Structured Data Capture from Multiple EMRs: Towards an Architecture for Clinical Research
Bibliographic record
Abstract
EMR adoption by primary care physicians in Canada has increased dramatically in recent years. This provides an excellent opportunity for researchers to collaborate with primary care providers to capture structured data at the point of care. This paper describes the feasibility of converting a popular well-baby checklist form into an electronic version for research data collection. Usability and scalability of the instrument to large numbers of physicians was assessed. We developed and tested a standardized, electronic version of the Rourke Baby Record (eRourke) that was embedded into two different EMRs at four primary care clinics in Southern Ontario over a 6-month period. We utilized qualitative and quantitative research techniques, including on-site observation, key informant interviews and administration of pre- and post-questionnaires. Implementation of the eRourke improved the quality of data for research and reporting significantly. Providers also reported a subjective sense of having collected better quality data. Enhancing the usability of the form in 3 specific areas would likely increase the receptivity to the form to larger numbers of providers. Overall, providers were satisfied with the eRourke and felt that it captured higher quality information than previous versions (55% Agree before vs 88% Agree after).
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 | 0.488 | 0.393 |
| Meta-epidemiology (narrow) | 0.002 | 0.004 |
| Meta-epidemiology (broad) | 0.004 | 0.003 |
| Bibliometrics | 0.016 | 0.017 |
| Science and technology studies | 0.004 | 0.010 |
| Scholarly communication | 0.022 | 0.023 |
| Open science | 0.009 | 0.019 |
| Research integrity | 0.004 | 0.007 |
| Insufficient payload (model declined to judge) | 0.002 | 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".