converted time-based billing codes to equivalent minutes to estimate face-to-face provider contact.ResultsWe identified 8,879 patients with FM, with 34 known suicide attempts and 96 documented cases of suicidal ideation. External validity was good for both suicidal ideation (AUC 0.80) and attempts (AUC 0.82) with excellent calibration. Risk factors specific to suicidal ideation included polysomatic symptoms such as fatigue (odds ratio [OR] 1.29 [95% confidence interval (95% CI) 1.25-1.32]), dizziness (OR 1.25 [95% CI 1.22-1.28]), and weakness (OR 1.17 [95% CI 1.15-1.19]). Risk factors specific to suicide attempt included obesity (OR 1.18 [95% CI 1.10-1.27]) and drug dependence (OR 1.15 [95% CI 1.12-1.18]). Per utilization analyses, those patients with FM and no suicidal ideation spent 3.5 times more time in follow-up annually, and those without documented suicide attempts spent more than 40 times more time face-to-face with providers annually.ConclusionThis is the first study to successfully apply machine learning to reliably detect suicidality in patients with FM, identifying novel risk factors for suicidality and highlighting outpatient engagement as a protective factor against suicide.

Project description:ObjectiveTo analyze the number and characteristics of suicide attempts by reviewing records of the public emergency healthcare service information system.MethodA retrospective observational study was conducted of emergency telephone calls received between January 1 2007 and December 31 2013 throughout the Andalusia region (Southern Spain). Cases were selected based on phone operator or healthcare team labeling. Data were analyzed on the characteristics of the individuals, the timing and severity of attempts, their prioritization, and their outcome.ResultsBetween January 1 2007 and December 31 2013, 20.942 calls related to suicide attempts were recorded, a rate of 34.7 attempts per 100,000 inhabitants. Most cases were classified by the public emergency healthcare service (Empresa Pública de Emergencias Sanitarias, EPES) as code X84 (The International Statistical Classification of Diseases, tenth revision, ICD-10) or 305(The International Statistical Classification of Diseases, ninth revision, ICD-9). Attempts were more frequent in the 35-49-year age group and there were similar proportions of males and females. The lowest number of calls for suicide attempts were in 2007 and the highest in 2013. Calls were more frequent during the summer months, at weekends, and between 16:00 and 23:00 h. The likelihood of evacuation to the hospital emergency department was almost two-fold lower in over 65-yr-olds than in younger individuals. Significant (ƿ = 0.001) gender differences were found in call outcome and prioritization. The most influential factor for evacuation to a hospital emergency department was the code assigned by the attending healthcare team.ConclusionsInformation obtained from extra-hospital emergency services provides valuable data on the characteristics and timing of calls related to suicide attempts, complementing information from hospital emergency departments or population surveys. There is a need to standardize the definition and recording of a suicide attempt.

Project description:The US federal government is spending billions of dollars in physician incentives to encourage the meaningful use of electronic health records (EHRs). Although the use of EHRs has potential to improve patient health outcomes, the existing evidence has been limited and inconsistent.To examine the association between implementing a commercially available outpatient EHR and emergency department (ED) visits, hospitalizations, and office visits for patients with diabetes mellitus.Staggered EHR implementation across outpatient clinics in an integrated delivery system (Kaiser Permanente Northern California) between 2005 and 2008 created an opportunity for studying changes associated with EHR use. Among a population-based sample of 169,711 patients with diabetes between 2004 and 2009, we analyzed 4,997,585 person-months before EHR implementation and 4,648,572 person-months after an EHR was being used by patients' physicians.We examined the association between EHR use and unfavorable clinical events (ED visits and hospitalizations) and office visit use among patients with diabetes, using multivariable regression with patient-level fixed-effect analyses and adjustment for trends over time.In multivariable analyses, use of the EHR was associated with a statistically significantly decreased number of ED visits, 28.80 fewer visits per 1000 patients annually (95% CI, 20.28 to 37.32), from a mean of 519.12 visits per 1000 patients annually without using the EHR to 490.32 per 1000 patients when using the EHR. The EHR was also associated with 13.10 fewer hospitalizations per 1000 patients annually (95% CI, 7.37 to 18.82), from a mean of 251.60 hospitalizations per 1000 patients annually with no EHR to 238.50 per 1000 patients annually when using the EHR. There were similar statistically significant reductions in nonelective hospitalizations (10.92 fewer per 1000 patients annually) and hospitalizations for ambulatory care-sensitive conditions (7.08 fewer per 1000 patients annually). There was no statistically significant association between EHR use and office visit rates.Among patients with diabetes, use of an outpatient EHR in an integrated delivery system was associated with modest reductions in ED visits and hospitalizations but not office visit rates. Further studies are needed to quantify the association of EHR use with changes in costs.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure