EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

An adaptive federated learning framework for clinical risk prediction with electronic health records from multiple hospitals

Weishen Pan, Zhenxing Xu, Suraj Rajendran, Fei Wang

Patterns · 2024-01 · 5 (1) · 100898

DOI: 10.1016/j.patter.2023.100898 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Patterns, 2024-01. Verfasst von Weishen Pan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Population Health Sciences, Weill Cornell Medical College, Cornell University, New York, NY 10065, USA. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIA NIH HHS, NIGMS NIH HHS, NIMH NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Clinical risk prediction with electronic health records (EHR) using machine learning has attracted lots of attentions in recent years, where one of the key challenges is how to protect data privacy. Federated learning (FL) provides a promising framework for building predictive models by leveraging the data from multiple institutions without sharing them. However, data distribution drift across different institutions greatly impacts the performance of FL. In this paper, an adaptive FL framework was proposed to address this challenge. Our framework separated the input features into stable, domain-specific, and conditional-irrelevant parts according to their relationships to clinical outcomes. We evaluate this framework on the tasks of predicting the onset risk of sepsis and acute kidney injury (AKI) for patients in the intensive care unit (ICU) from multiple clinical institutions. The results showed that our framework can achieve better prediction performance compared with existing FL baselines and provide reasonable feature interpretations.

Schlagwörter

Stichwörter der Autor:innen

clinical risk prediciondistribution driftfederated learning

Autor:innen und Institutionen

  • Department of Population Health Sciences, Weill Cornell Medical College, Cornell University, New York, NY 10065, USA.
  • Institute of Artificial Intelligence for Digital Health, Weill Cornell Medical College, Cornell University, New York, NY 10065, USA.
  • Tri-Institutional Computational Biology & Medicine Program, Weill Cornell Medical College, Cornell University, New York, NY 10065, USA.

Förderung

  • NIA NIH HHS
  • NIGMS NIH HHS
  • NIMH NIH HHS
  • National Science Foundation
  • Amazon
  • Google LLC
  • National Institutes of Health

Zitieren

APA

Pan, W., Xu, Z., Rajendran, S., & Wang, F. (2024). An adaptive federated learning framework for clinical risk prediction with electronic health records from multiple hospitals. Patterns, 5(1), 100898. https://doi.org/10.1016/j.patter.2023.100898

Vancouver

Pan W, Xu Z, Rajendran S, Wang F. An adaptive federated learning framework for clinical risk prediction with electronic health records from multiple hospitals. Patterns. 2024;5(1):100898. doi:10.1016/j.patter.2023.100898

BibTeX
@article{Pan2024,
  author = {Pan, Weishen and Xu, Zhenxing and Rajendran, Suraj and Wang, Fei},
  title = {An adaptive federated learning framework for clinical risk prediction with electronic health records from multiple hospitals},
  journal = {Patterns},
  year = {2024},
  volume = {5},
  number = {1},
  pages = {100898},
  doi = {10.1016/j.patter.2023.100898}
}
Kostenlos starten →