May  2019, 2(2): 169-181. doi: 10.3934/mfc.2019012

An RKHS approach to estimate individualized treatment rules based on functional predictors

1. 

Department of Mathematics, Hong Kong Baptist University, Kowloon, Hong Kong, China

2. 

School of Mathematical Sciences, Shanghai Key Laboratory for Contemporary Applied Mathematics, Fudan University, Shanghai, 200433, China

* Corresponding author: Lei Shi

Published  July 2019

In recent years there has been massive interest in precision medicine, which aims to tailor treatment plans to the individual characteristics of each patient. This paper studies the estimation of individualized treatment rules (ITR) based on functional predictors such as images or spectra. We consider a reproducing kernel Hilbert space (RKHS) approach to learn the optimal ITR which maximizes the expected clinical outcome. The algorithm can be conveniently implemented although it involves infinite-dimensional functional data. We provide convergence rate for prediction under mild conditions, which is jointly determined by both the covariance kernel and the reproducing kernel.

Citation: Jun Fan, Fusheng Lv, Lei Shi. An RKHS approach to estimate individualized treatment rules based on functional predictors. Mathematical Foundations of Computing, 2019, 2 (2) : 169-181. doi: 10.3934/mfc.2019012
References:
[1]

T. T. Cai and M. Yuan, Minimax and adaptive prediction for functional linear regression, Journal of the American Statistical Association, 107 (2012), 1201–1216. doi: 10.1080/01621459.2012.716337. Google Scholar

[2]

A. Ciarleglio, E. Petkova, T. Tarpey and R. T. Ogden, Flexible functional regression methods for estimating individualized treatment regimes, 5 (2016), 185–199. doi: 10.1002/sta4.114. Google Scholar

[3]

J. FanT. HuQ. Wu and D. X. Zhou, Consistency analysis of an empirical minimum error entropy algorithm, Applied and Computational Harmonic Analysis, 41 (2016), 164-189. doi: 10.1016/j.acha.2014.12.005. Google Scholar

[4]

X. GuoJ. Fan and D. X. Zhou, Sparsity and error analysis of empirical feature-based regularization schemes, Journal of Machine Learning Research, 17 (2016), 3058-3091. Google Scholar

[5]

Z. C. Guo, S. B. Lin and D. X. Zhou, Learning theory of distributed spectral algorithms, Inverse Problems, 33 (2017), 074009, 29pp. doi: 10.1088/1361-6420/aa72b2. Google Scholar

[6]

T. HuJ. FanQ. Wu and D. X. Zhou, Regularization schemes for minimum error entropy principle, Analysis and Applications, 13 (2015), 437-455. doi: 10.1142/S0219530514500110. Google Scholar

[7]

S. B. Lin, X. Guo and D. X. Zhou, Distributed learning with regularized least squares, Journal of Machine Learning Research, 18 (2017), Paper No. 92, 31 pp. Google Scholar

[8]

I. McKeague and M. Qian, Estimation of treatment policies based on functional predictors, Statistica Sinica, 24 (2014), 1461–1485. Google Scholar

[9]

S. A. Murphy, Optimal dynamic treatment regimes, Journal of the Royal Statistical Society: Series B (Statistical Methodology), 65 (2003), 331–366. doi: 10.1111/1467-9868.00389. Google Scholar

[10]

S. A. Murphy, An experimental design for the development of adaptive treatment strategies, Statistics in Medicine, 24 (2005), 1455–1481. doi: 10.1002/sim.2022. Google Scholar

[11]

Z. L. Qi and Y. F. Liu, D-learning to estimate optimal individual treatment rules, Electronic Journal of Statistics, 12 (2018), 3601–3638. doi: 10.1214/18-EJS1480. Google Scholar

[12]

J. O. Ramsay and B. W. Silverman, Applied Functional Data Analysis, Springer, New York, 2002. doi: 10.1007/b98886. Google Scholar

[13]

L. Shi, Distributed Learning with Indefinite Kernels, Analysis and Applications, 2019. doi: 10.1142/S021953051850032X. Google Scholar

[14]

R. Song, W. Wang, D. Zeng and M. R. Kosorok, Penalized q-learning for dynamic treatment regimes, Statistica Sinica, 25 (2015), 901–920. Google Scholar

[15]

M. Yuan and T. T. Cai, A reproducing kernel Hilbert space approach to functional linear regression, The Annals of Statistics, 38 (2010), 3412–3444. doi: 10.1214/09-AOS772. Google Scholar

[16]

T. Zhang, Learning bounds for kernel regression using effective data dimensionality, Neural Computation, 17 (2005), 2077-2098. doi: 10.1162/0899766054323008. Google Scholar

[17]

Y. Zhao, D. Zeng, A. J. Rush and M. R. Kosorok, Estimating individualized treatment rules using outcome weighted learning, Journal of the American Statistical Association, 107 (2012), 1106–1118. doi: 10.1080/01621459.2012.695674. Google Scholar

show all references

References:
[1]

T. T. Cai and M. Yuan, Minimax and adaptive prediction for functional linear regression, Journal of the American Statistical Association, 107 (2012), 1201–1216. doi: 10.1080/01621459.2012.716337. Google Scholar

[2]

A. Ciarleglio, E. Petkova, T. Tarpey and R. T. Ogden, Flexible functional regression methods for estimating individualized treatment regimes, 5 (2016), 185–199. doi: 10.1002/sta4.114. Google Scholar

[3]

J. FanT. HuQ. Wu and D. X. Zhou, Consistency analysis of an empirical minimum error entropy algorithm, Applied and Computational Harmonic Analysis, 41 (2016), 164-189. doi: 10.1016/j.acha.2014.12.005. Google Scholar

[4]

X. GuoJ. Fan and D. X. Zhou, Sparsity and error analysis of empirical feature-based regularization schemes, Journal of Machine Learning Research, 17 (2016), 3058-3091. Google Scholar

[5]

Z. C. Guo, S. B. Lin and D. X. Zhou, Learning theory of distributed spectral algorithms, Inverse Problems, 33 (2017), 074009, 29pp. doi: 10.1088/1361-6420/aa72b2. Google Scholar

[6]

T. HuJ. FanQ. Wu and D. X. Zhou, Regularization schemes for minimum error entropy principle, Analysis and Applications, 13 (2015), 437-455. doi: 10.1142/S0219530514500110. Google Scholar

[7]

S. B. Lin, X. Guo and D. X. Zhou, Distributed learning with regularized least squares, Journal of Machine Learning Research, 18 (2017), Paper No. 92, 31 pp. Google Scholar

[8]

I. McKeague and M. Qian, Estimation of treatment policies based on functional predictors, Statistica Sinica, 24 (2014), 1461–1485. Google Scholar

[9]

S. A. Murphy, Optimal dynamic treatment regimes, Journal of the Royal Statistical Society: Series B (Statistical Methodology), 65 (2003), 331–366. doi: 10.1111/1467-9868.00389. Google Scholar

[10]

S. A. Murphy, An experimental design for the development of adaptive treatment strategies, Statistics in Medicine, 24 (2005), 1455–1481. doi: 10.1002/sim.2022. Google Scholar

[11]

Z. L. Qi and Y. F. Liu, D-learning to estimate optimal individual treatment rules, Electronic Journal of Statistics, 12 (2018), 3601–3638. doi: 10.1214/18-EJS1480. Google Scholar

[12]

J. O. Ramsay and B. W. Silverman, Applied Functional Data Analysis, Springer, New York, 2002. doi: 10.1007/b98886. Google Scholar

[13]

L. Shi, Distributed Learning with Indefinite Kernels, Analysis and Applications, 2019. doi: 10.1142/S021953051850032X. Google Scholar

[14]

R. Song, W. Wang, D. Zeng and M. R. Kosorok, Penalized q-learning for dynamic treatment regimes, Statistica Sinica, 25 (2015), 901–920. Google Scholar

[15]

M. Yuan and T. T. Cai, A reproducing kernel Hilbert space approach to functional linear regression, The Annals of Statistics, 38 (2010), 3412–3444. doi: 10.1214/09-AOS772. Google Scholar

[16]

T. Zhang, Learning bounds for kernel regression using effective data dimensionality, Neural Computation, 17 (2005), 2077-2098. doi: 10.1162/0899766054323008. Google Scholar

[17]

Y. Zhao, D. Zeng, A. J. Rush and M. R. Kosorok, Estimating individualized treatment rules using outcome weighted learning, Journal of the American Statistical Association, 107 (2012), 1106–1118. doi: 10.1080/01621459.2012.695674. Google Scholar

[1]

Ali Akgül, Mustafa Inc, Esra Karatas. Reproducing kernel functions for difference equations. Discrete & Continuous Dynamical Systems - S, 2015, 8 (6) : 1055-1064. doi: 10.3934/dcdss.2015.8.1055

[2]

Nigel Higson and Gennadi Kasparov. Operator K-theory for groups which act properly and isometrically on Hilbert space. Electronic Research Announcements, 1997, 3: 131-142.

[3]

Alex Castro, Wyatt Howard, Corey Shanbrom. Complete spelling rules for the Monster tower over three-space. Journal of Geometric Mechanics, 2017, 9 (3) : 317-333. doi: 10.3934/jgm.2017013

[4]

G. Calafiore, M.C. Campi. A learning theory approach to the construction of predictor models. Conference Publications, 2003, 2003 (Special) : 156-166. doi: 10.3934/proc.2003.2003.156

[5]

Daniel Alpay, Mihai Putinar, Victor Vinnikov. A Hilbert space approach to bounded analytic extension in the ball. Communications on Pure & Applied Analysis, 2003, 2 (2) : 139-145. doi: 10.3934/cpaa.2003.2.139

[6]

Anna Karczewska, Carlos Lizama. On stochastic fractional Volterra equations in Hilbert space. Conference Publications, 2007, 2007 (Special) : 541-550. doi: 10.3934/proc.2007.2007.541

[7]

Onur Alp İlhan. Solvability of some partial integral equations in Hilbert space. Communications on Pure & Applied Analysis, 2008, 7 (4) : 837-844. doi: 10.3934/cpaa.2008.7.837

[8]

Mahmoud M. El-Borai. On some fractional differential equations in the Hilbert space. Conference Publications, 2005, 2005 (Special) : 233-240. doi: 10.3934/proc.2005.2005.233

[9]

P. Chiranjeevi, V. Kannan, Sharan Gopal. Periodic points and periods for operators on hilbert space. Discrete & Continuous Dynamical Systems - A, 2013, 33 (9) : 4233-4237. doi: 10.3934/dcds.2013.33.4233

[10]

Simone Creo, Maria Rosaria Lancia, Alejandro Vélez-Santiago, Paola Vernole. Approximation of a nonlinear fractal energy functional on varying Hilbert spaces. Communications on Pure & Applied Analysis, 2018, 17 (2) : 647-669. doi: 10.3934/cpaa.2018035

[11]

Tieliang Gong, Qian Zhao, Deyu Meng, Zongben Xu. Why curriculum learning & self-paced learning work in big/noisy data: A theoretical perspective. Big Data & Information Analytics, 2016, 1 (1) : 111-127. doi: 10.3934/bdia.2016.1.111

[12]

Jiang Xie, Junfu Xu, Celine Nie, Qing Nie. Machine learning of swimming data via wisdom of crowd and regression analysis. Mathematical Biosciences & Engineering, 2017, 14 (2) : 511-527. doi: 10.3934/mbe.2017031

[13]

Xiangmin Zhang. User perceived learning from interactive searching on big medical literature data. Big Data & Information Analytics, 2017, 2 (5) : 1-16. doi: 10.3934/bdia.2017019

[14]

Matthew O. Williams, Clarence W. Rowley, Ioannis G. Kevrekidis. A kernel-based method for data-driven koopman spectral analysis. Journal of Computational Dynamics, 2015, 2 (2) : 247-265. doi: 10.3934/jcd.2015005

[15]

Steven G. Krantz and Marco M. Peloso. New results on the Bergman kernel of the worm domain in complex space. Electronic Research Announcements, 2007, 14: 35-41. doi: 10.3934/era.2007.14.35

[16]

Carla Mascia, Giancarlo Rinaldo, Massimiliano Sala. Hilbert quasi-polynomial for order domains and application to coding theory. Advances in Mathematics of Communications, 2018, 12 (2) : 287-301. doi: 10.3934/amc.2018018

[17]

Andrew E.B. Lim, John B. Moore. A path following algorithm for infinite quadratic programming on a Hilbert space. Discrete & Continuous Dynamical Systems - A, 1998, 4 (4) : 653-670. doi: 10.3934/dcds.1998.4.653

[18]

Onur Alp İlhan. Solvability of some volterra type integral equations in hilbert space. Conference Publications, 2007, 2007 (Special) : 28-34. doi: 10.3934/proc.2007.2007.28

[19]

Matthew A. Fury. Regularization for ill-posed inhomogeneous evolution problems in a Hilbert space. Conference Publications, 2013, 2013 (special) : 259-272. doi: 10.3934/proc.2013.2013.259

[20]

Raffaele Chiappinelli. Eigenvalues of homogeneous gradient mappings in Hilbert space and the Birkoff-Kellogg theorem. Conference Publications, 2007, 2007 (Special) : 260-268. doi: 10.3934/proc.2007.2007.260

 Impact Factor: 

Article outline

[Back to Top]