Assessment of depression in veterans across missions: a validity study using Rasch measurement models

Early prediction of mental health problems following military deployment: Integrating pre- and post-deployment factors in neural network models

Military personnel deployed to war zones are at increased risk of mental health problems such as posttraumatic stress disorder (PTSD) or depression. Early pre- or post-deployment identification of those at highest risk of such problems is crucial to target intervention to those in need. However, sufficiently accurate models predicting objectively assessed mental health outcomes have not been put forward. In a sample consisting of all Danish military personnel who deployed to war zones for the first (N = 27,594), second (N = 11,083) and third (N = 5,161) time between 1992 and 2013, we apply neural networks to predict psychiatric diagnoses or use of psychotropic medicine in the years following deployment. Models are based on pre-deployment registry data alone or on pre-deployment registry data in combination with post-deployment questionnaire data on deployment experiences or early post-deployment reactions. Further, we identified the most central predictors of importance for the first, second, and third deployment. Models based on pre-deployment registry data alone had lower accuracy (AUCs ranging from 0.61 (third deployment) to 0.67 (first deployment)) than models including pre- and post-deployment data (AUCs ranging from 0.70 (third deployment) to 0.74 (first deployment)). Age at deployment, deployment year and previous physical trauma were important across deployments. Post-deployment predictors varied across deployments but included deployment exposures as well as early post-deployment symptoms. The results suggest that neural network models combining pre- and early post-deployment data can be utilized for screening tools that identify individuals at risk of severe mental health problems in the years following military deployment.

Measuring Social Support among Soldiers with the Experienced Post-Deployment Social Support Scale (EPSSS): A Rasch-Based Construct Validity Study

Perceived social support following deployment is a known buffer against post-deployment adverse mental health outcomes. Given contextual sensitivity of social support measures, scales that address specific social support needs of soldiers in the first months after home coming should be developed and validated. In a sample of 553 soldiers deployed to Afghanistan at two different time points (2009 and 2013, respectively), we selected items for and tested the construct validity of an 8-item measure of experienced post-deployment social support (experienced post-deployment social support scale; EPSSS). Within the item response theory framework, we used Rasch models (RM) to conduct item analysis with an emphasis on testing for differential item functioning (DIF) across background variables such as previous deployments and cohort. In short, we found that the scale did not fit the Rasch model, but with exclusion of two items, a 6-item version of the scale did fit an extended graphical loglinear Rasch model (GLLRM) with only one instance of DIF, for which the score can be adjusted. We also demonstrated that when applied as a scale, the DIF will not affect the results substantially. Hence, we conclude that the constructed 6-item EPSSS can be validly applied without score correction to assess the level of social support in Danish soldiers after home coming.

Deployment experiences and mental health problems as predictors of post-deployment unemployment length: a prospective, register-based study among Danish soldiers

OBJECTIVES

To test responses of formerly deployed soldiers (FDS) to a questionnaire on deployment experiences in combination with screening levels of post-traumatic stress disorder (PTSD) and depression approximately 6 months after homecoming as predictors of the subsequent probability of gaining employment when unemployed within 5 years post-deployment.

DESIGN, SETTING AND PARTICIPANTS

Danish FDS responders (n=3935) and non-responders (n=3046) to a 6-month post-deployment screening questionnaire after returning from a first-ever deployment to Kosovo, Iraq or Afghanistan (2002 to 2012) were included in the study and followed in public registers from 6 months to 5 years post-deployment.

PRIMARY AND SECONDARY OUTCOME MEASURES

We tested Cox regression models including deployment experiences (1a), screening levels of PTSD and depressive symptoms (1b), and their combination (2) for FDS responders. For all FDS, a secondary model included a measure on whether they responded to the questionnaire (3).

RESULTS

Neither the deployment experiences (1a) of exposure to danger and combat (HR=1.00, 95% CI=0.97 to 1.03) and witnessing consequences of war (HR=1.01, 95% CI=0.96 to 1.06), or the screening levels (1b) of PTSD (HR=1.06, 95% CI=0.84 to 1.33) and depressive symptoms (HR=0.82, 95% CI=0.64 to 1.06) were significant predictors of transitioning from unemployment to employment. Similar results were found for the combined model (2). A tendency among non-respondents (3) to have a lower probability of transitioning from unemployment to employment was found (HR=0.90, 95% CI=0.81 to 1.00).

CONCLUSION

Deployment experiences, PTSD and depressive symptoms, as measured at 6-month screening questionnaire, did not predict differences in the probability of gaining employment when unemployed within 5 years post-deployment. However, the findings suggest that those with the least probability of transitioning from unemployment to employment can be found among the non-responders to the post-deployment screening questionnaire.

Applicability of an Automated Model and Parameter Selection in the Prediction of Screening-Level PTSD in Danish Soldiers Following Deployment: Development Study of Transferable Predictive Models Using Automated Machine Learning

BACKGROUND

Posttraumatic stress disorder (PTSD) is a relatively common consequence of deployment to war zones. Early postdeployment screening with the aim of identifying those at risk for PTSD in the years following deployment will help deliver interventions to those in need but have so far proved unsuccessful.

OBJECTIVE

This study aimed to test the applicability of automated model selection and the ability of automated machine learning prediction models to transfer across cohorts and predict screening-level PTSD 2.5 years and 6.5 years after deployment.

METHODS

Automated machine learning was applied to data routinely collected 6-8 months after return from deployment from 3 different cohorts of Danish soldiers deployed to Afghanistan in 2009 (cohort 1, N=287 or N=261 depending on the timing of the outcome assessment), 2010 (cohort 2, N=352), and 2013 (cohort 3, N=232).

RESULTS

Models transferred well between cohorts. For screening-level PTSD 2.5 and 6.5 years after deployment, random forest models provided the highest accuracy as measured by area under the receiver operating characteristic curve (AUC): 2.5 years, AUC=0.77, 95% CI 0.71-0.83; 6.5 years, AUC=0.78, 95% CI 0.73-0.83. Linear models performed equally well. Military rank, hyperarousal symptoms, and total level of PTSD symptoms were highly predictive.

CONCLUSIONS

Automated machine learning provided validated models that can be readily implemented in future deployment cohorts in the Danish Defense with the aim of targeting postdeployment support interventions to those at highest risk for developing PTSD, provided the cohorts are deployed on similar missions.

Low-level cognitive ability in young adulthood and other risk factors of depression in an observational cohort study among deployed Danish soldiers

PURPOSE

Evidence exists of an association between pre-morbid lower cognitive ability and higher risk of hospitalization for depressive disorder in civilian cohorts. The purpose of this study was to examine the relationship of cognitive ability at conscription with post-deployment depression and the influence of (1) baseline factors: age, gender, and pre-deployment educational level, (2) deployment-related factors: e.g., war-zone stress and social support, and (3) co-morbid PTSD.

METHODS

An observational cohort study linking conscription board registry data with post-deployment self-report data. The study population consisted of Danish Army military personnel deployed to different war zones from 1997 to 2015. The association between cognitive ability at conscription and post-deployment depression was analyzed using repeated-measure logistic regression models.

RESULTS

Study population totaled 9716 with a total of 13,371 deployments. Low-level cognitive ability at conscription was found to be weakly associated with post-deployment probable depression after adjustment for more important risk factors like gender, education, and deployment-related factors [odds ratio (OR) 0.93, 95% confidence interval (CI) 0.88-0.99]. The co-occurrence rate with PTSD was nearly 60%. When adding co-morbid PTSD as an independent variable, the association between cognitive ability and probable depression became insignificant, OR 0.95, CI 0.89-1.02.

CONCLUSIONS

Low cognitive ability at conscription is a risk factor for depression among returning military personnel, but unimportant compared to gender, education, and deployment-related factors. Part of this effect may be related to co-morbid PTSD. Use of cognitive ability score as an isolated selection tool cannot be recommended because of low predictive performance.

Perceived danger during deployment: a Rasch validation of an instrument assessing perceived combat exposure and the witnessing of combat consequences in a war zone

The potential stressors associated with military deployment are related to an increased risk of adverse mental health outcomes. Perceived exposure to combat has been found to be proportional to the severity of post-deployment posttraumatic stress disorder (PTSD). However, other perceived adversities during deployment, such as witnessing danger, distress, and hardship in the war zone, have been less systematically studied, but might play an equally substantial role for post-deployment mental health. The development and validation of scales that assess these related constructs are needed to distinguish their contribution to post-deployment risk of PTSD. We evaluated the validity of 10 items measuring perceived danger distributed to all deployed personnel with the Danish Defense since 1998. We hypothesize two scales: Exposure to Danger and Combat (EDC) and Witnessing Consequences of War (WCW). Two military cohorts deployed to Afghanistan in 2009 (Cohort 1, N = 276) and 2013 (Cohort 2, N = 273) were included. Questionnaire data was collected six months after homecoming, including deployment experiences and post-deployment reactions. We tested the construct validity of the 10 items of perceived danger with Rasch models (RM), focusing specifically on presence of subscales, and differential item functioning (DIF) across cohorts. We confirmed the existence of two separate subscales, EDCS and WCWS, both with adequate reliability. None of the subscales fitted a pure RM, but adequate fit was found for graphical log-linear RMs with evidence of DIF for the ECDS. However, adjusting the score to account for DIF had practically no effect, suggesting that the total non-adjusted mean score can be used in future cohort comparisons. Perceived exposure to combat and danger and witnessing consequences of war are related, but essentially distinct, concepts, each providing unique information about deployment adversities. Future studies should evaluate their shared and unique contribution to the risk of post-deployment PTSD.