Predicting and Planning for Musculoskeletal Service-Connected Disabilities in VA Using Disability for Active Duty OEF/OIF Military Service Members.

INTRODUCTION: Musculoskeletal (MSK) conditions are commonly seen among military service members (SM) and Veterans. We explored correlates of award of MSK-related service-connected disability benefits (SCDB) among SM seeking care in Veterans Affairs (VA) hospitals. MATERIALS AND METHODS: Department of Defense data on SM who separated from October 1, 2001 to May 2017 were linked to VA administrative data. Using adjusted logistic regression models, we determined the odds of receiving MSK SCDB. RESULTS: A total of 1,558,449 (79% of separating SM) had at least one encounter in VA during the study period (7.8% disability separations). Overall, 51% of this cohort had at least one MSK SCDB (88% among disability separations, 48% among normal). Those with disability separations (as compared to normal separations) were significantly more likely to receive MSK SCDB (odds ratio 2.37) as were females (compared to males, odds ratio 1.15). CONCLUSIONS: Although active duty SM with disability separations were more likely to receive MSK-related service-connected disability ratings in the VA, those with normal separations also received such awards. Identifying those at highest risk for MSK-related disability could lead to improved surveillance and prevention strategies in the Department of Defense and VA health care systems to prevent further damage and disability.

Exploring Disparities in Awarding VA Service-Connected Disability for Post-Traumatic Stress Disorder for Active Duty Military Service Members from Recent Conflicts in Iraq and Afghanistan.

INTRODUCTION: We explore disparities in awarding post-traumatic stress disorder (PTSD) service-connected disability benefits (SCDB) to veterans based on gender, race/ethnicity, and misconduct separation. METHODS: Department of Defense data on service members who separated from October 1, 2001 to May 2017 were linked to Veterans Administration (VA) administrative data. Using adjusted logistic regression models, we determined the odds of receiving a PTSD SCDB conditional on a VA diagnosis of PTSD. RESULTS: A total of 1,558,449 (79% of separating service members) had at least one encounter in VA during the study period (12% female, 4.5% misconduct separations). Females (OR 0.72) and Blacks (OR 0.93) were less likely to receive a PTSD award and were nearly equally likely to receive a PTSD diagnosis (OR 0.97, 1.01). Other racial/ethnic minorities were more likely to receive an award and diagnosis, as were those with misconduct separations (award OR 1.3, diagnosis 2.17). CONCLUSIONS: Despite being diagnosed with PTSD at similar rates to their referent categories, females and Black veterans are less likely to receive PTSD disability awards. Other racial/ethnic minorities and those with misconduct separations were more likely to receive PTSD diagnoses and awards. Further study is merited to explore variation in awarding SCDB.

Distance Matters: Geographic barriers to long acting reversible and permanent contraception for homeless women Veterans.

Women Veterans who experience homelessness are at high risk of unintended pregnancy and adverse outcomes. Contraception could mitigate risks, yet access barriers exist across the Veterans Health Administration (VHA). We identified all US women Veterans, age 18-44y with evidence of homelessness in VHA administrative data between fiscal years 2002-2015, in order to document the geographic distribution of ever-homeless women Veterans in relation to VA Medical Centers (VAMCs) and assess geographic associations between long acting reversible contraceptives (LARC) or permanent contraception (PC) use. We calculated VAMC travel distance from last known ZIP Code. We used multivariate logistic regression models to explore contraceptive method associations. We included 41,722 ever-homeless women Veterans; 9.2% had LARC exposure and 7.5% PC. We found 29% of ever-homeless women Veterans resided >40miles from the nearest VAMC and increasing drive distance was negatively correlated with contraceptive exposure, especially for Veterans residing >100miles from a VAMC. Increasing distance to the nearest VAMC results in a geographic barrier to the most effective contraceptive options for women Veterans. The VHA is uniquely positioned to leverage its rural and homeless healthcare expertise to address geographic barriers and integrate comprehensive contraceptive services into established programs for high-risk Veterans.

Distance to Veterans Administration Medical Centers as a Barrier to Specialty Care for Homeless Women Veterans.

Homeless women Veterans have a high prevalence of chronic mental and physical conditions that necessitate frequent healthcare visits, but travel burdens to specialty services may be overwhelming to navigate for this population, especially for those in rural settings. Access to specialty care is a key priority in the Veterans Health Administration (VHA) and understanding the geographic distribution and rural designation of this population in relation to medical centers (VAMC) can assist in care coordination. We identified 41,747 women Veterans age 18-44y with administrative evidence of homelessness in the VHA anytime during 2002-2015. We found 7% live in rural settings and 29% live >40miles from a VAMC. The mean travel distance for homeless women Veterans with a rural designation to a VAMC specialty center was 107 miles. Developing interventions to overcome this travel burden and engage vulnerable Veterans in necessary care can improve overall health outcomes for this high-risk population.

Comparison of Grouping Methods for Template Extraction from VA Medical Record Text.

We investigate options for grouping templates for the purpose of template identification and extraction from electronic medical records. We sampled a corpus of 1000 documents originating from Veterans Health Administration (VA) electronic medical record. We grouped documents through hashing and binning tokens (Hashed) as well as by the top 5% of tokens identified as important through the term frequency inverse document frequency metric (TF-IDF). We then compared the approaches on the number of groups with 3 or more and the resulting longest common subsequences (LCSs) common to all documents in the group. We found that the Hashed method had a higher success rate for finding LCSs, and longer LCSs than the TF-IDF method, however the TF-IDF approach found more groups than the Hashed and subsequently more long sequences, however the average length of LCSs were lower. In conclusion, each algorithm appears to have areas where it appears to be superior.

A pilot study of a heuristic algorithm for novel template identification from VA electronic medical record text.

RATIONALE: Templates in text notes pose challenges for automated information extraction algorithms. We propose a method that identifies novel templates in plain text medical notes. The identification can then be used to either include or exclude templates when processing notes for information extraction. METHODS: The two-module method is based on the framework of information foraging and addresses the hypothesis that documents containing templates and the templates within those documents can be identified by common features. The first module takes documents from the corpus and groups those with common templates. This is accomplished through a binned word count hierarchical clustering algorithm. The second module extracts the templates. It uses the groupings and performs a longest common subsequence (LCS) algorithm to obtain the constituent parts of the templates. The method was developed and tested on a random document corpus of 750 notes derived from a large database of US Department of Veterans Affairs (VA) electronic medical notes. RESULTS: The grouping module, using hierarchical clustering, identified 23 groups with 3 documents or more, consisting of 120 documents from the 750 documents in our test corpus. Of these, 18 groups had at least one common template that was present in all documents in the group for a positive predictive value of 78%. The LCS extraction module performed with 100% positive predictive value, 94% sensitivity, and 83% negative predictive value. The human review determined that in 4 groups the template covered the entire document, with the remaining 14 groups containing a common section template. Among documents with templates, the number of templates per document ranged from 1 to 14. The mean and median number of templates per group was 5.9 and 5, respectively. DISCUSSION: The grouping method was successful in finding like documents containing templates. Of the groups of documents containing templates, the LCS module was successful in deciphering text belonging to the template and text that was extraneous. Major obstacles to improved performance included documents composed of multiple templates, templates that included other templates embedded within them, and variants of templates. We demonstrate proof of concept of the grouping and extraction method of identifying templates in electronic medical records in this pilot study and propose methods to improve performance and scaling up.