Pan-Canadian Respiratory Standards Initiative for Electronic Health Records (PRESTINE): Validation of a Severe Asthma Algorithm
Bibliographic record
Abstract
Background: Integration of knowledge translation tools into electronic medical records (EMRs) may facilitate evidence-based clinical care and improve patient outcomes. Objective: To determine the accuracy of an electronic algorithm to identify severe asthma (SA) patients in an EMR using Pan-Canadian Respiratory Standards Initiative for Electronic Health Records (PRESTINE) data elements. Methods: An electronic algorithm was programmed based on the Canadian Thoracic Society (CTS)’s definition of SA (Can J Respir Crit Care Sleep Med 2017) and applied to 150 patient charts from a tertiary care electronic asthma EMR. Clinical experts blinded to the algorithm result also classified each chart as SA or “else” (e.g. suspected or non-severe asthma, or COPD). Accuracy of the algorithm was assessed by % agreement and Cohen’s kappa statistic. Results: Nine charts were excluded because medications documented as free text could not be read by the algorithm. Of 141 patients (age 49.7 ± 23.7 years [mean ± SD]; 68% female; 13% pediatric), 20 charts were classified as SA, and 116 charts were classified as “else” by both the algorithm and clinicians (96.5% agreement; Cohen’s kappa=0.87 (95% CI: 0.78-1.04)). Five discordant charts were determined to be clinician error. The algorithm was correct; 3 met criteria for SA. Conclusion: The SA algorithm accurately identified SA patients according to the CTS definition, using PRESTINE asthma EMR elements. Use of free text for critical information limits the accuracy of the algorithm and should be discouraged. Next steps are to program decision support prompts and evaluate the impact of the algorithm on patient care and outcomes.
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 | 0.071 | 0.147 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.003 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".