Search

BACKGROUND Prior suicide attempts are a strong risk factor for future attempts. There is growing interest in using longitudinal electronic health record (EHR) data to derive risk prediction models for suicidal behavior. However, model performance may be inflated by an unrecognized form of “data leakage” during model training: codes for suicide attempt outcomes may refer to prior attempts also included as predictors. OBJECTIVE We aimed to develop an automated rule for determining when documented suicide attempt codes identify distinct events. METHODS From a large healthcare system’s EHR, patients with at least two suicide attempt codes were randomly sampled (N = 369). Chart reviewers assigned clinical setting, attempt method, and inter-code interval to each pair of suicide attempt codes. The probability that the second code in a pair referred to a distinct attempt from its preceding code was calculated by setting, method, and inter-code interval. RESULTS Of the 1,253 code pairs reviewed, 78% were non-independent (i.e., two codes referred to the same event). When the second code in a pair was assigned in a setting other than the emergency department (ED), it represented a distinct event less than 15% of the time. Code pairs in which the second code was assigned in the ED at least 5 days after its preceding code had a positive predictive value (PPV) of 0.90. CONCLUSIONS Suicide attempt codes documented in an ED setting at least 5 days after a preceding code can be confidently treated as new events in EHR-based suicide risk prediction models. CLINICALTRIAL NA

Clinical risk prediction models powered by electronic health records (EHRs) are becoming increasingly widespread in clinical practice. With suicide-related mortality rates rising in recent years, it is becoming increasingly urgent to understand, predict, and prevent suicidal behavior. Here, we compare the predictive value of structured and unstructured EHR data for predicting suicide risk. We find that Naive Bayes Classifier (NBC) and Random Forest (RF) models trained on structured EHR data perform better than those based on unstructured EHR data. An NBC model trained on both structured and unstructured data yields similar performance (AUC = 0.743) to an NBC model trained on structured data alone (0.742, p = 0.668), while an RF model trained on both data types yields significantly better results (AUC = 0.903) than an RF model trained on structured data alone (0.887, p

Background: Interest in developing machine learning algorithms that use electronic health record data to predict patients’ risk of suicidal behavior has recently proliferated. Whether and how such models might be implemented and useful in clinical practice, however, remains unknown. In order to ultimately make automated suicide risk prediction algorithms useful in practice, and thus better prevent patient suicides, it is critical to partner with key stakeholders (including the frontline providers who will be using such tools) at each stage of the implementation process.Objective: The aim of this focus group study was to inform ongoing and future efforts to deploy suicide risk prediction models in clinical practice. The specific goals were to better understand hospital providers’ current practices for assessing and managing suicide risk; determine providers’ perspectives on using automated suicide risk prediction algorithms; and identify barriers, facilitators, recommendations, and factors to consider for initiatives in this area. Methods: We conducted 10 two-hour focus groups with a total of 40 providers from psychiatry, internal medicine and primary care, emergency medicine, and obstetrics and gynecology departments within an urban academic medical center. Audio recordings of open-ended group discussions were transcribed and coded for relevant and recurrent themes by two independent study staff members. All coded text was reviewed and discrepancies resolved in consensus meetings with doctoral-level staff. Results: Though most providers reported using standardized suicide risk assessment tools in their clinical practices, existing tools were commonly described as unhelpful and providers indicated dissatisfaction with current suicide risk assessment methods. Overall, providers’ general attitudes toward the practical use of automated suicide risk prediction models and corresponding clinical decision support tools were positive. Providers were especially interested in the potential to identify high-risk patients who might be missed by traditional screening methods. Some expressed skepticism about the potential usefulness of these models in routine care; specific barriers included concerns about liability, alert fatigue, and increased demand on the healthcare system. Key facilitators included presenting specific patient-level features contributing to risk scores, emphasizing changes in risk over time, and developing systematic clinical workflows and provider trainings. Participants also recommended considering risk-prediction windows, timing of alerts, who will have access to model predictions, and variability across treatment settings.Conclusions: Providers were dissatisfied with current suicide risk assessment methods and open to the use of a machine learning-based risk prediction system to inform clinical decision-making. They also raised multiple concerns about potential barriers to the usefulness of this approach and suggested several possible facilitators. Future efforts in this area will benefit from incorporating systematic qualitative feedback from providers, patients, administrators, and payers on the use of new methods in routine care, especially given the complex, sensitive, and unfortunately still stigmatized nature of suicide risk.

BACKGROUND Interest in developing machine learning models that use electronic health record data to predict patients’ risk of suicidal behavior has recently proliferated. However, whether and how such models might be implemented and useful in clinical practice remain unknown. To ultimately make automated suicide risk–prediction models useful in practice, and thus better prevent patient suicides, it is critical to partner with key stakeholders, including the frontline providers who will be using such tools, at each stage of the implementation process. OBJECTIVE The aim of this focus group study is to inform ongoing and future efforts to deploy suicide risk–prediction models in clinical practice. The specific goals are to better understand hospital providers’ current practices for assessing and managing suicide risk; determine providers’ perspectives on using automated suicide risk–prediction models in practice; and identify barriers, facilitators, recommendations, and factors to consider. METHODS We conducted 10 two-hour focus groups with a total of 40 providers from psychiatry, internal medicine and primary care, emergency medicine, and obstetrics and gynecology departments within an urban academic medical center. Audio recordings of open-ended group discussions were transcribed and coded for relevant and recurrent themes by 2 independent study staff members. All coded text was reviewed and discrepancies were resolved in consensus meetings with doctoral-level staff. RESULTS Although most providers reported using standardized suicide risk assessment tools in their clinical practices, existing tools were commonly described as unhelpful and providers indicated dissatisfaction with current suicide risk assessment methods. Overall, providers’ general attitudes toward the practical use of automated suicide risk–prediction models and corresponding clinical decision support tools were positive. Providers were especially interested in the potential to identify high-risk patients who might be missed by traditional screening methods. Some expressed skepticism about the potential usefulness of these models in routine care; specific barriers included concerns about liability, alert fatigue, and increased demand on the health care system. Key facilitators included presenting specific patient-level features contributing to risk scores, emphasizing changes in risk over time, and developing systematic clinical workflows and provider training. Participants also recommended considering risk-prediction windows, timing of alerts, who will have access to model predictions, and variability across treatment settings. CONCLUSIONS Providers were dissatisfied with current suicide risk assessment methods and were open to the use of a machine learning–based risk-prediction system to inform clinical decision-making. They also raised multiple concerns about potential barriers to the usefulness of this approach and suggested several possible facilitators. Future efforts in this area will benefit from incorporating systematic qualitative feedback from providers, patients, administrators, and payers on the use of these new approaches in routine care, especially given the complex, sensitive, and unfortunately still stigmatized nature of suicide risk.

Importance Suicide is a leading cause of mortality, with suicide-related deaths increasing in recent years. Automated methods for individualized risk prediction have great potential to address this growing public health threat. To facilitate their adoption, they must first be validated across diverse health care settings. Objective To evaluate the generalizability and cross-site performance of a risk prediction method using readily available structured data from electronic health records in predicting incident suicide attempts across multiple, independent, US health care systems. Design, Setting, and Participants For this prognostic study, data were extracted from longitudinal electronic health record data comprisingInternational Classification of Diseases, Ninth Revisiondiagnoses, laboratory test results, procedures codes, and medications for more than 3.7 million patients from 5 independent health care systems participating in the Accessible Research Commons for Health network. Across sites, 6 to 17 years’ worth of data were available, up to 2018. Outcomes were defined byInternational Classification of Diseases, Ninth Revisioncodes reflecting incident suicide attempts (with positive predictive value >0.70 according to expert clinician medical record review). Models were trained using naive Bayes classifiers in each of the 5 systems. Models were cross-validated in independent data sets at each site, and performance metrics were calculated. Data analysis was performed from November 2017 to August 2019. Main Outcomes and Measures The primary outcome was suicide attempt as defined by a previously validated case definition usingInternational Classification of Diseases, Ninth Revisioncodes. The accuracy and timeliness of the prediction were measured at each site. Results Across the 5 health care systems, of the 3 714 105 patients (2 130 454 female [57.2%]) included in the analysis, 39 162 cases (1.1%) were identified. Predictive features varied by site but, as expected, the most common predictors reflected mental health conditions (eg, borderline personality disorder, with odds ratios of 8.1-12.9, and bipolar disorder, with odds ratios of 0.9-9.1) and substance use disorders (eg, drug withdrawal syndrome, with odds ratios of 7.0-12.9). Despite variation in geographical location, demographic characteristics, and population health characteristics, model performance was similar across sites, with areas under the curve ranging from 0.71 (95% CI, 0.70-0.72) to 0.76 (95% CI, 0.75-0.77). Across sites, at a specificity of 90%, the models detected a mean of 38% of cases a mean of 2.1 years in advance. Conclusions and Relevance Across 5 diverse health care systems, a computationally efficient approach leveraging the full spectrum of structured electronic health record data was able to detect the risk of suicidal behavior in unselected patients. This approach could facilitate the development of clinical decision support tools that inform risk reduction interventions.