Edges are all you need: Potential of medical time series analysis on complete blood count data with graph neural networks.

Journal: PloS one
Published Date: Jul 8, 2025

Abstract

PURPOSE: Machine learning is a powerful tool to develop algorithms for clinical diagnosis. However, standard machine learning algorithms are not perfectly suited for clinical data since the data are interconnected and may contain time series. As shown for recommender systems and molecular property predictions, Graph Neural Networks (GNNs) may represent a powerful alternative to exploit the inherently graph-based properties of clinical data. The main goal of this study is to evaluate when GNNs represent a valuable alternative for analyzing large clinical data from the clinical routine on the example of Complete Blood Count Data.

Authors

  • Daniel Walke
    Bioprocess Engineering, Otto von Guericke University, Universitätsplatz 2, Magdeburg, Germany.
  • Daniel Steinbach
    Institute of Laboratory Medicine, Clinical Chemistry and Molecular Diagnostics, Leipzig University Hospital, Leipzig, Germany.
  • Sebastian Gibb
    Institute of Laboratory Medicine, Clinical Chemistry and Molecular Diagnostics, Leipzig University Hospital, Leipzig, Germany.
  • Thorsten Kaiser
    Institute of Laboratory Medicine, Clinical Chemistry and Molecular Diagnostics, University Hospital Leipzig, 04103 Leipzig, Germany.
  • Gunter Saake
    Databases and Software Engineering, Otto-von-Guericke-University, Magdeburg, Germany.
  • Paul C Ahrens
    Institute of Laboratory Medicine, Clinical Chemistry and Molecular Diagnostics, Leipzig University Hospital, Leipzig, Germany.
  • David Broneske
    German Centre for Higher Education Research and Science Studies, Hannover, Germany.
  • Robert Heyer
    Multidimensional Omics Analyses group, Leibniz-Institut für Analytische Wissenschaften - ISAS - e.V., Bunsen-Kirchhoff-Straße 11, Dortmund, Germany.

Keywords

External Resources

Popular Topics
Recent Journals