External Control Arm with Synthetic Real-world Data for Comparative Oncology using Single Trial Arm Evidence (ECLIPSE): A Case Study using Lung-MAP S1400I
Bibliographic record
Abstract
2. Abstract Single-arm trials supplemented with external comparator arm(s) (ECA) derived from real-world data are sometimes used when randomized trials are infeasible. However, due to data sharing restrictions, privacy/security concerns, or for logistical reasons, patient-level real-world data may not be available to researchers for analysis. Instead, it may be possible to use generative models to construct synthetic data from the real-world dataset that can then be freely shared with researchers. Although the use of generative models and synthetic data is gaining prominence, the extent to which a synthetic data ECA can replace original data while preserving patient privacy in small samples is unclear. Objective To compare the efficacy of nivolumab + ipilimumab combination therapy (“experimental arm”) versus nivolumab monotherapy (“control arm”) in patients with metastatic non-small cell lung cancer (mNSCLC) using real-world data from two real-world databases (“original ECA”), and synthetic data versions of these datasets (“synthetic ECA”), with the aim of validating synthetic data for use in ECA analysis. Study design Non-randomized analyses of treatment efficacy comparing the experimental arm to the (i) original ECA and (ii) synthetic ECA, with baseline confounding adjustment. Data sources The experimental arm is from the Lung-MAP no-match substudy S1400I ( NCT02785952 ) provided by National Clinical Trials Network (NCTN) in the United States. The real-world data source for the ECA is data from population-based oncology data from the Canadian province of Alberta, and from Nordic countries in Europe, specifically Denmark and Norway.
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 | 0.223 | 0.449 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.008 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.005 | 0.003 |
| Insufficient payload (model declined to judge) | 0.013 | 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; 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".