• Medientyp: E-Artikel
  • Titel: Diagnostic Expert Advisor: A platform for developing machine learning models on medical time-series data
  • Beteiligte: Polzin, Richard [VerfasserIn]; Fritsch, Sebastian [VerfasserIn]; Sharafutdinov, Konstantin [VerfasserIn]; Marx, Gernot [VerfasserIn]; Schuppert, Andreas [VerfasserIn]
  • Erschienen: Elsevier, 2023
  • Erschienen in: SoftwareX 23, 101517 (2023). doi:10.1016/j.softx.2023.101517
  • Sprache: Englisch
  • DOI: https://doi.org/10.1016/j.softx.2023.101517; https://doi.org/10.34734/FZJ-2023-03458
  • ISSN: 2352-7110
  • Entstehung:
  • Anmerkungen: Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
  • Beschreibung: Setting up data structures, parallelizing code, and creating visualizations are tasks in almost any project aiming to develop healthcare AI solutions based on heterogeneous, high-dimensional data structures. While toolkits for individual parts of this workflow exist, a solution that provides integration of all steps is rarely found. We present the Diagnostic Expert Advisor, a platform for machine learning research on heterogeneous medical time-series data that aims to provide a robust environment for the rapid development of AI applications. It integrates a local web app through which whole patient cohorts, as well as the disease evolution of individual patients, can be analyzed with integrated tools for data handling, visualization, and parallelization. The platform provides sensible defaults while being flexible and extensible to fit various projects and working styles.
  • Zugangsstatus: Freier Zugang