Identification of Alzheimer’s disease in Veteran patients using clinical notes from electronic health records
Bibliographic record
Abstract
Abstract Background There are challenges in studying and monitoring Alzheimer’s disease (AD) in large patient populations. Clinicians often have insufficient availability of resources to make the diagnosis (e.g. brain scanning, referral to specialists) and clinical inertia may be tied to the perception that there are no clinical benefits in making the differential diagnosis of this stigmatized disease. Consequently, diagnosis codes specifically for AD are underutilized and prevalence is generally underestimated. Our goal was to improve identification of probable AD in a large patient population with the development and application of a refined search algorithm of computerized clinical notes contained in electronic health records. Method Our methods were developed using records for all Veteran patients in the national Department of Veterans Affairs Healthcare System (VA) in fiscal years 2010‐2019. Starting with initial searches for “Alzheimer” and related terms in all clinical notes, the algorithm was optimized through an iterative process. Multiple references to “Alz” in notes were evaluated separately and chunks were excluded when the term referred to family history, care facilities, or negative statements, or when it was part of text in assessment instruments or medication indications. The final algorithm was validated through manual reviews of over 2,400 randomly selected patient charts (predictive value positive = 86.3%; kappa = 0.76 among 2‐4 reviewers). Result When the algorithm was applied to records for the nearly 5 million VA patients over 50 years of age in fiscal year (FY) 2019, we identified 141,816 with probable AD, nearly five times the count based on ICD‐10 codes (30,090). Prevalence, standardized to the 2010 census for age and sex, was 2.70%, with higher prevalence in women (3.26%) than in men (2.06%). Median age of probable AD patients was 75 years. Conclusion As disease modifying treatments for AD enter the market, there will be more focus on proper diagnosis of AD, particularly early in the disease process, emphasizing the importance of better identification of the disease in patient populations. This method, based on searches of clinical notes, appears to be promising to identify patients with probable AD and study its progression in large patient populations.
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 | 0.041 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.009 | 0.005 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".