TY - JOUR
T1 - Quantile residual lifetime regression with functional principal component analysis of longitudinal data for dynamic prediction
AU - Lin, Xiao
AU - Li, Ruosha
AU - Yan, Fangrong
AU - Lu, Tao
AU - Huang, Xuelin
N1 - Funding Information:
The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: the research of RL was supported in part by USA NSF grant DMS 1612965. The research of FY was supported in part by National Social Science of China, Funding No. 16BTJ021. The research of X.H. was supported in part by USA NSF grant DMS 1612965, NIH grants U54 CA096300, U01 CA152958 and 5P50 CA100632.
Publisher Copyright:
© The Author(s) 2018.
PY - 2019/4/1
Y1 - 2019/4/1
N2 - Optimal therapeutic decisions can be made according to disease prognosis, where the residual lifetime is extensively used because of its straightforward interpretation and formula. To predict the residual lifetime in a dynamic manner, a longitudinal biomarker that is repeatedly measured during the post-baseline follow-up period should be included. In this article, we use functional principal component analysis, a powerful and flexible tool, to handle irregularly measured longitudinal data and extract the dominant features over a specific time interval. To capture the time-dependent trajectory pattern, a series of moving time windows are used to estimate window-specific functional principal component analysis scores, which are then combined with a quantile residual lifetime regression model to facilitate dynamic prediction. Estimation of this regression model can be achieved by solving estimating equations with the help of locating the minimizer of the L 1 -type function. Simulation studies demonstrate the advantages of our proposed method in both calibration and discrimination under various scenarios. The proposed method is applied to data from patients with chronic myeloid leukemia to illustrate its practicality, where we dynamically predict quantile residual lifetimes with longitudinal expression levels of an oncogene, BCR-ABL.
AB - Optimal therapeutic decisions can be made according to disease prognosis, where the residual lifetime is extensively used because of its straightforward interpretation and formula. To predict the residual lifetime in a dynamic manner, a longitudinal biomarker that is repeatedly measured during the post-baseline follow-up period should be included. In this article, we use functional principal component analysis, a powerful and flexible tool, to handle irregularly measured longitudinal data and extract the dominant features over a specific time interval. To capture the time-dependent trajectory pattern, a series of moving time windows are used to estimate window-specific functional principal component analysis scores, which are then combined with a quantile residual lifetime regression model to facilitate dynamic prediction. Estimation of this regression model can be achieved by solving estimating equations with the help of locating the minimizer of the L 1 -type function. Simulation studies demonstrate the advantages of our proposed method in both calibration and discrimination under various scenarios. The proposed method is applied to data from patients with chronic myeloid leukemia to illustrate its practicality, where we dynamically predict quantile residual lifetimes with longitudinal expression levels of an oncogene, BCR-ABL.
KW - Dynamic prediction
KW - functional principal component analysis
KW - longitudinal data
KW - quantile residual life
KW - survival analysis
UR - http://www.scopus.com/inward/record.url?scp=85044081823&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85044081823&partnerID=8YFLogxK
U2 - 10.1177/0962280217753466
DO - 10.1177/0962280217753466
M3 - Article
C2 - 29402190
AN - SCOPUS:85044081823
SN - 0962-2802
VL - 28
SP - 1216
EP - 1229
JO - Statistical Methods in Medical Research
JF - Statistical Methods in Medical Research
IS - 4
ER -