A Proof of Concept for Assessing Emergency Room Use with Primary Care Data and Natural Language Processing
Bibliographic record
Abstract
OBJECTIVE: The objective of this study was to undertake a proof of concept that demonstrated the use of primary care data and natural language processing and term extraction to assess emergency room use. The study extracted biopsychosocial concepts from primary care free text and related them to inappropriate emergency room use through the use of odds ratios. METHODS: De-identified free text notes were extracted from a primary care clinic in Guelph, Ontario and analyzed with a software toolkit that incorporated General Architecture for Text Engineering (GATE) and MetaMap components for natural language processing and term extraction. RESULTS: Over 10 million concepts were extracted from 13,836 patient records. Codes found in at least 1% percent of the sample were regressed against inappropriate emergency room use. 77 codes fell within the realm of biopsychosocial, were very statistically significant (p < 0.001) and had an OR > 2.0. Thematically, these codes involved mental health and pain related concepts. CONCLUSIONS: Analyzed thematically, mental health issues and pain are important themes; we have concluded that pain and mental health problems are primary drivers for inappropriate emergency room use. Age and sex were not significant. This proof of concept demonstrates the feasibly of combining natural language processing and primary care data to analyze a system use question. As a first work it supports further research and could be applied to investigate other, more complex problems.
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 | 0.061 | 0.177 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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".