A multiple imputation strategy for sequential multiple assignment randomized trials

Susan M Shortreed, Eric Laber, T Scott Stroup, Joelle Pineau, Susan A Murphy, Susan M Shortreed, Eric Laber, T Scott Stroup, Joelle Pineau, Susan A Murphy

Abstract

Sequential multiple assignment randomized trials (SMARTs) are increasingly being used to inform clinical and intervention science. In a SMART, each patient is repeatedly randomized over time. Each randomization occurs at a critical decision point in the treatment course. These critical decision points often correspond to milestones in the disease process or other changes in a patient's health status. Thus, the timing and number of randomizations may vary across patients and depend on evolving patient-specific information. This presents unique challenges when analyzing data from a SMART in the presence of missing data. This paper presents the first comprehensive discussion of missing data issues typical of SMART studies: we describe five specific challenges and propose a flexible imputation strategy to facilitate valid statistical estimation and inference using incomplete data from a SMART. To illustrate these contributions, we consider data from the Clinical Antipsychotic Trial of Intervention and Effectiveness, one of the most well-known SMARTs to date.

Trial registration: ClinicalTrials.gov NCT00140001.

Keywords: dynamic treatment regimes; individualized treatment; missing data; multiple imputation; sequential multiple assignment randomized trials; treatment policies.

Copyright © 2014 John Wiley & Sons, Ltd.

Figures

Figure 1
Figure 1
Bar plots showing the amount of missing data in the CATIE study. The total height of the bar displays the absolute number of people who have missing (a) PANSS, (b) BMI, and (c) adherence, as measured by pill count, at each of the monthly visits at which the scheduled variable was collected. The dark grey area represents individuals with missing values because they have dropped out of the study prior to that month. The unshaded area is the amount of item missingness in each variable.

Source: PubMed

Kommende kliniske studier

Innstillinger for informasjonskapsler

Vi bruker informasjonskapsler for å sikre at vi gir deg den beste opplevelsen på nettstedet vårt. For mer informasjon, les nøye vår Retningslinjer for personvern og informasjonskapsler. ...>>>Du kan når som helst endre preferansene dine eller trekke tilbake samtykket ditt ved å slette informasjonskapslene fra nettstedet ditt eller datamaskinen som beskrevet i policyen. Godta det og velg dine preferanser ved å krysse av i de tilhørende rutene i delen "Administrer innstillinger" nedenfor. Les nøye gjennom servicevilkårene før du fortsetter å bruke noen del av dette nettstedet.
«Administrer innstillinger