B Eggleston1, C E Dismuke-Greer2,3, T K Pogoda4,5, J H Denning6,7, B C Eapen8, K F Carlson9,10, S Bhatnagar11, R Nakase-Richardson12,13,14, M Troyanskaya15,16, T Nolen1, W C Walker17,18. 1. RTI International, Research Triangle Park, NC, USA. 2. Health Economics Resource Center (HERC), VA Palo Alto Healthcare System, Palo Alto, California, USA. 3. Department of Medicine, Medical University of South Carolina, Charleston, SC, USA. 4. Center for Healthcare Organization and Implementation Research, VA Boston Healthcare System, Boston, MA, USA. 5. School of Public Health, Boston University, Boston, MA, USA. 6. Mental Health Care Line, Ralph H. Johnson VA Medical Center, Charleston, SC, USA. 7. Department of Psychiatry and Behavioral Sciences, Medical University of South Carolina. 8. Department of Physical Medicine and Rehabilitation, VA Greater Los Angeles Healthcare System, Los Angeles, CA, USA. 9. HSR&D Center to Improve Veteran Involvement in Care (CIVIC), VA Portland Health Care System (R&D 66). 10. OHSU-PSU School of Public Health, Oregon Health and Science University. 11. Acting, Assistant Deputy Undersecretary for Health in Quality, Safety & Value, Department of Veterans Affairs. 12. MHBS, James A. Haley Veterans Hospital, Tampa, FL, USA. 13. Division of Pulmonary and Sleep Medicine, Morsani College of Medicine, University of South Florida, Tampa, FL, USA. 14. Defense and Veterans Brain Injury Center, Tampa, FL, USA. 15. Department of Physical Medicine and Rehabilitation, Baylor College of Medicine, Houston, TX, USA. 16. Michael E. DeBakey, Houston, VA, Medical Center. 17. Department Physical Medicine and Rehabilitation, Virginia Commonwealth University, Richmond, VA, USA. 18. Hunter Holmes McGuire Veterans Affairs Medical Center, Richmond, VA, USA.
Abstract
Background: Research has shown that number of and blast-related Traumatic Brain Injuries (TBI) are associated with higher levels of service-connected disability (SCD) among US veterans. This study builds and tests a prediction model of SCD based on combat and training exposures experienced during active military service. Methods: Based on 492 US service member and veteran data collected at four Department of Veterans Affairs (VA) sites, traditional and Machine Learning algorithms were used to identify a best set of predictors and model type for predicting %SCD ≥50, the cut-point that allows for veteran access to 0% co-pay for VA health-care services. Results: The final model of predicting %SCD ≥50 in veterans revealed that the best blast/injury exposure-related predictors while deployed or non-deployed were: 1) number of controlled detonations experienced, 2) total number of blast exposures (including controlled and uncontrolled), and 3) the total number of uncontrolled blast and impact exposures.Conclusions and Relevance: We found that the highest blast/injury exposure predictor of %SCD ≥50 was number of controlled detonations, followed by total blasts, controlled or uncontrolled, and occurring in deployment or non-deployment settings. Further research confirming repetitive controlled blast exposure as a mechanism of chronic brain insult should be considered.
Background: Research has shown that number of and blast-related Traumatic Brain Injuries (TBI) are associated with higher levels of service-connected disability (SCD) among US veterans. This study builds and tests a prediction model of SCD based on combat and training exposures experienced during active military service. Methods: Based on 492 US service member and veteran data collected at four Department of Veterans Affairs (VA) sites, traditional and Machine Learning algorithms were used to identify a best set of predictors and model type for predicting %SCD ≥50, the cut-point that allows for veteran access to 0% co-pay for VA health-care services. Results: The final model of predicting %SCD ≥50 in veterans revealed that the best blast/injury exposure-related predictors while deployed or non-deployed were: 1) number of controlled detonations experienced, 2) total number of blast exposures (including controlled and uncontrolled), and 3) the total number of uncontrolled blast and impact exposures.Conclusions and Relevance: We found that the highest blast/injury exposure predictor of %SCD ≥50 was number of controlled detonations, followed by total blasts, controlled or uncontrolled, and occurring in deployment or non-deployment settings. Further research confirming repetitive controlled blast exposure as a mechanism of chronic brain insult should be considered.
Authors: Kalyn C Jannace; Lisa Pompeii; David Gimeno Ruiz de Porras; William Brett Perkison; Jose-Miguel Yamal; Daniel W Trone; Rudolph P Rull Journal: Mil Med Date: 2022-02-27 Impact factor: 1.563