Speaking the same language? International variations in the safety information accompanying top-selling prescription drugs
Bibliographic record
Abstract
BACKGROUND: The official prescribing information document distributed with a prescription drug is a key source of safety information, but it may include excessive or insufficient details. OBJECTIVES: To compare prescribing information approved by the US Food and Drug Administration with the UK, Canada and Australia to identify content differences in safety warnings. METHODS: For 20 top-selling prescription drugs, we used an automated natural language processing tool to calculate the number and severity of reported adverse drug reactions (ADRs). We fit hierarchical Poisson models and included fixed effects for other prescribing information characteristics. Separately, we analysed the appearance and content of 'black box' warnings. RESULTS: There was substantial variation in safety content of approved prescribing information. Canada had the highest median ADRs per drug (138 (IQR 86-234)) and the UK had the lowest (84 (IQR 51-111)). The number of ADRs reported was on average 50% higher in Canada compared with the USA (ratio of ADRs/document: 1.5, 95% CI 1.4 to 1.6, p<0.001). By contrast, there were on average 15% fewer ADRs listed in the UK compared with the USA (ratio of ADRs/document 0.85 (95% CI 0.78 to 0.93, p<0.001), and 21% fewer ADRs listed in Australia compared with the USS (ratio of ADRs/document 0.79, 95% CI 0.74 to 0.85, p<0.001). There were no variations in ADR severity. The presence and qualitative content of boxed warnings also showed substantial diversity. CONCLUSIONS: International variations exist in the presentation of safety data in drug prescribing information, which may have important implications for patient safety. Better international coordination is necessary to enhance use of this information for patient decision-making.
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 | 0.006 | 0.031 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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 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".