Extreme restriction design as a method for reducing confounding by indication in pharmacoepidemiologic research
Bibliographic record
Abstract
PURPOSE: Confounding by indication is a concern in observational pharmacoepidemiologic studies, including those that use active comparator, new user (ACNU) designs. Here, we present a method of restriction to an indication, which we call "extreme restriction," to reduce confounding in such studies. METHODS: As a case study, we evaluated the effect of proton pump inhibitors (PPIs) on hospitalization for community-acquired pneumonia (HCAP). PPI use has been associated with increased HCAP risk, but this association likely results from confounding by indication due to gastroesophageal reflux disease (GERD). Using the UK's Clinical Practice Research Datalink, we compared the risk of HCAP within 180 days between PPI users and histamine-2 receptor antagonist (H2RA) users in an ACNU cohort using Cox proportional hazard models with a time-fixed exposure definition adjusted for high-dimensional propensity score deciles. We then performed the same analysis on an "extremely-restricted" cohort of incident nonsteroidal anti-inflammatory drug (NSAID) users, some of whom received PPIs for prophylaxis. Because PPIs were given as prophylaxis in this population, confounding due to GERD should be limited. We compared effect estimates between ACNU and restricted cohorts to evaluate confounding in both analyses. RESULTS: In the ACNU cohort, PPIs were associated with an increased risk of HCAP (hazard ratio [HR]: 1.25; 95% confidence interval [CI]: 1.05, 1.47), but this association was not present in the restricted cohort (HR: 1.06; 95% CI: 0.75, 1.49). CONCLUSIONS: Restriction to a single indication for treatment may reduce confounding by indication in studies conducted in distributed data networks and other large databases.
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 | 0.339 | 0.407 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.005 | 0.008 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.002 | 0.007 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.004 | 0.006 |
| Research integrity | 0.007 | 0.007 |
| Insufficient payload (model declined to judge) | 0.008 | 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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
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".