The methodological quality of 176,620 randomized controlled trials published between 1966 and 2018 reveals a positive trend but also an urgent need for improvement
Bibliographic record
Abstract
Many randomized controlled trials (RCTs) are biased and difficult to reproduce due to methodological flaws and poor reporting. There is increasing attention for responsible research practices and implementation of reporting guidelines, but whether these efforts have improved the methodological quality of RCTs (e.g., lower risk of bias) is unknown. We, therefore, mapped risk-of-bias trends over time in RCT publications in relation to journal and author characteristics. Meta-information of 176,620 RCTs published between 1966 and 2018 was extracted. The risk-of-bias probability (random sequence generation, allocation concealment, blinding of patients/personnel, and blinding of outcome assessment) was assessed using a risk-of-bias machine learning tool. This tool was simultaneously validated using 63,327 human risk-of-bias assessments obtained from 17,394 RCTs evaluated in the Cochrane Database of Systematic Reviews (CDSR). Moreover, RCT registration and CONSORT Statement reporting were assessed using automated searches. Publication characteristics included the number of authors, journal impact factor (JIF), and medical discipline. The annual number of published RCTs substantially increased over 4 decades, accompanied by increases in authors (5.2 to 7.8) and institutions (2.9 to 4.8). The risk of bias remained present in most RCTs but decreased over time for allocation concealment (63% to 51%), random sequence generation (57% to 36%), and blinding of outcome assessment (58% to 52%). Trial registration (37% to 47%) and the use of the CONSORT Statement (1% to 20%) also rapidly increased. In journals with a higher impact factor (>10), the risk of bias was consistently lower with higher levels of RCT registration and the use of the CONSORT Statement. Automated risk-of-bias predictions had accuracies above 70% for allocation concealment (70.7%), random sequence generation (72.1%), and blinding of patients/personnel (79.8%), but not for blinding of outcome assessment (62.7%). In conclusion, the likelihood of bias in RCTs has generally decreased over the last decades. This optimistic trend may be driven by increased knowledge augmented by mandatory trial registration and more stringent reporting guidelines and journal requirements. Nevertheless, relatively high probabilities of bias remain, particularly in journals with lower impact factors. This emphasizes that further improvement of RCT registration, conduct, and reporting is still urgently needed.
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 | 0.269 | 0.596 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.008 | 0.012 |
| Bibliometrics | 0.037 | 0.039 |
| Science and technology studies | 0.002 | 0.004 |
| Scholarly communication | 0.007 | 0.006 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
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".