Identifying individuals with physician-diagnosed chronic obstructive pulmonary disease in primary care electronic medical records: a retrospective chart abstraction study
Bibliographic record
Abstract
) housed at the Institute for Clinical Evaluative Sciences. Abstracted charts provided the reference standard based on available physician-diagnoses, chronic obstructive pulmonary disease-specific medications, smoking history and pulmonary function testing. Chronic obstructive pulmonary disease electronic medical record algorithms using combinations of terminology in the cumulative patient profile (CPP; problem list/past medical history), physician billing codes (chronic bronchitis/emphysema/other chronic obstructive pulmonary disease), and prescriptions, were tested against the reference standard. Sensitivity, specificity, and positive/negative predictive values (PPV/NPV) were calculated. There were 364 patients with chronic obstructive pulmonary disease identified in a 5889 randomly sampled cohort aged ≥ 35 years (prevalence = 6.2%). The electronic medical record algorithm consisting of ≥ 3 physician billing codes for chronic obstructive pulmonary disease per year; documentation in the CPP; tiotropium prescription; or ipratropium (or its formulations) prescription and a chronic obstructive pulmonary disease billing code had sensitivity of 76.9% (95% CI:72.2-81.2), specificity of 99.7% (99.5-99.8), PPV of 93.6% (90.3-96.1), and NPV of 98.5% (98.1-98.8). Electronic medical record algorithms can accurately identify patients with chronic obstructive pulmonary disease in primary care records. They can be used to enable further studies in practice patterns and chronic obstructive pulmonary disease management in primary care. CHRONIC LUNG DISEASE: NOVEL ALGORITHM SEARCH TECHNIQUE: Researchers develop an algorithm that can accurately search through electronic health records to find patients with chronic lung disease. Mining population-wide data for information on patients diagnosed and treated with chronic obstructive pulmonary disease (COPD) in primary care could help inform future healthcare and spending practices. Theresa Lee at the University of Toronto, Canada, and colleagues used an algorithm to search electronic medical records and identify patients with COPD from doctors' notes, prescriptions and symptom histories. They carefully adjusted the algorithm to improve sensitivity and predictive value by adding details such as specific medications, physician codes related to COPD, and different combinations of terminology in doctors' notes. The team accurately identified 364 patients with COPD in a randomly-selected cohort of 5889 people. Their results suggest opportunities for broader, informative studies of COPD in wider populations.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| 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".