Variation in patterns of health care before suicide: A population case-control study

Objective Limited research exists in predicting first-time suicide attempts that account for two-thirds of suicide decedents. We aimed to predict first-time suicide attempts using a large data-driven approach that applies natural language processing (NLP) and machine learning (ML) to unstructured (narrative) clinical notes and structured electronic health record (EHR) data. Methods This case-control study included patients aged 10–75 years who were seen between 2007 and 2016 from emergency departments and inpatient units. Cases were first-time suicide attempts from coded diagnosis; controls were randomly selected without suicide attempts regardless of demographics, following a ratio of nine controls per case. Four data-driven ML models were evaluated using 2-year historical EHR data prior to suicide attempt or control index visits, with prediction windows from 7 to 730 days. Patients without any historical notes were excluded. Model evaluation on accuracy and robustness was performed on a blind dataset (30% cohort). Results The study cohort included 45 238 patients (5099 cases, 40 139 controls) comprising 54 651 variables from 5.7 million structured records and 798 665 notes. Using both unstructured and structured data resulted in significantly greater accuracy compared to structured data alone (area-under-the-curve [AUC]: 0.932 vs. 0.901 P < .001). The best-predicting model utilized 1726 variables with AUC = 0.932 (95% CI, 0.922–0.941). The model was robust across multiple prediction windows and subgroups by demographics, points of historical most recent clinical contact, and depression diagnosis history. Conclusions Our large data-driven approach using both structured and unstructured EHR data demonstrated accurate and robust first-time suicide attempt prediction, and has the potential to be deployed across various populations and clinical settings.

show abstract

“…Moreover, the literature shows that patients seen in these two settings have an increased risk for suicide and suicidal behavior. 27 , 28…”

Section: Methodsmentioning

confidence: 99%

Natural language processing and machine learning of electronic health records for prediction of first-time suicide attempts

et al. 2021

View full text Add to dashboard Cite

show abstract

“…20 Regarding under-diagnosis and treatment from health professionals, evidence shows that a percentage of people who died by suicide had previously expressed death wishes, suicidal ideation or showed other alarm signs to health professionals. For example, Luoma and colleagues 21 concluded that 45% of the people who committed suicide had been in contact with primary healthcare providers within the month prior of the attempt. In general, people who died by suicide averaged 16.7 visits to healthcare during the latest year.…”

Section: Diagnosis and Treatment Of Depression And Suicidal Behaviormentioning

confidence: 99%

Collaborative care for depression and suicide prevention: a feasible intervention within the Mexican health system

Durand-Arias

Córdoba²,

Borges

et al. 2021

Salud Publica Mex

View full text Add to dashboard Cite

Mexico faces an enormous challenge in attending mental health disorders with depression rising as one of the five main contributors to disability adjusted life years (DALYs) and increasing suicide rates. These challenges are coupled with a dearth of resources and an inefficient allocation of the meager funds. While no magical bullet is available to ameliorate this situation in the short term, here we discuss current concepts and experiences that could be used in Mexico to deliver better primary mental health care. We focus on depression and suicidal behavior and argue that collaborative care is a feasible and replicable model, emphasizing the importance of training non-specialized primary care personnel to become case managers and provide primary mental health care. Mexico is currently undergoing a process of changes, including the emergence of universal health care. The time seems right to make mental health care more transversal, widely available and scientifically proven.

show abstract

“… 10 Furthermore, those at risk might not be identified despite health care encounters as recently as the day they die from suicide. 11 , 12 , 13 …”

Section: Introductionmentioning

confidence: 99%

Prospective Validation of an Electronic Health Record–Based, Real-Time Suicide Risk Model

et al. 2021

View full text Add to dashboard Cite

IMPORTANCE Numerous prognostic models of suicide risk have been published, but few have been implemented outside of integrated managed care systems. OBJECTIVE To evaluate performance of a suicide attempt risk prediction model implemented in a vendor-supplied electronic health record to predict subsequent (1) suicidal ideation and (2) suicide attempt. DESIGN, SETTING, AND PARTICIPANTS This observational cohort study evaluated implementation of a suicide attempt prediction model in live clinical systems without alerting. The cohort comprised patients seen for any reason in adult inpatient, emergency department, and ambulatory surgery settings at an academic medical center in the mid-South from June 2019 to April 2020. MAIN OUTCOMES AND MEASURES Primary measures assessed external, prospective, and concurrent validity. Manual medical record validation of coded suicide attempts confirmed incident behaviors with intent to die. Subgroup analyses were performed based on demographic characteristics, relevant clinical context/setting, and presence or absence of universal screening. Performance was evaluated using discrimination (number needed to screen, C statistics, positive/ negative predictive values) and calibration (Spiegelhalter z statistic). Recalibration was performed with logistic calibration. RESULTS The system generated 115 905 predictions for 77 973 patients (42 490 [54%] men, 35 404 [45%] women, 60 586 [78%] White, 12 620 [16%] Black). Numbers needed to screen in highest risk quantiles were 23 and 271 for suicidal ideation and attempt, respectively. Performance was maintained across demographic subgroups. Numbers needed to screen for suicide attempt by sex were 256 for men and 323 for women; and by race: 373, 176, and 407 for White, Black, and non-White/non-Black patients, respectively. Model C statistics were, across the health system: 0.836

show abstract

Variation in patterns of health care before suicide: A population case-control study

Cited by 80 publications

References 41 publications

Natural language processing and machine learning of electronic health records for prediction of first-time suicide attempts

Natural language processing and machine learning of electronic health records for prediction of first-time suicide attempts

Collaborative care for depression and suicide prevention: a feasible intervention within the Mexican health system

Prospective Validation of an Electronic Health Record–Based, Real-Time Suicide Risk Model

Contact Info

Product

Resources

About