EUVIMEDSkopri EUVIMED
ÜbersichtsarbeitOpen access · CC BY 4.0

The importance of graph databases and graph learning for clinical applications

Daniel Walke iD, Daniel Micheel, Kay Schallert, Thilo Muth iD, David Broneske, Gunter Saake, Robert Heyer

Database · 2024-01-20 · 2024

DOI: 10.1093/database/baad045 ↗

At a glance

Übersichtsarbeit in Database, published online on 2023-07-10. Written by Daniel Walke and 6 co-authors. Institution: Bioprocess Engineering, Otto von Guericke University, Universitätsplatz 2, Magdeburg 39106, Germany. Major MEDLINE topics: Algorithms, Database Management Systems. Cited 16 times so far (Crossref); 204 references. The full text is freely available (open access, CC BY 4.0). Funded by: German Research Foundation.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

The increasing amount and complexity of clinical data require an appropriate way of storing and analyzing those data. Traditional approaches use a tabular structure (relational databases) for storing data and thereby complicate storing and retrieving interlinked data from the clinical domain. Graph databases provide a great solution for this by storing data in a graph as nodes (vertices) that are connected by edges (links). The underlying graph structure can be used for the subsequent data analysis (graph learning). Graph learning consists of two parts: graph representation learning and graph analytics. Graph representation learning aims to reduce high-dimensional input graphs to low-dimensional representations. Then, graph analytics uses the obtained representations for analytical tasks like visualization, classification, link prediction and clustering which can be used to solve domain-specific problems. In this survey, we review current state-of-the-art graph database management systems, graph learning algorithms and a variety of graph applications in the clinical domain. Furthermore, we provide a comprehensive use case for a clearer understanding of complex graph learning algorithms. Graphical abstract

Subjects

MeSH terms (MEDLINE)

AlgorithmsDatabase Management SystemsDatabases, FactualCluster Analysis

Authors and institutions

  • Bioprocess Engineering, Otto von Guericke University, Universitätsplatz 2, Magdeburg 39106, Germany.
  • Database and Software Engineering Group, Otto von Guericke University, Universitätsplatz 2, Magdeburg 39106, Germany.
  • Multidimensional Omics Analyses Group, Leibniz-Institut für Analytische Wissenschaften-ISAS-e.V., Bunsen-Kirchhoff-Straße 11, Dortmund 44139, Germany.
  • Section eScience (S.3), Federal Institute for Materials Research and Testing (BAM), Unter den Eichen 87, Berlin 12205, Germany.
  • Infrastructure and Methods, German Center for Higher Education Research and Science Studies (DZHW), Lange Laube 12, Hannover 30159, Germany.
  • Faculty of Technology, Bielefeld University, Universitätsstraße 25, Bielefeld 33615, Germany.

ORCID profiles: Daniel Walke, Thilo Muth

Funding

  • German Research Foundation

Cite

APA

Walke, D., Micheel, D., Schallert, K., Muth, T., Broneske, D., Saake, G., & Heyer, R. (2024). The importance of graph databases and graph learning for clinical applications. Database, 2024. https://doi.org/10.1093/database/baad045

Vancouver

Walke D, Micheel D, Schallert K, Muth T, Broneske D, Saake G, et al. The importance of graph databases and graph learning for clinical applications. Database. 2024;2024. doi:10.1093/database/baad045

BibTeX
@article{Walke2024,
  author = {Walke, Daniel and Micheel, Daniel and Schallert, Kay and Muth, Thilo and Broneske, David and Saake, Gunter and Heyer, Robert},
  title = {The importance of graph databases and graph learning for clinical applications},
  journal = {Database},
  year = {2024},
  volume = {2024},
  doi = {10.1093/database/baad045}
}
Start for free →