Rule-Based Identification of Individuals with Mild Cognitive Impairment or Alzheimer’s Disease Using Clinical Notes from the United States Veterans Affairs Healthcare System
Bibliographic record
Abstract
BACKGROUND: Early identification of individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD) is a clinical and research imperative. Use of diagnostic codes for MCI and AD identification has limitations. We used clinical notes to supplement diagnostic codes in the Veterans Affairs Healthcare System (VAHS) electronic health records (EHR) to identify and establish cohorts of Veterans recorded with MCI or AD. METHODS: Targeted keyword searches for MCI ("Mild cognitive impairment;" "MCI") and AD ("Alz*") were used to extract clinical notes from the VAHS EHR from fiscal year (FY) 2010 through FY 2019. Iterative steps of inclusion and exclusion were applied until searches achieved a positive predictive value ≥ 80%. MCI and AD cohorts were identified via clinical notes and/or diagnostic codes (i.e., including Veterans recorded by "Notes Only," "Notes + Code," or "Codes Only"). RESULTS: A total of 2,134,661 clinical notes from 339,007 Veterans met the iterative search criteria for MCI due to any cause and 4,231,933 notes from 572,063 Veterans met the iterative search criteria for AD. Over the 10-year study period, the number of clinical notes recording AD was generally stable, whereas the number for MCI more than doubled. More Veterans were identified for the MCI or AD cohorts via clinical notes than by diagnostic codes, particularly in the AD cohort. Among Veterans identified by having "Notes + Code" for MCI, the number first recorded by a code was lower than the number first recorded by a note until FY 2015 and then gradually became comparable after FY 2015. Among Veterans identified by having "Notes + Code" for AD, the number first recorded by a note was more than double the number first recorded by a code AD in each of the FYs. CONCLUSIONS: Clinical note-based identification captured more Veterans recorded with MCI and AD than diagnostic code-based identification.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.052 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.010 | 0.005 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.003 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".