Quantile residual life regression with longitudinal biomarker measurements for dynamic prediction

Summary Residual life is of great interest to patients with life threatening disease. It is also important for clinicians who estimate prognosis and make treatment decisions. Quantile residual life has emerged as a useful summary measure of the residual life. It has many desirable features, such as robustness and easy interpretation. In many situations, the longitudinally collected biomarkers during patients' follow-up visits carry important prognostic value. In this work, we study quantile regression methods that allow for dynamic predictions of the quantile residual life, by flexibly accommodating the post-baseline biomarker measurements in addition to the baseline covariates. We propose unbiased estimating equations that can be solved via existing L1-minimization algorithms. The resulting estimators have desirable asymptotic properties and satisfactory finite sample performance. We apply our method to a study of chronic myeloid leukaemia to demonstrate its usefulness as a dynamic prediction tool.

[1]  Xuelin Huang,et al.  Predicting outcomes in patients with chronic myeloid leukemia at any time during tyrosine kinase inhibitor therapy. , 2014, Clinical lymphoma, myeloma & leukemia.

[2]  Jing Ning,et al.  Estimation of time‐dependent association for bivariate failure times in the presence of a competing risk , 2014, Biometrics.

[3]  Tianxi Cai,et al.  Application of the Time‐Dependent ROC Curves for Prognostic Accuracy with Multiple Biomarkers , 2006, Biometrics.

[4]  Tamraparni Dasu,et al.  Inference for the proportional mean residual life model , 2003 .

[5]  Frank Proschan,et al.  Mean Residual Life: Theory and Applications , 1988 .

[6]  David C. Schmittlein,et al.  The Median Residual Lifetime: A Characterization Theorem and an Application , 1981, Oper. Res..

[7]  Z. Ying,et al.  Rank-based inference for the accelerated failure time model , 2003 .

[8]  Hein Putter,et al.  Dynamic predicting by landmarking as an alternative for multi-state modeling: an application to acute lymphoid leukemia data , 2008, Lifetime data analysis.

[9]  Mai Zhou,et al.  Censored quantile regression for residual lifetimes , 2012, Lifetime data analysis.

[10]  Tianxi Cai,et al.  Evaluating Prediction Rules for t-Year Survivors With Censored Regression Models , 2007 .

[11]  Sin-Ho Jung,et al.  Regression on Quantile Residual Life , 2009, Biometrics.

[12]  Z. Ying,et al.  A resampling method based on pivotal estimating functions , 1994 .

[13]  Sin-Ho Jung,et al.  Nonparametric Inference on Median Residual Life Function , 2008, Biometrics.

[14]  Xin-Yuan Song,et al.  Mean residual life models with time-dependent coefficients under right censoring , 2012 .

[15]  E. Langford,et al.  On the determination of a distribution by its median residual life function: a functional equation , 1984, Journal of Applied Probability.

[16]  Yanyuan Ma,et al.  ANALYSIS ON CENSORED QUANTILE RESIDUAL LIFE MODEL VIA SPLINE SMOOTHING. , 2012, Statistica Sinica.

[17]  Z. Ying,et al.  A simple resampling method by perturbing the minimand , 2001 .

[18]  J. Fine,et al.  Competing Risks Quantile Regression , 2009 .

[19]  Patrick Royston,et al.  Comparison between splines and fractional polynomials for multivariable model building with continuous covariates: a simulation study with continuous response , 2013, Statistics in medicine.

[20]  Dimitris Rizopoulos,et al.  Dynamic Predictions and Prospective Accuracy in Joint Models for Longitudinal and Time‐to‐Event Data , 2011, Biometrics.

[21]  Min Zhu,et al.  Quantile regression without the curse of unsmoothness , 2009, Comput. Stat. Data Anal..

[22]  R. Koenker.  Quantile Regression: Name Index , 2005 .

[23]  Jianhua Z. Huang,et al.  Varying‐coefficient models and basis function approximations for the analysis of repeated measurements , 2002 .

[24]  Yingye Zheng,et al.  Partly Conditional Survival Models for Longitudinal Data , 2005, Biometrics.

[25]  P. Royston,et al.  Regression using fractional polynomials of continuous covariates: parsimonious parametric modelling. , 1994 .

[26]  Lan Wang,et al.  Locally Weighted Censored Quantile Regression , 2009 .

[27]  Zhiliang Ying,et al.  Survival analysis with median regression models , 1995 .

[28]  J. Robins,et al.  Time-dependent cross ratio estimation for bivariate failure times. , 2011, Biometrika.

[29]  Grace L. Yang.  ESTIMATION OF A BIOMETRIC FUNCTION , 1978 .

[30]  Yijian Huang,et al.  QUANTILE CALCULUS AND CENSORED REGRESSION. , 2010, Annals of statistics.

[31]  Limin Peng,et al.  Survival Analysis With Quantile Regression Models , 2008 .

[32]  N P Jewell,et al.  Semiparametric Estimation of Proportional Mean Residual Life Model in Presence of Censoring , 2005, Biometrics.

[33]  Stephen Portnoy,et al.  Censored Regression Quantiles , 2003 .

[34]  H. V. Houwelingen.  Dynamic Prediction by Landmarking in Event History Analysis , 2007 .