Novel methods of incorporating time in longitudinal multivariate analysis reveals hidden associations with disease activity in systemic lupus erythematosus

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Objective: Systemic lupus erythematosus (SLE) is a multisystem autoimmune disease. SLE is characterized by high inter-patient variability, including fluctuations over time, a factor which most biomarker studies omit from consideration. We investigated relationships between disease activity and biomarker expression in SLE, using novel methods to control for time-dependent variability, in a proof-of-concept study to evaluate whether doing so revealed additional information. Methods: We measured 4 serum biomarkers (MIF, CCL2, CCL19, and CXCL10) and 13 routine clinical laboratory parameters, alongside disease activity measured by the SLE disease activity index-2k (SLEDAI-2k), collected longitudinally. We analyzed these data with unsupervised learning methods via ensemble clustering, incorporating temporal relationships using dynamic time warping for distance metric calculation. Results: Data from 843 visits in 110 patients (median age 47, 83% female) demonstrated highly heterogeneous time-dependent relationships between disease activity and biomarkers. Unbiased magnitude-based hierarchical clustering of biomarker expression levels isolated a patient subset (n = 9) with distinctively heterogeneous expression of the 17 biological parameters, and who had MIF, CCL2, CCL19, and CXCL10 levels that were higher and more strongly associated with disease activity, based on leave-one-out cross-validated regression analysis. In the remaining subgroup, a time-dependent regression model revealed significantly stronger predictive power of biomarkers for disease activity, compared to a time-agnostic regression model. Despite no significant difference in simple magnitude, using dynamic time warping analysis to align longitudinal profiles revealed a large subset (n = 69) with significantly stronger associations between biological parameters and disease activity. This subgroup had significantly lower flare rates, disease activity and damage scores, suggesting this clustering is clinically meaningful. Conclusions: These results suggest associations between biological parameters and disease activity in SLE exist in a multi-dimensional time-dependent pattern, with implications for the analysis of biomarkers in SLE often used to identify therapeutic targets. Novel methods to analyse high-dimensional data and control for time-dependent variability may have broad utility in the study complex relationships between clinical and biological parameters.

Original languageEnglish
Article number01649
Number of pages10
JournalFrontiers in Immunology
Volume10
Issue numberJULY
DOIs
Publication statusPublished - 17 Jul 2019

Keywords

  • Biomarkers
  • Clustering
  • Longitudinal analysis
  • Regression models
  • Systemic lupus erythematosus

Cite this

@article{3c342ea9ad9645bea3e8e2e03db5fe45,
title = "Novel methods of incorporating time in longitudinal multivariate analysis reveals hidden associations with disease activity in systemic lupus erythematosus",
abstract = "Objective: Systemic lupus erythematosus (SLE) is a multisystem autoimmune disease. SLE is characterized by high inter-patient variability, including fluctuations over time, a factor which most biomarker studies omit from consideration. We investigated relationships between disease activity and biomarker expression in SLE, using novel methods to control for time-dependent variability, in a proof-of-concept study to evaluate whether doing so revealed additional information. Methods: We measured 4 serum biomarkers (MIF, CCL2, CCL19, and CXCL10) and 13 routine clinical laboratory parameters, alongside disease activity measured by the SLE disease activity index-2k (SLEDAI-2k), collected longitudinally. We analyzed these data with unsupervised learning methods via ensemble clustering, incorporating temporal relationships using dynamic time warping for distance metric calculation. Results: Data from 843 visits in 110 patients (median age 47, 83{\%} female) demonstrated highly heterogeneous time-dependent relationships between disease activity and biomarkers. Unbiased magnitude-based hierarchical clustering of biomarker expression levels isolated a patient subset (n = 9) with distinctively heterogeneous expression of the 17 biological parameters, and who had MIF, CCL2, CCL19, and CXCL10 levels that were higher and more strongly associated with disease activity, based on leave-one-out cross-validated regression analysis. In the remaining subgroup, a time-dependent regression model revealed significantly stronger predictive power of biomarkers for disease activity, compared to a time-agnostic regression model. Despite no significant difference in simple magnitude, using dynamic time warping analysis to align longitudinal profiles revealed a large subset (n = 69) with significantly stronger associations between biological parameters and disease activity. This subgroup had significantly lower flare rates, disease activity and damage scores, suggesting this clustering is clinically meaningful. Conclusions: These results suggest associations between biological parameters and disease activity in SLE exist in a multi-dimensional time-dependent pattern, with implications for the analysis of biomarkers in SLE often used to identify therapeutic targets. Novel methods to analyse high-dimensional data and control for time-dependent variability may have broad utility in the study complex relationships between clinical and biological parameters.",
keywords = "Biomarkers, Clustering, Longitudinal analysis, Regression models, Systemic lupus erythematosus",
author = "Nim, {Hieu T.} and Kathryn Connelly and Vincent, {Fabien Bernard} and Francois Petitjean and Alberta Hoi and Rachel Koelmeyer and Sarah Boyd and Morand, {Eric F.}",
year = "2019",
month = "7",
day = "17",
doi = "10.3389/fimmu.2019.01649",
language = "English",
volume = "10",
journal = "Frontiers in Immunology",
issn = "1664-3224",
publisher = "Frontiers Media",
number = "JULY",

}

TY - JOUR

T1 - Novel methods of incorporating time in longitudinal multivariate analysis reveals hidden associations with disease activity in systemic lupus erythematosus

AU - Nim, Hieu T.

AU - Connelly, Kathryn

AU - Vincent, Fabien Bernard

AU - Petitjean, Francois

AU - Hoi, Alberta

AU - Koelmeyer, Rachel

AU - Boyd, Sarah

AU - Morand, Eric F.

PY - 2019/7/17

Y1 - 2019/7/17

N2 - Objective: Systemic lupus erythematosus (SLE) is a multisystem autoimmune disease. SLE is characterized by high inter-patient variability, including fluctuations over time, a factor which most biomarker studies omit from consideration. We investigated relationships between disease activity and biomarker expression in SLE, using novel methods to control for time-dependent variability, in a proof-of-concept study to evaluate whether doing so revealed additional information. Methods: We measured 4 serum biomarkers (MIF, CCL2, CCL19, and CXCL10) and 13 routine clinical laboratory parameters, alongside disease activity measured by the SLE disease activity index-2k (SLEDAI-2k), collected longitudinally. We analyzed these data with unsupervised learning methods via ensemble clustering, incorporating temporal relationships using dynamic time warping for distance metric calculation. Results: Data from 843 visits in 110 patients (median age 47, 83% female) demonstrated highly heterogeneous time-dependent relationships between disease activity and biomarkers. Unbiased magnitude-based hierarchical clustering of biomarker expression levels isolated a patient subset (n = 9) with distinctively heterogeneous expression of the 17 biological parameters, and who had MIF, CCL2, CCL19, and CXCL10 levels that were higher and more strongly associated with disease activity, based on leave-one-out cross-validated regression analysis. In the remaining subgroup, a time-dependent regression model revealed significantly stronger predictive power of biomarkers for disease activity, compared to a time-agnostic regression model. Despite no significant difference in simple magnitude, using dynamic time warping analysis to align longitudinal profiles revealed a large subset (n = 69) with significantly stronger associations between biological parameters and disease activity. This subgroup had significantly lower flare rates, disease activity and damage scores, suggesting this clustering is clinically meaningful. Conclusions: These results suggest associations between biological parameters and disease activity in SLE exist in a multi-dimensional time-dependent pattern, with implications for the analysis of biomarkers in SLE often used to identify therapeutic targets. Novel methods to analyse high-dimensional data and control for time-dependent variability may have broad utility in the study complex relationships between clinical and biological parameters.

AB - Objective: Systemic lupus erythematosus (SLE) is a multisystem autoimmune disease. SLE is characterized by high inter-patient variability, including fluctuations over time, a factor which most biomarker studies omit from consideration. We investigated relationships between disease activity and biomarker expression in SLE, using novel methods to control for time-dependent variability, in a proof-of-concept study to evaluate whether doing so revealed additional information. Methods: We measured 4 serum biomarkers (MIF, CCL2, CCL19, and CXCL10) and 13 routine clinical laboratory parameters, alongside disease activity measured by the SLE disease activity index-2k (SLEDAI-2k), collected longitudinally. We analyzed these data with unsupervised learning methods via ensemble clustering, incorporating temporal relationships using dynamic time warping for distance metric calculation. Results: Data from 843 visits in 110 patients (median age 47, 83% female) demonstrated highly heterogeneous time-dependent relationships between disease activity and biomarkers. Unbiased magnitude-based hierarchical clustering of biomarker expression levels isolated a patient subset (n = 9) with distinctively heterogeneous expression of the 17 biological parameters, and who had MIF, CCL2, CCL19, and CXCL10 levels that were higher and more strongly associated with disease activity, based on leave-one-out cross-validated regression analysis. In the remaining subgroup, a time-dependent regression model revealed significantly stronger predictive power of biomarkers for disease activity, compared to a time-agnostic regression model. Despite no significant difference in simple magnitude, using dynamic time warping analysis to align longitudinal profiles revealed a large subset (n = 69) with significantly stronger associations between biological parameters and disease activity. This subgroup had significantly lower flare rates, disease activity and damage scores, suggesting this clustering is clinically meaningful. Conclusions: These results suggest associations between biological parameters and disease activity in SLE exist in a multi-dimensional time-dependent pattern, with implications for the analysis of biomarkers in SLE often used to identify therapeutic targets. Novel methods to analyse high-dimensional data and control for time-dependent variability may have broad utility in the study complex relationships between clinical and biological parameters.

KW - Biomarkers

KW - Clustering

KW - Longitudinal analysis

KW - Regression models

KW - Systemic lupus erythematosus

UR - http://www.scopus.com/inward/record.url?scp=85069540354&partnerID=8YFLogxK

U2 - 10.3389/fimmu.2019.01649

DO - 10.3389/fimmu.2019.01649

M3 - Article

VL - 10

JO - Frontiers in Immunology

JF - Frontiers in Immunology

SN - 1664-3224

IS - JULY

M1 - 01649

ER -