A threshold linear mixed model for identification of treatment-sensitive subsets in a clinical trial based on longitudinal outcomes and a continuous covariate
Restricted accessResearch articleFirst published online October, 2020
A threshold linear mixed model for identification of treatment-sensitive subsets in a clinical trial based on longitudinal outcomes and a continuous covariate
Identification of a subset of patients who may be sensitive to a specific treatment is an important problem in clinical trials. In this paper, we consider the case where the treatment effect is measured by longitudinal outcomes, such as quality of life scores assessed over the duration of a clinical trial, and the subset is determined by a continuous baseline covariate, such as age and expression level of a biomarker. A threshold linear mixed model is introduced, and a smoothing maximum likelihood method is proposed to obtain the estimation of the parameters in the model. Broyden-Fletcher-Goldfarb-Shanno algorithm is employed to maximize the proposed smoothing likelihood function. The proposed procedure is evaluated through simulation studies and application to the analysis of data from a randomized clinical trial on patients with advanced colorectal cancer.
BezjakATuDSeymourL, et al.
Symptom improvement in lung cancer patients treated with erlotinib: quality of life analysis of the National Cancer Institute of Canada Clinical Trials Group Study BR. 21. J Clin Oncol2006;
24: 3831–3837.
2.
WellsCO’CallaghanCKarapetisC, et al.
Outcomes of older patients (70 years) treated with targeted therapy in metastatic chemorefractory colorectal cancer: retrospective analysis of NCIC CTG CO.17 and CO.20. Clin Colorectal Cancer2008;
18: e140–e149.
LohWY.Regression trees with unbiased variable selection and interaction detection. Statistica Sinica2002;
12: 361–386.
5.
FosterJCTaylorJMCRubergSJ.Subgroup identification from randomized clinical trial data.Stat Med2011;
30: 2867–2880.
6.
LipkovichIDmitrienkoAD’AgostinoRB, et al.
Tutorial in biostatistics: data-driven subgroup identification and analysis in clinical trials.Stat Med2017;
36: 136–196.
7.
JiangWFreidlinBSimonR.Biomarker-adaptive threshold design: a procedure for evaluating treatment with possible biomarker-defined subset effect.J Natl Cancer Inst2007;
99: 1036–1043.
8.
ChenBEJiangWTuD.A hierarchical Bayes model for biomarker subset effects in clinical trials. Comput Stat Data Anal2014;
71: 324–334.
9.
MoineddinRButtDATomlinsonG, et al.
Identifying subpopulations for subgroup analysis in a longitudinal clinical trial.Contemp Clin Trials2008;
29: 817–822.
10.
AndrewsN.Subgroup analysis and growth curve models for longitudinal data. PhD Thesis, Western Michigan University, USA, 2017.
11.
PattersonHDThompsonR.Recovery of inter-block information when block sizes are unequal. Biometrika1971;
58: 545–554.
12.
BrownBWangYG.Induced smoothing for rank regression with censored survival times.Stat Med2007;
26: 828–836.
13.
BroydenCG.The convergence of a class of double-rank minimization algorithms 1. General considerations. IMA J Appl Math1970;
6: 76–90.
14.
FletcherR.A new approach to variable metric algorithms. Comput J1970;
13: 317–322.
15.
GoldfarbD.A family of variable-metric methods derived by variational means. Math Comput1970;
24: 23–26.
16.
ShannoDF.Conditioning of quasi-newton methods for function minimization. Math Comput1970;
24: 647–656.
17.
HenningsenAToometO.MaxLik: A package for maximum likelihood estimation in R. Comput Stat2011;
26: 443–458.
18.
LinHZhouLPengH, et al.
Selection and combination of biomarkers using ROC method for disease classification and prediction. Can J Stat2011;
39: 324–343.
19.
HeYLinHTuD.A single-index threshold Cox proportional hazard model for identifying a treatment-sensitive subset based on multiple biomarkers.Stat Med2018;
37: 3267–3279.
20.
DigglePKenwardMG.Informative drop-out in longitudinal data analysis. Appl Stat1994;
43: 49–93.
21.
HenryKEriceATierneyC, et al.
A randomized, controlled, double-blind study comparing the survival benefit of four different reverse transcriptase inhibitor therapies (three-drug, two-drug, and alternating drug) for the treatment of advanced AIDS. AIDS Clinical Trial Group 193A Study Team. J Acquir Immune Defic Syndr1998;
19: 339–349.
22.
JonkerDJO’callaghanCJKarapetisCS, et al.
Cetuximab for the treatment of colorectal cancer.N Engl J Med2007;
357: 2040–2048.
23.
KarapetisCSKhambata-FordSJonkerDJ, et al.
K-ras mutations and benefit from cetuximab in advanced colorectal cancer.N Engl J Med2008;
359: 1757–1765.
24.
AuHJKarapetisCSO’CallaghanCJ, et al.
Health-related quality of life in patients with advanced colorectal cancer treated with cetuximab: overall and KRAS-specific results of the NCIC CTG and AGITG CO. 17 trial. J Clin Oncol2009;
27: 1822–1828.
25.
Flores-AgredaDCantoniE.Bootstrap estimation of uncertainty in prediction for generalized linear mixed models. Comput Stat Data Anal2019;
130: 1–17.
26.
FieldCAWelshAH.Bootstrapping clustered data. J R Stat Soc Series B Stat Methodol2007;
69: 369–390.
27.
HungerMDoringAHolleR.Longitudinal beta regression models for analyzing health-related quality of life scores over time.BMC Med Res Methodol2012;
12(1): 144. DOI:10.1186/1471-2288-12-144.
28.
FanYLiR.Variable selection in linear mixed effects models.Ann. Statist2012;
40: 2043–2068.
