Statistical Methods for Analyzing EQ-5D in Randomized Clinical Trials: A Systematic Literature Review
Bibliographic record
Abstract
OBJECTIVES: We conducted a systematic literature review to summarize the application of statistical methods for analyzing treatment effect on EQ-5D in randomized clinical trials (RCTs). METHOD: We searched 2 electronic databases (MEDLINE and EMBASE, from inception through 2021) and www. CLINICALTRIAL: gov. Eligible studies were RCTs that analyzed postbaseline EQ-5D data by treatment group. Information on trial characteristics, EQ-5D data characteristics, and statistical methods were extracted. Descriptive statistics were used to summarize results by dimension response, EQ visual analog scale (EQ VAS), and EQ-5D utility. RESULTS: A total of 2125 trials met the eligibility criteria. EQ-5D was commonly considered a secondary (n = 1219, 57.4%) or exploratory (n = 775, 36.5%) endpoint in RCTs. EQ-5D utilities were the most analyzed. Both utilities and EQ VAS were primarily analyzed in numerical format. The most common statistical models for analyzing utilities were the linear fixed-effect model for single postbaseline (192/589, 32.6%) and the linear mixed-effect model for multiple post-baselines (338/984, 34.3%). Of the 2054 studies that analyzed numerical EQ-5D, 221 (10.8%) examined model assumptions and 438 (21.3%) adjusted for the baseline score. Missing data were explicitly assessed in 661 trials, among which 347 (52.5% of 661) applied imputations, with the 2 most used imputation methods being multiple imputations (n = 200, 57.6% of 347) and last observation carried forward (n = 106, 30.5% of 347). CONCLUSIONS: This review found that health utilities are the most frequently analyzed EQ-5D data collected in clinical trials, followed by EQ VAS. Significant variation was observed in the selection of models, with most trials lacking adjustments for baseline data and appropriate methods for handling missing data.
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 | 0.104 | 0.281 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.024 | 0.020 |
| Bibliometrics | 0.012 | 0.011 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.006 | 0.004 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.004 | 0.004 |
| 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; 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".