Application of Targeted Maximum Likelihood Estimation using Varying Lookback Windows in Pharmacoepidemiology
Bibliographic record
Abstract
In observational research, confounding control is critical to appropriate inference.In the field of pharmacoepidemiology, determining the appropriate lookback period is essential as it dictates how far back we examine potential confounding factors from the time of exposure.This study aims to compare treatment effect estimates using two different approaches: targeted maximum likelihood estimation (TMLE) and propensity score method under inverse probability weighting approach (PS-IPW), considering varying lookback periods (short term and long term).To conduct the comparison, simulation settings were established, considering eight different lookback periods (1,3,6 months, and 1,2,5,7,9 years), with 10 years as the ideal reference lookback period.We applied two different approaches: PS-IPW and TMLElogistic, both within the logistic regression framework.Additionally, we included TMLE using SuperLearner (TMLE-SL) as part of our simulation.To assess the effect of lookback on propensity score models, propensity score quantile estimates were computed, revealing that longer lookback periods exhibited less bias compared to shorter ones.Subsequently, the average treatment effect (ATE) along with standard error was estimated using PS-IPW, TMLE-logistic, and TMLE-SL.It was observed that TMLE-logistic and TMLE-SL produced lower standard errors than the PS-IPW approach across the varying lookback periods.Finally, the study applied both methods to the CPRD (Clinical Practice Research Datalink) database to evaluate how TMLE and PS-IPW perform in real-life scenarios for each of the specified lookback periods.In conclusion, this research contributes valuable insights into the impact of lookback periods on treatment effect estimates, highlighting the advantages of using TMLE approaches over PS-IPW in certain lookback scenarios.Furthermore, the application of these methods to real-world data from CPRD aids in understanding their performance in practical healthcare research settings.
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 | 0.042 | 0.128 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 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".