Evaluation of a Model to Target High-risk Psychiatric Inpatients for an Intensive Postdischarge Suicide Prevention Intervention.

Importance: The months after psychiatric hospital discharge are a time of high risk for suicide. Intensive postdischarge case management, although potentially effective in suicide prevention, is likely to be cost-effective only if targeted at high-risk patients. A previously developed machine learning (ML) model showed that postdischarge suicides can be predicted from electronic health records and geospatial data, but it is unknown if prediction could be improved by adding additional information. Objective: To determine whether model prediction could be improved by adding information extracted from clinical notes and public records. Design, Setting, and Participants: Models were trained to predict suicides in the 12 months after Veterans Health Administration (VHA) short-term (less than 365 days) psychiatric hospitalizations between the beginning of 2010 and September 1, 2012 (299 050 hospitalizations, with 916 hospitalizations followed within 12 months by suicides) and tested in the hospitalizations from September 2, 2012, to December 31, 2013 (149 738 hospitalizations, with 393 hospitalizations followed within 12 months by suicides). Validation focused on net benefit across a range of plausible decision thresholds. Predictor importance was assessed with Shapley additive explanations (SHAP) values. Data were analyzed from January to August 2022. Main Outcomes and Measures: Suicides were defined by the National Death Index. Base model predictors included VHA electronic health records and patient residential data. The expanded predictors came from natural language processing (NLP) of clinical notes and a social determinants of health (SDOH) public records database. Results: The model included 448 788 unique hospitalizations. Net benefit over risk horizons between 3 and 12 months was generally highest for the model that included both NLP and SDOH predictors (area under the receiver operating characteristic curve range, 0.747-0.780; area under the precision recall curve relative to the suicide rate range, 3.87-5.75). NLP and SDOH predictors also had the highest predictor class-level SHAP values (proportional SHAP = 64.0% and 49.3%, respectively), although the single highest positive variable-level SHAP value was for a count of medications classified by the US Food and Drug Administration as increasing suicide risk prescribed the year before hospitalization (proportional SHAP = 15.0%). Conclusions and Relevance: In this study, clinical notes and public records were found to improve ML model prediction of suicide after psychiatric hospitalization. The model had positive net benefit over 3-month to 12-month risk horizons for plausible decision thresholds. Although caution is needed in inferring causality based on predictor importance, several key predictors have potential intervention implications that should be investigated in future studies.

Using Administrative Data to Predict Suicide After Psychiatric Hospitalization in the Veterans Health Administration System.

There is a very high suicide rate in the year after psychiatric hospital discharge. Intensive postdischarge case management programs can address this problem but are not cost-effective for all patients. This issue can be addressed by developing a risk model to predict which inpatients might need such a program. We developed such a model for the 391,018 short-term psychiatric hospital admissions of US veterans in Veterans Health Administration (VHA) hospitals 2010-2013. Records were linked with the National Death Index to determine suicide within 12 months of hospital discharge (n=771). The Super Learner ensemble machine learning method was used to predict these suicides for time horizon between 1 week and 12 months after discharge in a 70% training sample. Accuracy was validated in the remaining 30% holdout sample. Predictors included VHA administrative variables and small area geocode data linked to patient home addresses. The models had AUC=.79-.82 for time horizons between 1 week and 6 months and AUC=.74 for 12 months. An analysis of operating characteristics showed that 22.4%-32.2% of patients who died by suicide would have been reached if intensive case management was provided to the 5% of patients with highest predicted suicide risk. Positive predictive value (PPV) at this higher threshold ranged from 1.2% over 12 months to 3.8% per case manager year over 1 week. Focusing on the low end of the risk spectrum, the 40% of patients classified as having lowest risk account for 0%-9.7% of suicides across time horizons. Variable importance analysis shows that 51.1% of model performance is due to psychopathological risk factors accounted, 26.2% to social determinants of health, 14.8% to prior history of suicidal behaviors, and 6.6% to physical disorders. The paper closes with a discussion of next steps in refining the model and prospects for developing a parallel precision treatment model.

Alcohol and Suicide Risk: Examining the Role of Meaning-Making.

OBJECTIVE: Conceptual understandings of meaning-making suggest that it may have protective value in regard to alcohol misuse and suicidal behavior. Accordingly, the aim of this study was to examine whether meaning-making attenuated the relationship between alcohol misuse and suicide risk severity in a population of active-duty service members. METHODS: The sample (N = 97) was recruited while presenting for emergency behavioral health services in circumstances indicative of high-risk suicidality: endorsing current suicidal ideation with intent to die. Those who reported ideation with a lifetime history of a past suicide attempt were conceptualized as being in a more severe category of suicide risk than ideation without a lifetime history of a past suicide attempt. Participants completed the Suicidal Behaviors Questionnaire-Revised, Meaning in Life Questionnaire, Alcohol Use Disorders Identification Test consumption questions, and items that assessed demographic variables. Data were analyzed using chi-squared test of independence, Fisher's exact test, Kendall rank correlation coefficient, and logistic regression modeling. RESULTS: Regression analysis identified a statistically significant association between number of drinks consumed daily and reporting a lifetime history of a past suicide attempt, odds ratio (OR) = 1.60, 95% confidence interval (CI) [1.11, 2.32], p = .01. Number of drinks consumed remained significant even after adjusting for both the search for and presence of meaning, OR = 1.70, 95% CI [1.16, 2.51], p = .01. These results remained unchanged even when adjusting for gender, race, ethnicity, and relationship status. No statistically significant interaction effects were noted between meaning-making and alcohol consumption. CONCLUSIONS: Meaning-making did not appear to attenuate the effect of alcohol misuse on suicide risk severity in a sample of service members at high-risk of suicidality. Additional research is needed to better understand the relationship among meaning-making, alcohol misuse, and suicidal behavior.

Considerations in the Use of Interactive Voice Recording for the Temporal Assessment of Suicidal Ideation and Alcohol Use.

BACKGROUND: A greater understanding of the temporal variation of suicidal ideation and suicidal behavior is needed to inform more effective prevention efforts. Interactive voice recording (IVR) allows for the study of temporal relationships that cannot be captured with most traditional methodologies. AIMS: To examine the feasibility of implementing IVR for the assessment of suicidal ideation. METHOD: Participants (n = 4) receiving a brief intervention based on dialectical behavior therapy were asked to respond to three phone-based surveys each day over 6 weeks that assessed suicidal ideation and alcohol consumption. RESULTS: Participants completed 77.7% of daily assessments, reported that calls were not burdensome, and indicated that calls were sometimes helpful in interrupting suicidal ideation. CONCLUSION: The preliminary data reported here provide optimism for the use of IVR and other forms of ecological momentary assessment in the exploration of the antecedents of suicidal behavior.