EUVIMEDEUVIMED entdecken
Crossref

Generalizing Treatment Effect to a Target Population Without Individual Patient Data in a Real‐World Setting

Hui Quan iD, Tong Li, Xun Chen, Gang Li iD

Pharmaceutical Statistics · 2025

DOI: 10.1002/pst.2435 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pharmaceutical Statistics, 2025. Verfasst von Hui Quan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Biostatistics and Programming, Sanofi, Bridgewater, New Jersey, USA. Hauptthemen laut MEDLINE: Computer Simulation, Treatment Outcome. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The innovative use of real‐world data (RWD) can answer questions that cannot be addressed using data from randomized clinical trials (RCTs). While the sponsors of RCTs have a central database containing all individual patient data (IPD) collected from trials, analysts of RWD face a challenge: regulations on patient privacy make access to IPD from all regions logistically prohibitive. In this research, we propose a double inverse probability weighting (DIPW) approach for the analysis sponsor to estimate the population average treatment effect (PATE) for a target population without the need to access IPD. One probability weighting is for achieving comparable distributions in confounders across treatment groups; another probability weighting is for generalizing the result from a subpopulation of patients who have data on the endpoint to the whole target population. The likelihood expressions for propensity scores and the DIPW estimator of the PATE can be written to only rely on regional summary statistics that do not require IPD. Our approach hinges upon the positivity and conditional independency assumptions, prerequisites to most RWD analysis approaches. Simulations are conducted to compare the performances of the proposed method against a modified meta‐analysis and a regular meta‐analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computer SimulationTreatment OutcomeHumansData Interpretation, StatisticalDatabases, FactualMeta-Analysis as TopicProbabilityPropensity ScoreRandomized Controlled Trials as TopicResearch Design

Stichwörter der Autor:innen

double inverse probability weighting (DIPW)individual patient datapropensity scorereal‐world datareal‐world evidence

Autor:innen und Institutionen

  • Biostatistics and Programming, Sanofi, Bridgewater, New Jersey, USA.
  • Eisai Inc, Nutley, New Jersey, USA.

ORCID-Profile: Hui Quan, Gang Li

Zitieren

APA

Quan, H., Li, T., Chen, X., & Li, G. (2025). Generalizing Treatment Effect to a Target Population Without Individual Patient Data in a Real‐World Setting. Pharmaceutical Statistics. https://doi.org/10.1002/pst.2435

Vancouver

Quan H, Li T, Chen X, Li G. Generalizing Treatment Effect to a Target Population Without Individual Patient Data in a Real‐World Setting. Pharmaceutical Statistics. 2025. doi:10.1002/pst.2435

BibTeX
@article{Quan2025,
  author = {Quan, Hui and Li, Tong and Chen, Xun and Li, Gang},
  title = {Generalizing Treatment Effect to a Target Population Without Individual Patient Data in a Real‐World Setting},
  journal = {Pharmaceutical Statistics},
  year = {2025},
  doi = {10.1002/pst.2435}
}
Kostenlos starten →