How reproducible are real-world research utilizing scientific apply information? – Healthcare Economist

That’s the query posed by a paper by Wang, Sreedhara and Schneeweiss (2022). The authors replicate the findings from n=250 real-world information research. The research had been replicated utilizing 3 datasets: (i) Optum Clinformatics claims information, (ii) IBM MarketScan Analysis Database claims information, Medicare fee-for-service claims information, and (iii) CPRD digital well being data. Key paper findings are under:

Unique and copy impact sizes had been positively correlated (Pearson’s correlation = 0.85), a powerful relationship with some room for enchancment. The median and interquartile vary for the relative magnitude of impact (e.g., hazard ratiooriginal/ hazard ratioreproduction) is 1.0 [0.9, 1.1], vary [0.3, 2.1]. Whereas the vast majority of outcomes are intently reproduced, a subset usually are not. The latter could be defined by incomplete reporting and up to date information. Better methodological transparency aligned with new steering could additional enhance reproducibility and validity evaluation, thus facilitating evidence-based decision-making