In:
PLOS Computational Biology, Public Library of Science (PLoS), Vol. 17, No. 2 ( 2021-2-12), p. e1008735-
Abstract:
In this work, we introduce an entirely data-driven and automated approach to reveal disease-associated biomarker and risk factor networks from heterogeneous and high-dimensional healthcare data. Our workflow is based on Bayesian networks, which are a popular tool for analyzing the interplay of biomarkers. Usually, data require extensive manual preprocessing and dimension reduction to allow for effective learning of Bayesian networks. For heterogeneous data, this preprocessing is hard to automatize and typically requires domain-specific prior knowledge. We here combine Bayesian network learning with hierarchical variable clustering in order to detect groups of similar features and learn interactions between them entirely automated. We present an optimization algorithm for the adaptive refinement of such group Bayesian networks to account for a specific target variable, like a disease. The combination of Bayesian networks, clustering, and refinement yields low-dimensional but disease-specific interaction networks. These networks provide easily interpretable, yet accurate models of biomarker interdependencies. We test our method extensively on simulated data, as well as on data from the Study of Health in Pomerania (SHIP-TREND), and demonstrate its effectiveness using non-alcoholic fatty liver disease and hypertension as examples. We show that the group network models outperform available biomarker scores, while at the same time, they provide an easily interpretable interaction network.
Type of Medium:
Online Resource
ISSN:
1553-7358
DOI:
10.1371/journal.pcbi.1008735
DOI:
10.1371/journal.pcbi.1008735.g001
DOI:
10.1371/journal.pcbi.1008735.g002
DOI:
10.1371/journal.pcbi.1008735.g003
DOI:
10.1371/journal.pcbi.1008735.g004
DOI:
10.1371/journal.pcbi.1008735.g005
DOI:
10.1371/journal.pcbi.1008735.g006
DOI:
10.1371/journal.pcbi.1008735.t001
DOI:
10.1371/journal.pcbi.1008735.t002
DOI:
10.1371/journal.pcbi.1008735.t003
DOI:
10.1371/journal.pcbi.1008735.s001
DOI:
10.1371/journal.pcbi.1008735.s002
DOI:
10.1371/journal.pcbi.1008735.s003
DOI:
10.1371/journal.pcbi.1008735.s004
DOI:
10.1371/journal.pcbi.1008735.s005
DOI:
10.1371/journal.pcbi.1008735.s006
DOI:
10.1371/journal.pcbi.1008735.s007
DOI:
10.1371/journal.pcbi.1008735.r001
DOI:
10.1371/journal.pcbi.1008735.r002
DOI:
10.1371/journal.pcbi.1008735.r003
DOI:
10.1371/journal.pcbi.1008735.r004
Language:
English
Publisher:
Public Library of Science (PLoS)
Publication Date:
2021
detail.hit.zdb_id:
2193340-6
Bookmarklink