Constructing Treatment Decision Rules Based on Scalar and Functional Predictors when Moderators of Treatment Effect are Unknown

Adam Ciarleglio1, Eva Petkova2, Todd Ogden3, Thaddeus Tarpey4
1Columbia University and New York State Psychiatric Institute, New York, USA
2New York University School of Medicine, USA
3Columbia University, New York, USA
4Wright State University, Dayton, USA

Tóm tắt

Summary

Treatment response heterogeneity poses serious challenges for selecting treatment for many diseases. To understand this heterogeneity better and to help in determining the best patient-specific treatments for a given disease, many clinical trials are collecting large amounts of patient level data before administering treatment in the hope that some of these data can be used to identify moderators of treatment effect. These data can range from simple scalar values to complex functional data such as curves or images. Combining these various types of baseline data to discover ‘biosignatures’ of treatment response is crucial for advancing precision medicine. Motivated by the problem of selecting optimal treatment for subjects with depression based on clinical and neuroimaging data, we present an approach that both identifies covariates associated with differential treatment effect and estimates a treatment decision rule based on these covariates. We focus on settings where there is a potentially large collection of candidate biomarkers consisting of both scalar and functional data. The validity of the approach proposed is justified via extensive simulation experiments and illustrated by using data from a placebo-controlled clinical trial investigating antidepressant treatment response in subjects with depression.

Từ khóa


Tài liệu tham khảo

Ciarleglio, 2015, Treatment decisions based on scalar and functional baseline covariates, Biometrics, 71, 884, 10.1111/biom.12346

Ciarleglio, 2016, Flexible functional regression methods for estimating indivdualized treatment rules, Stat, 5, 185, 10.1002/sta4.114

Cortes, 1995, Support-vector networks, Mach. Learn., 20, 273, 10.1007/BF00994018

Fan, 2001, Variable selection via nonconcave penalized likelihood and its oracle properties, J. Am. Statist. Ass., 96, 1348, 10.1198/016214501753382273

Friedman, 2010, Regularization paths for generalized linear models via coordinate descent, J. Statist. Softwr., 33, 1

Gertheiss, 2013, Variable selection in generalized functional linear models, Stat, 2, 86, 10.1002/sta4.20

Gueorguieva, 2011, Trajectories of depression severity in clinical trials of duloxetine: insights into antidepressant and placebo responses, Arch. Gen. Psychiatr., 68, 1227, 10.1001/archgenpsychiatry.2011.132

Hardin, 2013, Understanding heterogeneity in response to antidiabetes treatment: a post hoc analysis using sides, a subgroup identification algorithm, J. Diab. Sci. Technol., 7, 420, 10.1177/193229681300700219

Herrmann, 2014, lokern: kernel regression smoothing with local or global plug-in bandwidth

Laber, 2017, Functional feature construction for individualized treatment regimes, J. Am. Statist. Ass.

Liu, 2017, Augmented multistage outcome weighted learning

Lu, 2013, Variable selection for optimal treatment decision, Statist. Meth. Med. Res., 22, 493, 10.1177/0962280211428383

Masi, 2017, An overview of autism spectrum disorder, heterogeneity and treatment options, Neursci. Bull., 33, 183, 10.1007/s12264-017-0100-y

McGrath, 2013, Toward a neuroimaging treatment selection biomarker for major depressive disorder, J. Am. Med. Ass. Psychiatr., 70, 821

McKeague, 2014, Estimation of treatment policies based on functional predictors, Statist. Sin., 24, 1461

Meier, 2015, grplasso: fitting user specified models with Group Lasso penalty

Meier, 2009, High-dimensional additive modelling, Ann. Statist., 37, 3779, 10.1214/09-AOS692

Murphy, 2003, Optimal dynamic treatment regimes (with discussion), J. R. Statist. Soc., 65, 331, 10.1111/1467-9868.00389

Oliva, 2014, Fusso: functional shrinkage and selection operator, J. Mach. Learn. Res. Wrkshp Conf. Proc., 33, 715

Qian, 2011, Performance guarantees for individualized treatment rules, Ann. Statist., 39, 1180, 10.1214/10-AOS864

Ramsay, 2005, Functional Data Analysis, 10.1007/b98888

Rubin, 1978, Bayesian inference for causal effects: the role of randomization, Ann. Statist., 6, 34, 10.1214/aos/1176344064

Stone, 1974, Cross-validatory choice and assessment of statistical predictions (with discussion), J. R. Statist. Soc., 36, 111, 10.1111/j.2517-6161.1974.tb00994.x

Therneau, 2015, rpart: recursive partitioning and regression trees

Tian, 2014, A simple method for estimating interactions between a treatment and a large number of covariates, J. Am. Statist. Ass., 109, 1517, 10.1080/01621459.2014.951443

Tibshirani, 1996, Regression shrinkage and selection via the lasso, J. R. Statist. Soc., 58, 267, 10.1111/j.2517-6161.1996.tb02080.x

Verma, 2012, Personalized medicine and cancer, J. Person. Med., 2, 1, 10.3390/jpm2010001

Wood, 2011, Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models, J. R. Statist. Soc., 73, 3, 10.1111/j.1467-9868.2010.00749.x

Zhang, 2012, Estimating optimal treatment regimes from a classification perspective, Stat, 1, 103, 10.1002/sta.411

Zhang, 2012, A robust method for estimating optimal treatment regimes, Biometrics, 68, 1010, 10.1111/j.1541-0420.2012.01763.x

Zhao, 2012, Estimating individualized treatment rules using outcome weighted learning, J. Am. Statist. Ass., 107, 1106, 10.1080/01621459.2012.695674

Zhou, 2015, Residual weighted learning for estimating individualized treatment rules, J. Am. Statist. Ass., 112, 169, 10.1080/01621459.2015.1093947

Zou, 2006, The adaptive lasso and its oracle properties, J. Am. Statist. Ass., 101, 1418, 10.1198/016214506000000735

Zou, 2005, Regularization and variable selection via the elastic net, J. R. Statist. Soc., 67, 301, 10.1111/j.1467-9868.2005.00503.x