Handling Missing Data and Drop Out in Hospice/Palliative Care Trials Through the Estimand Framework

Anneke C Grobler; Katherine J Lee; Aaron Wong; David C Currow; Sabine Braat

doi:10.1016/j.jpainsymman.2021.12.022

Handling Missing Data and Drop Out in Hospice/Palliative Care Trials Through the Estimand Framework

J Pain Symptom Manage. 2022 Apr;63(4):e431-e439. doi: 10.1016/j.jpainsymman.2021.12.022. Epub 2021 Dec 23.

Authors

Anneke C Grobler¹, Katherine J Lee², Aaron Wong³, David C Currow⁴, Sabine Braat⁵

Affiliations

¹ Department of Paediatrics , University of Melbourne (A.C.G., K.J.L.); Murdoch Children's Research Institute (A.C.G., K.J.L.), Melbourne, Australia. Electronic address: Anneke.grobler@mcri.edu.au.
² Department of Paediatrics , University of Melbourne (A.C.G., K.J.L.); Murdoch Children's Research Institute (A.C.G., K.J.L.), Melbourne, Australia.
³ Department of Palliative Care (A.W.), Peter MacCallum Cancer Centre, Victoria, Australia; Department of Palliative Care (A.W.), The Royal Melbourne Hospital, Victoria, Australia; Department of Medicine (A.W.), University of Melbourne, Melbourne, Australia.
⁴ IMPACCT, Faculty of Health (D.C.C.), University of Technology Sydney, New South Wales, Australia; Wolfson Palliative Care Research Centre (D.C.C.), University of Hull, Hull, England.
⁵ Centre for Epidemiology and Biostatistics (S.B.), Melbourne School of Population and Global Health, University of Melbourne, Melbourne, Australia.

PMID: 34954068
DOI: 10.1016/j.jpainsymman.2021.12.022

Abstract

Context: Missing data are common in hospice/palliative care randomized trials due to high drop-out because of the demographic of interest. It can introduce bias in the estimate of the treatment effect and its precision.

Objectives: The International Council for Harmonization of Technical Requirements for Pharmaceuticals for Human Use (ICH) released updated guidance on statistical principles for clinical trials introducing the estimand framework to align trial objectives, trial conduct, statistical analysis and interpretation of results. Our objective is to present how the estimand framework can be used to guide the handling of missing data in palliative care trials.

Methods: We outline the estimand framework by highlighting the five elements of an estimand: treatment, population, variable, summary measure and intercurrent event handling. We list common intercurrent events in palliative care trials and present the five strategies for handling intercurrent events outlined in the ICH guidance.

Results: We describe common intercurrent events in palliative care trials and discuss and justify what analytic strategies could be followed with each. We provide an example using a palliative care trial comparing two opioids for pain relieve in participants with cancer pain.

Conclusion: When planning a palliative care trial, the estimand should be explicitly stated, including how intercurrent events will be handled in the analysis. This should be informed by the scientific objectives of the trial. The estimand guides the handling of missing data during the conduct and analysis of the trial. Defining an estimand is not a statistical activity, but a multi-disciplinary process involving all stakeholders.

Keywords: Estimand; ICH E9 addendum; Missing data; intercurrent event; randomised controlled clinical trial design; withdrawal.

Publication types

Research Support, Non-U.S. Gov't
Review

MeSH terms

Data Interpretation, Statistical
Hospice and Palliative Care Nursing*
Hospices*
Humans
Palliative Care
Research Design