TY - JOUR
T1 - Effectively selecting a target population for a future comparative study
AU - Zhao, Lihui
AU - Tian, Lu
AU - Cai, Tianxi
AU - Claggett, Brian
AU - Wei, L. J.
N1 - Funding Information:
Lihui Zhao is Assistant Professor, Department of Preventive Medicine, Northwestern University, Chicago, IL 60611, USA (E-mail: lihui.zhao@northwestern.edu). Lu Tian is Associate Professor, Department of Health Research and Policy, Stanford University, Stanford, CA 94305, USA (E-mail: lutian@stanford.edu). Tianxi Cai is Professor, Department of Biostatistics, Harvard University, Boston, MA 02115, USA (E-mail: tcai@hsph.harvard.edu). Brian Claggett is Instructor, Division of Cardiovascular Medicine, Harvard Medical School, Boston, MA 02115, USA (E-mail: bclaggett@partners.org). L. J. Wei is Professor, Department of Biostatistics, Harvard University, Boston, MA 02115, USA (E-mail: wei@hsph.harvard.edu). The authors are grateful to the editor, an associate editor and two referees for their insightful comments. This research was partially supported by the grants from the U.S. National Institutes of Health (R01 AI052817, RC4 CA155940, U01 AI068616, UM1 AI068634, R01 AI024643, U54 LM008748, R01 HL089778, R01 GM079330).
PY - 2013
Y1 - 2013
N2 - When comparing a new treatment with a control in a randomized clinical study, the treatment effect is generally assessed by evaluating a summary measure over a specific study population. The success of the trial heavily depends on the choice of such a population. In this article, we show a systematic, effective way to identify a promising population, for which the new treatment is expected to have a desired benefit, using the data from a current study involving similar comparator treatments. Specifically, using the existing data, we first create a parametric scoring system as a function of multiple baseline covariates to estimate subject-specific treatment differences. Based on this scoring system, we specify a desired level of treatment difference and obtain a subgroup of patients, defined as those whose estimated scores exceed this threshold. An empirically calibrated threshold-specific treatment difference curve across a range of score values is constructed. The subpopulation of patients satisfying any given level of treatment benefit can then be identified accordingly. To avoid bias due to overoptimism, we use a cross-training-evaluation method for implementing the above two-step procedure. We then show how to select the best scoring system among all competing models. Furthermore, for cases in which only a single prespecified working model is involved, inference procedures are proposed for the average treatment difference over a range of score values using the entire dataset and are justified theoretically and numerically. Finally, the proposals are illustrated with the data from two clinical trials in treating HIV and cardiovascular diseases. Note that if we are not interested in designing a new study for comparing similar treatments, the new procedure can also be quite useful for the management of future patients, so that treatment may be targeted toward those who would receive nontrivial benefits to compensate for the risk or cost of the new treatment. Supplementary materials for this article are available online.
AB - When comparing a new treatment with a control in a randomized clinical study, the treatment effect is generally assessed by evaluating a summary measure over a specific study population. The success of the trial heavily depends on the choice of such a population. In this article, we show a systematic, effective way to identify a promising population, for which the new treatment is expected to have a desired benefit, using the data from a current study involving similar comparator treatments. Specifically, using the existing data, we first create a parametric scoring system as a function of multiple baseline covariates to estimate subject-specific treatment differences. Based on this scoring system, we specify a desired level of treatment difference and obtain a subgroup of patients, defined as those whose estimated scores exceed this threshold. An empirically calibrated threshold-specific treatment difference curve across a range of score values is constructed. The subpopulation of patients satisfying any given level of treatment benefit can then be identified accordingly. To avoid bias due to overoptimism, we use a cross-training-evaluation method for implementing the above two-step procedure. We then show how to select the best scoring system among all competing models. Furthermore, for cases in which only a single prespecified working model is involved, inference procedures are proposed for the average treatment difference over a range of score values using the entire dataset and are justified theoretically and numerically. Finally, the proposals are illustrated with the data from two clinical trials in treating HIV and cardiovascular diseases. Note that if we are not interested in designing a new study for comparing similar treatments, the new procedure can also be quite useful for the management of future patients, so that treatment may be targeted toward those who would receive nontrivial benefits to compensate for the risk or cost of the new treatment. Supplementary materials for this article are available online.
KW - Cross-training-evaluation
KW - Lasso procedure
KW - Personalized medicine
KW - Prediction
KW - Ridge regression
KW - Stratified medicine
KW - Subgroup analysis
KW - Variable selection
UR - http://www.scopus.com/inward/record.url?scp=84890112672&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84890112672&partnerID=8YFLogxK
U2 - 10.1080/01621459.2013.770705
DO - 10.1080/01621459.2013.770705
M3 - Article
C2 - 24058223
AN - SCOPUS:84890112672
SN - 0162-1459
VL - 108
SP - 527
EP - 539
JO - Journal of the American Statistical Association
JF - Journal of the American Statistical Association
IS - 502
ER -
