Using multiple imputation to classify potential outcomes subgroups
- 22 April 2021
- journal article
- research article
- Published by SAGE Publications in Statistical Methods in Medical Research
- Vol. 30 (6), 1428-1444
- https://doi.org/10.1177/09622802211002866
Abstract
With medical tests becoming increasingly available, concerns about over-testing, over-treatment and health care cost dramatically increase. Hence, it is important to understand the influence of testing on treatment selection in general practice. Most statistical methods focus on average effects of testing on treatment decisions. However, this may be ill-advised, particularly for patient subgroups that tend not to benefit from such tests. Furthermore, missing data are common, representing large and often unaddressed threats to the validity of most statistical methods. Finally, it is often desirable to conduct analyses that can be interpreted causally. Using the Rubin Causal Model framework, we propose to classify patients into four potential outcomes subgroups, defined by whether or not a patient’s treatment selection is changed by the test result and by the direction of how the test result changes treatment selection. This subgroup classification naturally captures the differential influence of medical testing on treatment selections for different patients, which can suggest targets to improve the utilization of medical tests. We can then examine patient characteristics associated with patient potential outcomes subgroup memberships. We used multiple imputation methods to simultaneously impute the missing potential outcomes as well as regular missing values. This approach can also provide estimates of many traditional causal quantities of interest. We find that explicitly incorporating causal inference assumptions into the multiple imputation process can improve the precision for some causal estimates of interest. We also find that bias can occur when the potential outcomes conditional independence assumption is violated; sensitivity analyses are proposed to assess the impact of this violation. We applied the proposed methods to examine the influence of 21-gene assay, the most commonly used genomic test in the United States, on chemotherapy selection among breast cancer patients.Keywords
Funding Information
- National Cancer Institute (P01CA163233, CA46592, CA129102 and U057141)
This publication has 56 references indexed in Scilit:
- Design and Estimation for Evaluating Principal Surrogate Markers in Vaccine TrialsBiometrics, 2013
- Treatment Heterogeneity and Individual Qualitative InteractionThe American Statistician, 2012
- Causal assessment of surrogacy in a meta-analysis of colorectal cancer trialsBiostatistics, 2011
- A Bayesian Approach to Surrogacy Assessment Using Principal Stratification in Clinical TrialsBiometrics, 2010
- Estimating Causal Effects in Trials Involving Multitreatment Arms Subject to Non-Compliance: A Bayesian FrameworkJournal of the Royal Statistical Society Series C: Applied Statistics, 2010
- Prognostic and predictive value of the 21-gene recurrence score assay in postmenopausal women with node-positive, oestrogen-receptor-positive breast cancer on chemotherapy: a retrospective analysis of a randomised trialThe Lancet Oncology, 2010
- A most stubborn bias: no adjustment method fully resolves confounding by indication in observational studiesJournal of Clinical Epidemiology, 2010
- Bayesian inference for causal mediation effects using principal stratification with dichotomous mediators and outcomesBiostatistics, 2010
- Multiple Imputation Methods for Treatment Noncompliance and Nonresponse in Randomized Clinical TrialsBiometrics, 2009
- A Multigene Assay to Predict Recurrence of Tamoxifen-Treated, Node-Negative Breast CancerThe New England Journal of Medicine, 2004