Big Data Approaches in Heart Failure Research

  • PDF / 695,422 Bytes
  • 12 Pages / 595.276 x 790.866 pts Page_size
  • 56 Downloads / 242 Views

DOWNLOAD

REPORT


TRANSLATIONAL RESEARCH IN HEART FAILURE (J. BACKS AND M. VAN DEN HOOGENHOF, SECTION EDITORS)

Big Data Approaches in Heart Failure Research Jan D. Lanzer 1,2,3 & Florian Leuschner 4,5 & Rafael Kramann 6,7 & Rebecca T. Levinson 1,3 & Julio Saez-Rodriguez 1,8

# The Author(s) 2020

Abstract Purpose of Review The goal of this review is to summarize the state of big data analyses in the study of heart failure (HF). We discuss the use of big data in the HF space, focusing on “omics” and clinical data. We address some limitations of this data, as well as their future potential. Recent Findings Omics are providing insight into plasmal and myocardial molecular profiles in HF patients. The introduction of single cell and spatial technologies is a major advance that will reshape our understanding of cell heterogeneity and function as well as tissue architecture. Clinical data analysis focuses on HF phenotyping and prognostic modeling. Summary Big data approaches are increasingly common in HF research. The use of methods designed for big data, such as machine learning, may help elucidate the biology underlying HF. However, important challenges remain in the translation of this knowledge into improvements in clinical care. Keywords Heart failure . Big data . Omics . Single cell . Machine learning

Introduction In the past 5–10 years, big data has become an integral part of the study of cardiovascular disease. There are many definitions of big data; however, one definition is data large or complex enough that they cannot be analyzed or interpreted by traditional methods. As a result, computational methods, primarily statistics and machine learning (ML), are used to analyze this data. Several big data technologies are starting

to be applied in the clinic: for example, genomics and transcriptomics are used for patient stratification in breast cancer diagnosis and treatment [1, 2] and can be used to determine acute cardiac allograft rejection [3, 4]. However, due to challenges in clinical implementation and questions about the benefits of these methods [5], most big data approaches are implemented in preclinical research. Chronic heart failure (HF) is a prime target for big data research due to the complex etiology of the syndrome, the

Rebecca T. Levinson and Julio Saez-Rodriguez - co-advised the review This article is part of the Topical Collection on Translational Research in Heart Failure * Julio Saez-Rodriguez [email protected]

5

DZHK (German Centre for Cardiovascular Research), Heidelberg, Germany

1

Institute for Computational Biomedicine, Bioquant, Heidelberg University, Faculty of Medicine, and Heidelberg University Hospital, Heidelberg, Germany

6

Department of Nephrology and Clinical Immunology, RWTH Aachen University, Aachen, Germany

2

Faculty of Biosciences, Heidelberg University, Heidelberg, Germany

7

3

Internal Medicine II, Heidelberg University Hospital, Heidelberg, Germany

Department of Internal Medicine, Nephrology and Transplantation, Erasmus Medical Center, Rotterdam, The Netherla