Skip to main content
Grant Details

Grant Number: 5R01CA129102-09 Interpret this number
Primary Investigator: Taylor, Jeremy
Organization: University Of Michigan At Ann Arbor
Project Title: Statistical Methods for Cancer Biomarkers
Fiscal Year: 2018
Back to top


Abstract

Project Summary/Abstract Individualized prognostic models abound in clinical biomedicine. They are used to make predictions of the future, derived from individual patient characteristics, and will play increasingly important roles in the move towards per- sonalized medicine. They can be used in the settings of early detection and screening, or after a cancer diagnosis to help decide on treatment, or after treatment to monitor for progression and recurrence. While some models are well established, they likely have the potential to be improved through the use of additional variables. Larger and better quality training datasets and improved statistical models and methods will improve their accuracy, but the potential for largest improvement is through new biomarkers. Since cancer is a heterogenous disease with multifactorial etiology, many clinical and molecular factors will likely aid in predicting the future for a patient, and would be candidates for inclusion in a new model. The challenge we will address in this research is how to de- velop a new model that both includes the new biomarkers and makes use of the knowledge implicit in the existing models, when the datasets that are available containing the new biomarkers are only of modest size. To develop a new model from a new dataset of modest size that contains the new biomarkers, the typical approach will be to analyze these data, as a separate entity, and build a model based on that analysis. However, this approach does not utilize the external information from an established model. Such external information will often be available, however it may come in the form of regression coef?cients, odds ratios or other summary statistics for a subset of the variables, or in the form of a prediction from an online calculator. We will consider a variety of statistical methods for incorporating the external information. The methods we propose to develop are motivated by speci?c head and neck cancer and prostate cancer stud- ies, but have much broader applicability to other cancers and other diseases. In the head and neck study the additional new biomarkers to be incorporated in to the prediction models are HPV status and other molecular biomarkers. For the prostate cancer risk prediction model the new bimarkers are based on proteins measured from urine. The research is separated into three speci?c aims. The ?rst aim considers the situation in which there is a modest sized new dataset, that includes a new biomarker, and there is an existing prediction model, that does not include this new biomarker. The external information comes in the form of estimates and standard errors of regression parameters from an established prediction model based on a subset of the predictors. We propose a number of different frequentist and Bayesian methods, in which the information on the lower dimensional parameter space is used via inequality constraints and Lagrange multipliers, through prior distributions and through a novel transformation approach. The properties of the approaches will be compared in the situation of continuous and binary response variables. In the second aim the external information comes in the form of a prediction from one or more calculators, and speci?cally the predictions for each individual in our own data are used. We include in this aim consideration of the situation where there are multiple established prediction models and where the outcome variable is the survival time. We consider different possible methodological approaches, one is an adaptation of the methods in the ?rst aim, a second very general method is to incorporate synthetic data generated from the existing models and a third general method uses weights that enable the new biomarker to have a stronger role for observations that were were not predicted well by the existing models. In the third aim we consider the situation where there may be a panel of new biomarkers, and there is also knowledge about the unadjusted association between each new biomarker and the outcome variable, as might be available from a genome-wide association study. A novel nonparametric Bayes approach is proposed to solve this problem.

Back to top


Publications

Individualized survival prediction for patients with oropharyngeal cancer in the human papillomavirus era.
Authors: Beesley L.J. , Hawkins P.G. , Amlani L.M. , Bellile E.L. , Casper K.A. , Chinn S.B. , Eisbruch A. , Mierzwa M.L. , Spector M.E. , Wolf G.T. , et al. .
Source: Cancer, 2018-10-06 00:00:00.0; , .
EPub date: 2018-10-06 00:00:00.0.
PMID: 30291798
Related Citations

Incorporating historical models with adaptive Bayesian updates.
Authors: Boonstra P.S. , Barbaro R.P. .
Source: Biostatistics (oxford, England), 2018-09-21 00:00:00.0; , .
EPub date: 2018-09-21 00:00:00.0.
PMID: 30247557
Related Citations

Prognostic Value of FDG-PET/CT Metabolic Parameters in Metastatic Radioiodine-Refractory Differentiated Thyroid Cancer.
Authors: Manohar P.M. , Beesley L.J. , Bellile E.L. , Worden F.P. , Avram A.M. .
Source: Clinical Nuclear Medicine, 2018 Sep; 43(9), p. 641-647.
PMID: 30015659
Related Citations

Redefining Perineural Invasion: Integration of Biology With Clinical Outcome.
Authors: Schmitd L.B. , Beesley L.J. , Russo N. , Bellile E.L. , Inglehart R.C. , Liu M. , Romanowicz G. , Wolf G.T. , Taylor J.M.G. , D'Silva N.J. .
Source: Neoplasia (new York, N.y.), 2018 Jul; 20(7), p. 657-667.
EPub date: 2018-05-23 00:00:00.0.
PMID: 29800815
Related Citations

Improving estimation and prediction in linear regression incorporating external information from an established reduced model.
Authors: Cheng W. , Taylor J.M.G. , Vokonas P.S. , Park S.K. , Mukherjee B. .
Source: Statistics In Medicine, 2018-01-24 00:00:00.0; , .
EPub date: 2018-01-24 00:00:00.0.
PMID: 29365342
Related Citations

Estimating the Optimal Personalized Treatment Strategy Based on Selected Variables to Prolong Survival via Random Survival Forest with Weighted Bootstrap.
Authors: Shen J. , Wang L. , Daignault S. , Spratt D.E. , Morgan T.M. , Taylor J.M.G. .
Source: Journal Of Biopharmaceutical Statistics, 2018; 28(2), p. 362-381.
EPub date: 2017-10-25 00:00:00.0.
PMID: 28934002
Related Citations

Comparison of joint modeling and landmarking for dynamic prediction under an illness-death model.
Authors: Suresh K. , Taylor J.M.G. , Spratt D.E. , Daignault S. , Tsodikov A. .
Source: Biometrical Journal. Biometrische Zeitschrift, 2017 Nov; 59(6), p. 1277-1300.
EPub date: 2017-05-16 00:00:00.0.
PMID: 28508545
Related Citations

Covariate adjustment using propensity scores for dependent censoring problems in the accelerated failure time model.
Authors: Cho Y. , Hu C. , Ghosh D. .
Source: Statistics In Medicine, 2017-10-10 00:00:00.0; , .
EPub date: 2017-10-10 00:00:00.0.
PMID: 29023972
Related Citations

Links between causal effects and causal association for surrogacy evaluation in a gaussian setting.
Authors: Conlon A. , Taylor J. , Li Y. , Diaz-Ordaz K. , Elliott M. .
Source: Statistics In Medicine, 2017-08-08 00:00:00.0; , .
EPub date: 2017-08-08 00:00:00.0.
PMID: 28786131
Related Citations

Surrogacy assessment using principal stratification and a Gaussian copula model.
Authors: Conlon A. , Taylor J. , Elliott M.R. .
Source: Statistical Methods In Medical Research, 2017 Feb; 26(1), p. 88-107.
PMID: 24947559
Related Citations

Increasing efficiency for estimating treatment-biomarker interactions with historical data.
Authors: Boonstra P.S. , Taylor J.M. , Mukherjee B. .
Source: Statistical Methods In Medical Research, 2016 Dec; 25(6), p. 2959-2971.
EPub date: 2014-05-21 00:00:00.0.
PMID: 24855118
Related Citations

Individualized Risk Prediction Of Outcomes For Oral Cavity Cancer Patients
Authors: Prince V. , Bellile E.L. , Sun Y. , Wolf G.T. , Hoban C.W. , Shuman A.G. , Taylor J.M. .
Source: Oral Oncology, 2016 Dec; 63, p. 66-73.
PMID: 27939002
Related Citations

Estimation Of The Optimal Regime In Treatment Of Prostate Cancer Recurrence From Observational Data Using Flexible Weighting Models
Authors: Shen J. , Wang L. , Taylor J.M. .
Source: Biometrics, 2016-11-28 00:00:00.0; , .
PMID: 27893926
Related Citations

A modified risk set approach to biomarker evaluation studies.
Authors: Ghosh D. .
Source: Statistics In Biosciences, 2016 Oct; 8(2), p. 395-406.
EPub date: 2016-08-22 00:00:00.0.
PMID: 28989545
Related Citations

Permutation Testing for Treatment-Covariate Interactions and Subgroup Identification.
Authors: Foster J.C. , Nan B. , Shen L. , Kaciroti N. , Taylor J.M. .
Source: Statistics In Biosciences, 2016 Jun; 8(1), p. 77-98.
PMID: 27606036
Related Citations

Personalized screening intervals for biomarkers using joint models for longitudinal and survival data.
Authors: Rizopoulos D. , Taylor J.M. , Van Rosmalen J. , Steyerberg E.W. , Takkenberg J.J. .
Source: Biostatistics (oxford, England), 2016 Jan; 17(1), p. 149-64.
PMID: 26319700
Related Citations

An Adaptive Genetic Association Test Using Double Kernel Machines.
Authors: Zhan X. , Epstein M.P. , Ghosh D. .
Source: Statistics In Biosciences, 2015-10-01 00:00:00.0; 7(2), p. 262-281.
EPub date: 2015-10-01 00:00:00.0.
PMID: 26640602
Related Citations

Data-adaptive Shrinkage via the Hyperpenalized EM Algorithm.
Authors: Boonstra P.S. , Taylor J.M. , Mukherjee B. .
Source: Statistics In Biosciences, 2015-10-01 00:00:00.0; 7(2), p. 417-431.
EPub date: 2015-10-01 00:00:00.0.
PMID: 26834856
Related Citations

A prediction model for colon cancer surveillance data.
Authors: Good N.M. , Suresh K. , Young G.P. , Lockett T.J. , Macrae F.A. , Taylor J.M. .
Source: Statistics In Medicine, 2015-08-15 00:00:00.0; 34(18), p. 2662-75.
EPub date: 2015-08-15 00:00:00.0.
PMID: 25851283
Related Citations

Surrogacy assessment using principal stratification with multivariate normal and Gaussian copula models.
Authors: Taylor J.M. , Conlon A.S. , Elliott M.R. .
Source: Clinical Trials (london, England), 2015 Aug; 12(4), p. 317-22.
PMID: 25490988
Related Citations

A Small-Sample Choice of the Tuning Parameter in Ridge Regression.
Authors: Boonstra P.S. , Mukherjee B. , Taylor J.M. .
Source: Statistica Sinica, 2015-07-01 00:00:00.0; 25(3), p. 1185-1206.
PMID: 26985140
Related Citations

Improving efficiency in clinical trials using auxiliary information: Application of a multi-state cure model.
Authors: Conlon A.S. , Taylor J.M. , Sargent D.J. .
Source: Biometrics, 2015 Jun; 71(2), p. 460-8.
PMID: 25585942
Related Citations

Penalized regression procedures for variable selection in the potential outcomes framework.
Authors: Ghosh D. , Zhu Y. , Coffman D.L. .
Source: Statistics In Medicine, 2015-05-10 00:00:00.0; 34(10), p. 1645-58.
EPub date: 2015-05-10 00:00:00.0.
PMID: 25628185
Related Citations

Surrogacy marker paradox measures in meta-analytic settings.
Authors: Elliott M.R. , Conlon A.S. , Li Y. , Kaciroti N. , Taylor J.M. .
Source: Biostatistics (oxford, England), 2015 Apr; 16(2), p. 400-12.
PMID: 25236906
Related Citations

Simple subgroup approximations to optimal treatment regimes from randomized clinical trial data.
Authors: Foster J.C. , Taylor J.M. , Kaciroti N. , Nan B. .
Source: Biostatistics (oxford, England), 2015 Apr; 16(2), p. 368-82.
PMID: 25398774
Related Citations

Reader reaction to "a robust method for estimating optimal treatment regimes" by Zhang et al. (2012).
Authors: Taylor J.M. , Cheng W. , Foster J.C. .
Source: Biometrics, 2015 Mar; 71(1), p. 267-71.
PMID: 25228049
Related Citations

Incorporating auxiliary information for improved prediction using combination of kernel machines.
Authors: Zhan X. , Ghosh D. .
Source: Statistical Methodology, 2015-01-01 00:00:00.0; 22, p. 47-57.
PMID: 25419198
Related Citations

Weighted estimation of the accelerated failure time model in the presence of dependent censoring.
Authors: Cho Y. , Ghosh D. .
Source: Plos One, 2015; 10(4), p. e0124381.
PMID: 25909753
Related Citations

Regression hidden Markov modeling reveals heterogeneous gene expression regulation: a case study in mouse embryonic stem cells.
Authors: Lee Y. , Ghosh D. , Zhang Y. .
Source: Bmc Genomics, 2014-05-12 00:00:00.0; 15, p. 360.
EPub date: 2014-05-12 00:00:00.0.
PMID: 24884369
Related Citations

Multi-state models for colon cancer recurrence and death with a cured fraction.
Authors: Conlon A.S. , Taylor J.M. , Sargent D.J. .
Source: Statistics In Medicine, 2014-05-10 00:00:00.0; 33(10), p. 1750-66.
EPub date: 2014-05-10 00:00:00.0.
PMID: 24307330
Related Citations

Surrogacy assessment using principal stratification when surrogate and outcome measures are multivariate normal.
Authors: Conlon A.S. , Taylor J.M. , Elliott M.R. .
Source: Biostatistics (oxford, England), 2014 Apr; 15(2), p. 266-83.
PMID: 24285772
Related Citations

Comparison of methods for estimating the effect of salvage therapy in prostate cancer when treatment is given by indication.
Authors: Taylor J.M. , Shen J. , Kennedy E.H. , Wang L. , Schaubel D.E. .
Source: Statistics In Medicine, 2014-01-30 00:00:00.0; 33(2), p. 257-74.
EPub date: 2014-01-30 00:00:00.0.
PMID: 23824930
Related Citations

CONFIDENCE INTERVALS UNDER ORDER RESTRICTIONS.
Authors: Park Y. , Kalbfleisch J.D. , Taylor J.M. .
Source: Statistica Sinica, 2014 Jan; 24(1), p. 429-445.
PMID: 24505210
Related Citations

BAYESIAN SHRINKAGE METHODS FOR PARTIALLY OBSERVED DATA WITH MANY PREDICTORS.
Authors: Boonstra P.S. , Mukherjee B. , Taylor J.M. .
Source: The Annals Of Applied Statistics, 2013-12-01 00:00:00.0; 7(4), p. 2272-2292.
PMID: 24436727
Related Citations

Criteria for the use of omics-based predictors in clinical trials.
Authors: McShane L.M. , Cavenagh M.M. , Lively T.G. , Eberhard D.A. , Bigbee W.L. , Williams P.M. , Mesirov J.P. , Polley M.Y. , Kim K.Y. , Tricoli J.V. , et al. .
Source: Nature, 2013-10-17 00:00:00.0; 502(7471), p. 317-20.
PMID: 24132288
Related Citations

Variable selection in monotone single-index models via the adaptive LASSO.
Authors: Foster J.C. , Taylor J.M. , Nan B. .
Source: Statistics In Medicine, 2013-09-30 00:00:00.0; 32(22), p. 3944-54.
EPub date: 2013-09-30 00:00:00.0.
PMID: 23650074
Related Citations

Incorporating auxiliary information for improved prediction in high-dimensional datasets: an ensemble of shrinkage approaches.
Authors: Boonstra P.S. , Taylor J.M. , Mukherjee B. .
Source: Biostatistics (oxford, England), 2013 Apr; 14(2), p. 259-72.
PMID: 23087411
Related Citations

Real-time individual predictions of prostate cancer recurrence using joint models.
Authors: Taylor J.M. , Park Y. , Ankerst D.P. , Proust-Lima C. , Williams S. , Kestin L. , Bae K. , Pickles T. , Sandler H. .
Source: Biometrics, 2013 Mar; 69(1), p. 206-13.
PMID: 23379600
Related Citations

Accommodating missingness when assessing surrogacy via principal stratification.
Authors: Elliott M.R. , Li Y. , Taylor J.M. .
Source: Clinical Trials (london, England), 2013; 10(3), p. 363-77.
PMID: 23553326
Related Citations

Association Testing To Detect Gene-gene Interactions On Sex Chromosomes In Trio Data
Authors: Lee Y. , Ghosh D. , Zhang Y. .
Source: Frontiers In Genetics, 2013; 4, p. 239.
PMID: 24312118
Related Citations

On Bayesian methods of exploring qualitative interactions for targeted treatment.
Authors: Chen W. , Ghosh D. , Raghunathan T.E. , Norkin M. , Sargent D.J. , Bepler G. .
Source: Statistics In Medicine, 2012-12-10 00:00:00.0; 31(28), p. 3693-707.
EPub date: 2012-12-10 00:00:00.0.
PMID: 22733620
Related Citations

A causal framework for surrogate endpoints with semi-competing risks data.
Authors: Ghosh D. .
Source: Statistics & Probability Letters, 2012 Oct; 82(11), p. 1898-1902.
PMID: 22899873
Related Citations

Assumption weighting for incorporating heterogeneity into meta-analysis of genomic data.
Authors: Li Y. , Ghosh D. .
Source: Bioinformatics (oxford, England), 2012-03-15 00:00:00.0; 28(6), p. 807-14.
EPub date: 2012-03-15 00:00:00.0.
PMID: 22285559
Related Citations

Meta-analysis for surrogacy: accelerated failure time models and semicompeting risks modeling.
Authors: Ghosh D. , Taylor J.M. , Sargent D.J. .
Source: Biometrics, 2012 Mar; 68(1), p. 226-32.
PMID: 21668903
Related Citations

Rejoinder for "Meta-analysis for surrogacy: accelerated failure time models and semi-competing risks modelling"
Authors: Ghosh D. , Taylor J.M. , Sargent D.J. .
Source: Biometrics, 2012 Mar; 68(1), p. 245-247.
PMID: 22547832
Related Citations

A shrinkage approach for estimating a treatment effect using intermediate biomarker data in clinical trials.
Authors: Li Y. , Taylor J.M. , Little R.J. .
Source: Biometrics, 2011 Dec; 67(4), p. 1434-41.
PMID: 21627627
Related Citations

Subgroup identification from randomized clinical trial data.
Authors: Foster J.C. , Taylor J.M. , Ruberg S.J. .
Source: Statistics In Medicine, 2011-10-30 00:00:00.0; 30(24), p. 2867-80.
EPub date: 2011-10-30 00:00:00.0.
PMID: 21815180
Related Citations

Using cure models and multiple imputation to utilize recurrence as an auxiliary variable for overall survival.
Authors: Conlon A.S. , Taylor J.M. , Sargent D.J. , Yothers G. .
Source: Clinical Trials (london, England), 2011 Oct; 8(5), p. 581-90.
PMID: 21921063
Related Citations

Causal assessment of surrogacy in a meta-analysis of colorectal cancer trials.
Authors: Li Y. , Taylor J.M. , Elliott M.R. , Sargent D.J. .
Source: Biostatistics (oxford, England), 2011 Jul; 12(3), p. 478-92.
PMID: 21252079
Related Citations

Links between analysis of surrogate endpoints and endogeneity.
Authors: Ghosh D. , Elliott M.R. , Taylor J.M. .
Source: Statistics In Medicine, 2010-12-10 00:00:00.0; 29(28), p. 2869-79.
PMID: 20803482
Related Citations




Back to Top