Projecting effectiveness after ending a randomized controlled trial: a two-state Markov microsimulation model
Bibliographic record
Abstract
OBJECTIVE: To investigate the behavior of restricted mean survival time (RMST) and designs of a two-state Markov microsimulation model through a 2 × 4 × 2 full factorial experiment. METHOD: By projecting patient-wise 15-year-post-trial survival, we estimated life-year-gained between an intervention and a control group using data from the Cardiovascular Outcomes for People Using Anticoagulation Strategies Study (COMPASS). Projections considered either in-trial events or post-trial medications. They were compared based on three factors: (i) choice of probability of death, (ii) lengths of cycle, and (iii) usage of half-a-cycle age correction. Three-way analysis of variance and post-hoc Tukey's Honest Significant Difference test compared means among factors. RESULTS: When both in-trial events and post-trial study medications were considered, monthly, quarterly, or semiannually were not different from one other in projected life-year-gained. However, the annual one was different from the others: mean and 95 percent confidence interval 252.2 (190.5-313.9) days monthly, 251.8 (192.0-311.6) quarterly, 249.1 (189.7-308.5) semiannually, and 240.8 (178.5-303.1) annually. The other two factors also impacted life-year-gained: background probability (269.1 [260.3-277.9] days projected with REACH-based-probabilities, 227.7 [212.6-242.8] with a USA life table); half-a-cycle age correction (245.5 [199.0-292] with correction and 251.4 [209.1-293.7] without correction). When not considering post-trial medications, only the choice of probability of death appeared to impact life-year-gained. CONCLUSION: For a large trial or cohort, to optimally project life-year-gained, one should consider using (i) annual projections, (ii) life table probabilities, (iii) in-trial events, and (iv) post-trial medication use.
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 | 0.061 | 0.081 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.006 | 0.004 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.009 | 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".