Multiple kernel learning with random effects for predicting longitudinal outcomes and data integration.

TitleMultiple kernel learning with random effects for predicting longitudinal outcomes and data integration.
Publication TypeJournal Article
Year of Publication2015
AuthorsChen, Tianle, Donglin Zeng, and Yuanjia Wang
JournalBiometrics
Volume71
Issue4
Pagination918-28
Date Published2015 Dec
ISSN1541-0420
KeywordsAlgorithms, Alzheimer Disease, Biometry, Computer Simulation, Disease Progression, Humans, Huntington Disease, Longitudinal Studies, Machine Learning, Models, Statistical, Statistics, Nonparametric, Support Vector Machine
Abstract

Predicting disease risk and progression is one of the main goals in many clinical research studies. Cohort studies on the natural history and etiology of chronic diseases span years and data are collected at multiple visits. Although, kernel-based statistical learning methods are proven to be powerful for a wide range of disease prediction problems, these methods are only well studied for independent data, but not for longitudinal data. It is thus important to develop time-sensitive prediction rules that make use of the longitudinal nature of the data. In this paper, we develop a novel statistical learning method for longitudinal data by introducing subject-specific short-term and long-term latent effects through a designed kernel to account for within-subject correlation of longitudinal measurements. Since the presence of multiple sources of data is increasingly common, we embed our method in a multiple kernel learning framework and propose a regularized multiple kernel statistical learning with random effects to construct effective nonparametric prediction rules. Our method allows easy integration of various heterogeneous data sources and takes advantage of correlation among longitudinal measures to increase prediction power. We use different kernels for each data source taking advantage of the distinctive feature of each data modality, and then optimally combine data across modalities. We apply the developed methods to two large epidemiological studies, one on Huntington's disease and the other on Alzheimer's Disease (Alzheimer's Disease Neuroimaging Initiative, ADNI) where we explore a unique opportunity to combine imaging and genetic data to study prediction of mild cognitive impairment, and show a substantial gain in performance while accounting for the longitudinal aspect of the data.

DOI10.1111/biom.12343
Alternate JournalBiometrics
Original PublicationMultiple kernel learning with random effects for predicting longitudinal outcomes and data integration.
PubMed ID26177419
PubMed Central IDPMC4713389
Grant ListR01 CA082659 / CA / NCI NIH HHS / United States
U01 AG024904 / AG / NIA NIH HHS / United States
R01 GM047845 / GM / NIGMS NIH HHS / United States
NS073671 / NS / NINDS NIH HHS / United States
R01 NS073671 / NS / NINDS NIH HHS / United States
NS082062 / NS / NINDS NIH HHS / United States
UL1 RR025747 / RR / NCRR NIH HHS / United States
P01CA142538 / CA / NCI NIH HHS / United States
P01 CA142538 / CA / NCI NIH HHS / United States
NUL1 RR025747 / RR / NCRR NIH HHS / United States
U01 NS082062 / NS / NINDS NIH HHS / United States