Potential Pitfalls of Reporting and Bias in Observational Studies With Propensity Score Analysis Assessing a Surgical Procedure
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
OBJECTIVE: To describe the evolution of the use and reporting of propensity score (PS) analysis in observational studies assessing a surgical procedure. BACKGROUND: Assessing surgery in randomized controlled trials raises several challenges. Observational studies with PS analysis are a robust alternative for comparative effectiveness research. METHODS: In this methodological systematic review, we identified all PubMed reports of observational studies with PS analysis that evaluated a surgical procedure and described the evolution of their use over time. Then, we selected a sample of articles published from August 2013 to July 2014 and systematically appraised the quality of reporting and potential bias of the PS analysis used. RESULTS: We selected 652 reports of observational studies with PS analysis. The publications increased over time, from 1 report in 1987 to 198 in 2013. Among the 129 reports assessed, 20% (n = 24) did not detail the covariates included in the PS and 77% (n = 100) did not report a justification for including these covariates in the PS. The rate of missing data for potential covariates was reported in 9% of articles. When a crossover by conversion was possible, only 14% of reports (n = 12) mentioned this issue. For matched analysis, 10% of articles reported all 4 key elements that allow for reproducibility of a PS-matched analysis (matching ratio, method to choose the nearest neighbors, replacement and method for statistical analysis). CONCLUSIONS: Observational studies with PS analysis in surgery are increasing in frequency, but specific methodological issues and weaknesses in reporting exist.
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.
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 | 0.004 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.004 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 it