EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Evaluation of Graph-Based Algorithms for Early Detection of In-Hospital Mortality

Paul-Antoine Beaudoin, Christophe Cance, Sophie Achard, Jean-Luc Bosson, Alexandre Moreau-Gaudry

Studies in Health Technology and Informatics · 21.05.2026

DOI: 10.3233/shti260233 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Paul-Antoine Beaudoin und 4 weiteren Autor:innen. Beteiligte Einrichtung: Univ. Grenoble Alpes, CNRS, UMR 5525, VetAgro Sup, Grenoble INP, CHU Grenoble Alpes, TIMC, 38000 Grenoble, France. Hauptthemen laut MEDLINE: Hospital Mortality, Electronic Health Records, Algorithms. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Enhancing patient care quality depends on preventing health-related adverse events (HAEs), including in-hospital mortality, right from the start of hospitalization. Today, machine learning tools offer innovative solutions for predicting such events. Nevertheless, and despite their predictive potential, graph neural networks (GNNs) remain largely unexplored in the literature for analyzing complex, interconnected, real-life clinical hospital data from a clinical data warehouse (CDW). In this study, we present a robust evaluation of two GNN models which are benchmarked against strong baseline methods for predicting in-hospital death. Our findings demonstrate that these models perform as well as the best benchmarks established in previous research. Additionally, we highlight promising opportunities enabled by the graph structure of the data, including graph model optimization and enhanced prediction explainability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Hospital MortalityElectronic Health RecordsAlgorithmsGraph Neural NetworksHumansMachine LearningPrediction AlgorithmsEarly Diagnosis

Stichwörter der Autor:innen

Clinical data warehouseClinical risk predictionElectronic Health recordsGraph modelGraph neural networksIn-hospital mortality

Autor:innen und Institutionen

  • Univ. Grenoble Alpes, CNRS, UMR 5525, VetAgro Sup, Grenoble INP, CHU Grenoble Alpes, TIMC, 38000 Grenoble, France.
  • Univ. Grenoble Alpes, CNRS, UMR 5525, VetAgro Sup, Grenoble INP, TIMC, 38000 Grenoble, France.
  • Univ. Grenoble Alpes, CNRS, Inria, Grenoble INP, LJK, 38000 Grenoble, France.

Zitieren

APA

Beaudoin, P. A., Cance, C., Achard, S., Bosson, J. L., & Moreau-Gaudry, A. (2026). Evaluation of Graph-Based Algorithms for Early Detection of In-Hospital Mortality. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260233

Vancouver

Beaudoin PA, Cance C, Achard S, Bosson JL, Moreau-Gaudry A. Evaluation of Graph-Based Algorithms for Early Detection of In-Hospital Mortality. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260233

BibTeX
@article{Beaudoin2026,
  author = {Beaudoin, Paul-Antoine and Cance, Christophe and Achard, Sophie and Bosson, Jean-Luc and Moreau-Gaudry, Alexandre},
  title = {Evaluation of Graph-Based Algorithms for Early Detection of In-Hospital Mortality},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260233}
}
Kostenlos starten →