TY - JOUR PY - 2023// TI - Evaluation of a model to target high-risk psychiatric inpatients for an intensive postdischarge suicide prevention intervention JO - JAMA Psychiatry A1 - Kessler, Ronald C. A1 - Bauer, Mark S. A1 - Bishop, Todd M. A1 - Bossarte, Robert M. A1 - Castro, Victor M. A1 - Demler, Olga V. A1 - Gildea, Sarah M. A1 - Goulet, Joseph L. A1 - King, Andrew J. A1 - Kennedy, Chris J. A1 - Landes, Sara J. A1 - Liu, Howard A1 - Luedtke, Alex A1 - Mair, Patrick A1 - Marx, Brian P. A1 - Nock, Matthew K. A1 - Petukhova, Maria V. A1 - Pigeon, Wilfred R. A1 - Sampson, Nancy A. A1 - Smoller, Jordan W. A1 - Miller, Aletha A1 - Haas, Gretchen A1 - Benware, Jeffrey A1 - Bradley, John A1 - Owen, Richard R. A1 - House, Samuel A1 - Urosevic, Snezana A1 - Weinstock, Lauren M. SP - ePub EP - ePub VL - ePub IS - ePub N2 - 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.

Language: en

LA - en SN - 2168-622X UR - http://dx.doi.org/10.1001/jamapsychiatry.2022.4634 ID - ref1 ER -