A comparison of measures for identifying possible dementia in Veterans Affairs nursing home residents

Abstract: Objectives: Identifying people with possible dementia in health care systems is important to study outcomes and target improvements in care. This study sought to compare the performance of diagnostic codes and Minimum Data Set (MDS)-based measures for identifying dementia and cognitive impairment in older veteran nursing home residents. Design: Retrospective, cross-sectional analysis. Setting and Participants: We used real-world health care data from the Veterans Affairs (VA) Residential History File, VA Corporate Data Warehouse (CDW), Medicare claims, and the MDS to assemble a cohort of VA Community Living Center (CLC) admissions over 2015 to 2021 for veterans aged ≥ 65 with dual VA and Medicare enrollment (n = 54,234). Methods: We defined 3 measures of possible dementia: (1) claims/CDW diagnoses using Chronic Conditions Warehouse (CCW) algorithms for Alzheimer’s disease or non-Alzheimer’s dementia; (2) MDS active diagnosis items for Alzheimer’s disease and non-Alzheimer’s dementia; and (3) MDS Cognitive Function Scale (CFS) assessment indicating at least mild cognitive impairment. We calculated proportions identified with each definition, and sensitivity, specificity, and positive predictive value of claims/CDW diagnoses and MDS indicators for dementia for identifying CFS impairment. Results: Among VA CLC residents, 61.4% met at least 1 criterion for possible dementia (38.6% claims/CDW, 23.3% MDS active diagnosis, 50.8% CFS). Diagnoses from claims/CDW had 56.5% sensitivity and 80.0% specificity for identifying veterans with CFS cognitive impairment. Active diagnoses from the MDS exhibited poorer sensitivity (38.1%), but higher specificity (92.0%) identifying veterans with cognitive impairment on the CFS. Conclusions and Implications: Consistent with what has been reported in Medicare nursing home residents, we observed only partial overlap between indicators of possible dementia across diagnosis codes and other indicators vs cognitive assessments in MDS. Our findings support the utility of these measures for identifying individuals with possible dementia across different systems, but further work is needed to understand implications when using diagnosis codes or cognitive assessments.

Read the full article
Report a problem with this article

Related articles

  • More for Researchers

    Identifying opioid relapse during COVID-19 using natural language processing of nationwide Veterans Health Administration electronic medical record data

    Abstract: Novel and automated means of opioid use and relapse risk detection are needed. Unstructured electronic medical record data, including written progress notes, can be mined for clinically relevant information, including the presence of substance use and relapse-critical markers of risk and recovery from opioid use disorder (OUD). In this study, we used natural language processing (NLP) to automate the extraction of opioid relapses, and the timing of these occurrences, from veteran patients' electronic medical record. We then demonstrated the utility of our NLP tool via analysis of pre-/post-COVID-19 opioid relapse trends among veterans with OUD. For this demonstration, we analyzed data from 107,606 veterans OUD enrolled in Veterans Health Administration, comparing a pandemic-exposed cohort (n = 53,803; January 2019-March 2021) to a matched prepandemic cohort (n = 53,803; October 2017-December 2019). The recall of our NLP tool was 75% and our precision was 94%, demonstrating moderate sensitivity and excellent specificity. Using the NLP tool, we found that the odds of opioid relapse postpandemic onset were proportionally higher compared to prepandemic trends, despite patients having fewer mental health encounters from which to derive instances of relapse postpandemic onset. In this research application of the tool, and as hypothesized, we found that opioid relapse risk was elevated postpandemic. The application of NLP Methods: to identify and monitor relapse risk holds promise for future surveillance, risk prevention, and clinical outcome research.

    Mental Health Peer reviewed