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.
Abstract: Background: Exposure to potentially morally injurious events (PMIEs) during military service can lead to moral injury (MI) outcomes and posttraumatic stress symptoms (PTSS). This longitudinal study examined the relationships between PMIE exposure, MI outcomes, and PTSS among Israeli combat veterans, and the potential protective role of dispositional forgiveness in these associations. Method: Participants were 169 Israeli combat veterans who participated in a six-year longitudinal study with four measurement points (T1: 12 months before enlistment, T2: Six months following enlistment- pre-deployment, T3: 18 months following enlistment- post-deployment, and T4: 28 months following discharge). Participants’ characteristics were assessed via semi-structured interviews (T1) and validated self-report measures (T2-T4) between 2019-2024. Results: Approximately 36% of participants reported exposure to PMIEs during service, with 13% exceeding the clinical threshold for probable PTSD at T4. PMIE-Betrayal at T3 was positively associated with MI outcomes of shame and trust violation at T4. The indirect effect of PMIEs on PTSS through MI outcome-Shame depended on forgiveness levels. Among veterans with low forgiveness, higher exposure to PMIE-Betrayal was associated with increased MI shame, which was linked to more severe PTSS. Conversely, for those with high forgiveness, exposure to PMIE-Self and Other was associated with decreased MI shame and subsequently reduced PTSS. Conclusion: Dispositional forgiveness moderates the relationship between PMIE exposure and MI outcomes, particularly shame, which mediates the development of PTSS. These findings highlight forgiveness as a potential target for intervention in treating moral injury and preventing PTSS among combat veterans.