Estimand Framework and Statistical Considerations for Integrated Analysis of Clinical Trial Safety Data
Authors:
- 31 August 2024
- journal article
- research article
- Published by Springer Nature in Therapeutic Innovation & Regulatory Science
- Vol. 58 (6) , 1120-1128
Abstract
Background Safety analyses play a pivotal role in drug development, ensuring the protection of patients while advancing innovative pharmaceuticals to market. A single study generally does not have sufficient sample size to evaluate all important safety events with reasonable precision and may not cover the full target population for the investigational treatment. Integrated analyses (pooled or meta-analysis) over several studies may be helpful in that regard. But without a structured conscious workflow accompanied with appropriate statistical methods for the integrated analysis, this can easily take a route compromising the interpretation. Methods In this article we apply the ICH estimand framework to clinical trial integration and summarize respective critical statistical assumptions to ensure the integrated analyses are interpretable. Results The estimand framework is valuable for developing principles for a deeper understanding of the critical statistical aspects of planning an integrated safety analysis. Our principles address the clinical question of interest, estimand and estimation. Special focus was given to the criteria for inclusion and exclusion of the component studies in the integrated analysis, and to integration of estimates pertaining to signal detection. Conclusion Performing an integrated analysis and its preparatory steps calls for a good understanding of the clinical question of interest and its estimand, care and sound practice, to enable interpretation and avoid introducing unnecessary bias. It is valuable to use the estimand framework not only for efficacy evaluations, but also for safety evaluations in clinical trials and for integrated safety analyses.Keywords
This publication has 13 references indexed in Scilit:
- Meta-Analysis of Drug Safety Assessment2021
- On estimands and the analysis of adverse events in the presence of varying follow‐up times within the benefit assessment of therapiesPharmaceutical Statistics, 2018
- Meta-analysis using individual participant data: one-stage and two-stage approaches, and why they may differStatistics in Medicine, 2016
- Impact of Informative Censoring on the Kaplan-Meier Estimate of Progression-Free Survival in Phase II Clinical TrialsJournal of Clinical Oncology, 2014
- Meta-analysis of clinical trial safety data in a drug development program: Answers to frequently asked questionsClinical Trials, 2012
- Reporting cumulative proportion of subjects with an adverse event based on data from multiple studiesPharmaceutical Statistics, 2011
- Recommendations for safety planning, data collection, evaluation and reporting during drug, biologic and vaccine development: a report of the safety planning, evaluation, and reporting teamClinical Trials, 2009
- Survival Analysis in Clinical Trials: Past Developments and Future DirectionsBiometrics, 2000
- The Role of Meta-analysis in the Regulatory Process for Foods, Drugs, and DevicesJAMA, 1999
- The Interpretation of Interaction in Contingency TablesJournal of the Royal Statistical Society Series B: Statistical Methodology, 1951