Concordance and discordance in disease severity classification between clinician judgments and cognitive testing scores for Alzheimer’s disease in the United States Veterans Affairs Healthcare System

Abstract

AbstractBackgroundThe current standard of practice for assessment of Alzheimer’s disease (AD) severity in the Department of Veterans Affairs (VA) Healthcare System is primarily based on clinical examination and cognitive testing. We aimed to assess the consistency between clinician judgements of AD severity compared with that classified by cognitive test scores in the VA system.MethodWe identified medical notes for patients with mild, moderate, or severe AD from the VA electronic healthcare records (EHR) database between March 2008 and October 2021, using the natural language processing technology. Mini‐Mental Status Exam (MMSE) and Montreal Cognitive Assessment (MoCA) scores from the corresponding medical notes with physician judgments were classified and used for comparisons of severity levels. A binary variable was coded to indicate concordance or discordance for each paired comparison.ResultWe screened clinical notes from 51,809 AD patients and analyzed 8,888 clinical notes that had either an MMSE or MoCA test score from 5,150 AD patients (3.5% female; average age at 78.1±9.4 years). Clinician judgements and test‐score‐based classification of AD severity were concordant in 53.2% of comparisons (weighted Kappa = 0.39, 95% CI:0.38‐0.41, p = 0.009); whereas clinician judgments were less severe in 25.7% and more severe in 21.1% comparisons, relative to the test‐score‐based severity level. Clinician judgments were concordant with 54.1%, 51.8%, and 53.0% cognitive test‐score‐based classifications, of mild, moderate, and severe AD, respectively. Concordance was observed in 55.9% clinician judgments involving internist, 53.0% involving psychiatrist or neurologist, and 51.7% involving psychologist specialties, and in 50.4% involving nurse practitioners. Among discordant severity classifications, clinician judgments tended to be less severe than test scores (Figure).ConclusionExamination of VA EHR reveals that nearly one half of clinician judgments of AD severity are discordant with severity classification based on the MMSE or MoCA test scores. Discordance is more pronounced in the moderate relative to mild and severe AD categories but does not vary substantially over clinicians’ specialty background. Research will aim to find plausible explanations for the variation of concordance vs discordance by further examining the relative contributions of patient, clinician, and system characteristics in the process of AD clinical assessments.