Investigating the differential impact of psychosocial factors by patient characteristics and demographics on Veteran suicide risk through machine learning extraction of cross-modal interactions

Accurate prediction of suicide risk is crucial for identifying patients with elevated risk burden, helping ensure these patients receive targeted care. The US Department of Veteran Affairs' suicide prediction model primarily leverages structured electronic health records (EHR) data. This approach largely overlooks unstructured EHR, a data format that could be utilized to enhance predictive accuracy. This study aims to enhance suicide risk models' predictive accuracy by developing a model that incorporates both structured EHR predictors and semantic NLP-derived variables from unstructured EHR. XGBoost models were fit to predict suicide risk- the interactions identified by the model were extracted using SHAP, validated using logistic regression models, added to a ridge regression model, which was subsequently compared to a ridge regression approach without the use of interactions. By introducing a selection parameter, α, to balance the influence of structured (α=1) and unstructured (α=0) data, we found that intermediate α values achieved optimal performance across various risk strata, improved model performance of the ridge regression approach and uncovered significant cross-modal interactions between psychosocial constructs and patient characteristics. These interactions highlight how psychosocial risk factors are influenced by individual patient contexts, potentially informing improved risk prediction methods and personalized interventions. Our findings underscore the importance of incorporating nuanced narrative data into predictive models and set the stage for future research that will expand the use of advanced machine learning techniques, including deep learning, to further refine suicide risk prediction methods.

Read the full article
Report a problem with this article

Related articles

  • More for Researchers

    Examination of the mental health symptoms and stigmatizing attitudes of student servicemembers and Veterans in postsecondary education

    Abstract:Student servicemembers and veterans (SSM/V) face challenges when transitioning from military service into higher education, including mental health concerns and difficulties with academic and social adjustment. This study examined mental health symptoms, adjustment to college, stigma, and help-seeking attitudes among 79 SSM/V enrolled in postsecondary education. Participants completed measures related to depression (PHQ-8), anxiety (GAD-7), posttraumatic stress (PCL-5), adjustment to college (VAC), self-stigma (SSOSH), public stigma (SSRPH), and attitudes toward seeking professional psychological help (ATSPPH-SF). Results indicated that average scores reflected mild levels of depression, anxiety, and posttraumatic stress. Veterans reported significantly higher levels of depressive and PTSD symptoms compared to active-duty servicemembers. Number of deployments was negatively correlated with adjustment scores. Race and ethnicity were found to be significant predictors of help-seeking attitudes. Although college adjustment was negatively correlated with depression, anxiety, and PTSD symptoms, the findings did not reach statistical significance, perhaps due to the limited variability in the sample. Most participants reported generally positive attitudes toward mental health services, though both self-stigma and perceived public stigma were present. Service utilization was high overall, with 76% of participants reporting prior mental health service use and 44% who were currently engaged in treatment at time of survey completion. Findings underscore the importance of addressing cultural factors, deployment experiences, and stigma to improve adjustment, retention, and well-being among SSM/V in postsecondary education.

    Mental Health