Immortal time bias in observational studies of drug effects in pregnancy
Bibliographic record
Abstract
BACKGROUND: The use of decongestants during the second or third trimesters of pregnancy has been associated with a decreased risk of preterm delivery in two observational studies. This effect may have been subject to immortal time bias, a bias arising from the improper classification of exposure during follow-up. We illustrate this bias by repeating the studies using a different data source. METHODS: The United Kingdom Hospital Episodes Statistics and the Clinical Practice Research Datalink databases were linked to identify all live singleton pregnancies among women aged 15 to 45 years between 1997 and 2012. Cox proportional hazards models were used to estimate hazard ratios (HRs) and 95% confidence intervals of preterm delivery (before 37 weeks of gestation) by considering the use of decongestants during the third trimester as a time-fixed (biased analysis which misclassifies unexposed person-time as exposed person-time) and time-varying exposure (unbiased analysis with proper classification of unexposed person-time). All models were adjusted for maternal age, smoking status, maternal diabetes, maternal hypertension, preeclampsia, and parity. RESULTS: Of the 195,582 singleton deliveries, 10,248 (5.2%) were born preterm. In the time-fixed analysis, the HR of preterm delivery for the use of decongestants was below the null and suggestive of a 46% decreased risk (adjusted HR = 0.54; 95% confidence interval, 0.24-1.20). In contrast, the HR was closer to null (adjusted HR = 0.93 95% confidence interval, 0.42-2.06) when the use of decongestants was treated as a time-varying variable. CONCLUSION: Studies of drug safety in pregnancy should use the appropriate statistical techniques to avoid immortal time bias, particularly when the exposure occurs at later stages of pregnancy.
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 | 0.173 | 0.397 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.004 |
| Bibliometrics | 0.003 | 0.005 |
| Science and technology studies | 0.002 | 0.004 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 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".