Sparse generalized functional linear model for predicting remission status of depression patients.

Yashu Liu, Zhi Nie, Jiayu Zhou, Michael Farnum, Vaibhav A. Narayan, Gayle Wittenberg, Jieping Ye

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Complex diseases such as major depression affect people over time in complicated patterns. Longitudinal data analysis is thus crucial for understanding and prognosis of such diseases and has received considerable attention in the biomedical research community. Traditional classification and regression methods have been commonly applied in a simple (controlled) clinical setting with a small number of time points. However, these methods cannot be easily extended to the more general setting for longitudinal analysis, as they are not inherently built for time-dependent data. Functional regression, in contrast, is capable of identifying the relationship between features and outcomes along with time information by assuming features and/or outcomes as random functions over time rather than independent random variables. In this paper, we propose a novel sparse generalized functional linear model for the prediction of treatment remission status of the depression participants with longitudinal features. Compared to traditional functional regression models, our model enables high-dimensional learning, smoothness of functional coefficients, longitudinal feature selection and interpretable estimation of functional coefficients. Extensive experiments have been conducted on the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) data set and the results show that the proposed sparse functional regression method achieves significantly higher prediction power than existing approaches.

Original languageEnglish (US)
Pages (from-to)364-375
Number of pages12
JournalPacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
StatePublished - 2014
Externally publishedYes

Fingerprint

Linear Models
Depression
Biomedical Research
Learning
Therapeutics

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Sparse generalized functional linear model for predicting remission status of depression patients. / Liu, Yashu; Nie, Zhi; Zhou, Jiayu; Farnum, Michael; Narayan, Vaibhav A.; Wittenberg, Gayle; Ye, Jieping.

In: Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing, 2014, p. 364-375.

Research output: Contribution to journalArticle

Liu, Yashu ; Nie, Zhi ; Zhou, Jiayu ; Farnum, Michael ; Narayan, Vaibhav A. ; Wittenberg, Gayle ; Ye, Jieping. / Sparse generalized functional linear model for predicting remission status of depression patients. In: Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing. 2014 ; pp. 364-375.
@article{10fdf1ac9b9a499d83239ebd6f2beadc,
title = "Sparse generalized functional linear model for predicting remission status of depression patients.",
abstract = "Complex diseases such as major depression affect people over time in complicated patterns. Longitudinal data analysis is thus crucial for understanding and prognosis of such diseases and has received considerable attention in the biomedical research community. Traditional classification and regression methods have been commonly applied in a simple (controlled) clinical setting with a small number of time points. However, these methods cannot be easily extended to the more general setting for longitudinal analysis, as they are not inherently built for time-dependent data. Functional regression, in contrast, is capable of identifying the relationship between features and outcomes along with time information by assuming features and/or outcomes as random functions over time rather than independent random variables. In this paper, we propose a novel sparse generalized functional linear model for the prediction of treatment remission status of the depression participants with longitudinal features. Compared to traditional functional regression models, our model enables high-dimensional learning, smoothness of functional coefficients, longitudinal feature selection and interpretable estimation of functional coefficients. Extensive experiments have been conducted on the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) data set and the results show that the proposed sparse functional regression method achieves significantly higher prediction power than existing approaches.",
author = "Yashu Liu and Zhi Nie and Jiayu Zhou and Michael Farnum and Narayan, {Vaibhav A.} and Gayle Wittenberg and Jieping Ye",
year = "2014",
language = "English (US)",
pages = "364--375",
journal = "Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing",
issn = "2335-6936",

}

TY - JOUR

T1 - Sparse generalized functional linear model for predicting remission status of depression patients.

AU - Liu, Yashu

AU - Nie, Zhi

AU - Zhou, Jiayu

AU - Farnum, Michael

AU - Narayan, Vaibhav A.

AU - Wittenberg, Gayle

AU - Ye, Jieping

PY - 2014

Y1 - 2014

N2 - Complex diseases such as major depression affect people over time in complicated patterns. Longitudinal data analysis is thus crucial for understanding and prognosis of such diseases and has received considerable attention in the biomedical research community. Traditional classification and regression methods have been commonly applied in a simple (controlled) clinical setting with a small number of time points. However, these methods cannot be easily extended to the more general setting for longitudinal analysis, as they are not inherently built for time-dependent data. Functional regression, in contrast, is capable of identifying the relationship between features and outcomes along with time information by assuming features and/or outcomes as random functions over time rather than independent random variables. In this paper, we propose a novel sparse generalized functional linear model for the prediction of treatment remission status of the depression participants with longitudinal features. Compared to traditional functional regression models, our model enables high-dimensional learning, smoothness of functional coefficients, longitudinal feature selection and interpretable estimation of functional coefficients. Extensive experiments have been conducted on the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) data set and the results show that the proposed sparse functional regression method achieves significantly higher prediction power than existing approaches.

AB - Complex diseases such as major depression affect people over time in complicated patterns. Longitudinal data analysis is thus crucial for understanding and prognosis of such diseases and has received considerable attention in the biomedical research community. Traditional classification and regression methods have been commonly applied in a simple (controlled) clinical setting with a small number of time points. However, these methods cannot be easily extended to the more general setting for longitudinal analysis, as they are not inherently built for time-dependent data. Functional regression, in contrast, is capable of identifying the relationship between features and outcomes along with time information by assuming features and/or outcomes as random functions over time rather than independent random variables. In this paper, we propose a novel sparse generalized functional linear model for the prediction of treatment remission status of the depression participants with longitudinal features. Compared to traditional functional regression models, our model enables high-dimensional learning, smoothness of functional coefficients, longitudinal feature selection and interpretable estimation of functional coefficients. Extensive experiments have been conducted on the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) data set and the results show that the proposed sparse functional regression method achieves significantly higher prediction power than existing approaches.

UR - http://www.scopus.com/inward/record.url?scp=84905882514&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905882514&partnerID=8YFLogxK

M3 - Article

C2 - 24297562

AN - SCOPUS:84905882514

SP - 364

EP - 375

JO - Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing

JF - Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing

SN - 2335-6936

ER -