Building a neuropsychiatric testing database for veterans with mild cognitive impairment and Alzheimer’s disease with unstructured electronic health records
Bibliographic record
Abstract
Abstract Background Information on clinical decision making and disease severity assessments for mild cognitive impairment (MCI) or Alzheimer’s dementia (AD) typically only exists in medical notes. In this study, we present the methodology of constructing a database from unstructured electronic health records (EHR), which enables enriched population studies when combined with structured administrative databases. Method A multidisciplinary team with expertise in neurology, epidemiology, biology, and health informatics designed and created the relational database. The database was established with three tables for patient demographics, neurocognitive and neuropsychiatric test results, and clinical judgment of AD severity. Patient cohorts were identified by searching keywords ("Alz*” or “Mild Cognitive Impairment”) from electronic clinical notes and excluding false positives using expert‐designed rules. The most frequently used six neuropsychiatric tests (MMSE, MoCA, SLUMS, Mini‐cog, BNT, BVRT) and their corresponding testing results were extracted in addition to clinicians’ judgment on disease severity. The test scores were extracted using a rule‐based natural language processing (NLP) system. Result A patient cohort with MCI (N = 74,444) or probable AD (N = 141,816) was identified in the VA database for the fiscal year of 2019 (Table 1), with 18,173 patients having both MCI and AD diagnosis among their clinical notes of the year. A total of 1,529,897 neuropsychiatric testing scores were extracted from the patients’ clinical notes across all years, with 388,253 MMSE scores, 614,400 MoCA scores, 462,646 SLUMS scores, 18,868 Mini‐cog scores, 45,259 BNT scores, and 471 BVRT scores. A total of 57,879 (77.75%) MCI patients and 82,656 (58.28%) AD patients had at least one test score extracted. A total of 18,939 (13.35%) AD patients had at least one documented severity categorization made by a clinician. Conclusion We established a database of neuropsychiatric testing scores for patients with MCI or AD based on electronic medical notes from the VA healthcare system, aided by NLP tools. Our approach demonstrated a scalable pipeline to integrate with structured EHR in support of enriched population level analysis in AD.
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 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.009 | 0.007 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".