Extracting Cognitive SLUMS Scores from Unstructured National Veterans Clinical Notes with AI
Bibliographic record
Abstract
Abstract Clinical assessment of cognitive status is critical to evaluating patient health risk and outcomes yet rarely found within the structured data in the electronic health record (EHR). The Saint Louis University Mental Status (SLUMS) Examination is a cognitive screening tool widely used within the Veterans Affairs (VA). Compared to the Mini-Mental State Examination (MMSE), the SLUMS score has greater sensitivity to earlier stages of cognitive impairment. We present a natural language processing (NLP) method for extracting SLUMS scores from unstructured EHR notes. We identified clinical notes from VA patients that contained the word “SLUMS” and a number within a 500 character window. Two researchers independently annotated 1,275 notes. Of these, 899 contained a single SLUMS score and 376 contained missing, multiple, invalid (typo), or qualitative scores. We developed a rule-based system incorporating regular–expression–based pattern matching. The algorithm was developed on the full set of notes and optimized for precision over recall (i.e., only makes predictions when confident). It achieved 83.0% accuracy and 99.6% precision with an F1 score of 78.2%. We further ran the algorithm on 2.96 million unannotated notes. The algorithm throughput exceeded 20 thousand notes per minute when run on a single laptop processor. This work demonstrates how NLP can extract SLUMS scores with high accuracy at scale from millions of unstructured clinical notes. By creating structured cognitive assessment data from information previously buried in free-form clinical text, our work enables cognitive impairment research at the population scale.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".