EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bayesian federated inference for estimating statistical models based on non‐shared multicenter data sets

Marianne A Jonker iD, Hassan Pazira, Anthony Cc Coolen

Statistics in Medicine · 2024

DOI: 10.1002/sim.10072 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Statistics in Medicine, 2024. Verfasst von Marianne A Jonker und 2 weiteren Autor:innen. Beteiligte Einrichtung: Research Institute for Medical Innovation, Science Department IQ Health, Section Biostatistics, Radboud University Medical Center, Nijmegen, Netherla…. Hauptthemen laut MEDLINE: Bayes Theorem, Models, Statistical, Multicenter Studies as Topic. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Stichting Hanarth Fonds, the Netherlands, Hanarth Fonds.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Identifying predictive factors for an outcome of interest via a multivariable analysis is often difficult when the data set is small. Combining data from different medical centers into a single (larger) database would alleviate this problem, but is in practice challenging due to regulatory and logistic problems. Federated learning (FL) is a machine learning approach that aims to construct from local inferences in separate data centers what would have been inferred had the data sets been merged. It seeks to harvest the statistical power of larger data sets without actually creating them. The FL strategy is not always efficient and precise. Therefore, in this paper we refine and implement an alternative Bayesian federated inference (BFI) framework for multicenter data with the same aim as FL. The BFI framework is designed to cope with small data sets by inferring locally not only the optimal parameter values, but also additional features of the posterior parameter distribution, capturing information beyond what is used in FL. BFI has the additional benefit that a single inference cycle across the centers is sufficient, whereas FL needs multiple cycles. We quantify the performance of the proposed methodology on simulated and real life data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bayes TheoremModels, StatisticalMulticenter Studies as TopicHumansMachine LearningComputer SimulationData Interpretation, StatisticalMultivariate Analysis

Stichwörter der Autor:innen

MAP estimatordata integrationfederated learningmulticenter datasmall data sets

Autor:innen und Institutionen

  • Research Institute for Medical Innovation, Science Department IQ Health, Section Biostatistics, Radboud University Medical Center, Nijmegen, Netherlands.
  • Donders Institute, Faculty of Science, Radboud University, Nijmegen, Netherlands.
  • Saddle Point Science Europe, Mercator Science Park, Nijmegen, Netherlands.

ORCID-Profile: Marianne A Jonker

Förderung

  • Stichting Hanarth Fonds, the Netherlands
  • Hanarth Fonds

Zitieren

APA

Jonker, M. A., Pazira, H., & Coolen, A. C. (2024). Bayesian federated inference for estimating statistical models based on non‐shared multicenter data sets. Statistics in Medicine. https://doi.org/10.1002/sim.10072

Vancouver

Jonker MA, Pazira H, Coolen AC. Bayesian federated inference for estimating statistical models based on non‐shared multicenter data sets. Statistics in Medicine. 2024. doi:10.1002/sim.10072

BibTeX
@article{Jonker2024,
  author = {Jonker, Marianne A and Pazira, Hassan and Coolen, Anthony Cc},
  title = {Bayesian federated inference for estimating statistical models based on non‐shared multicenter data sets},
  journal = {Statistics in Medicine},
  year = {2024},
  doi = {10.1002/sim.10072}
}
Kostenlos starten →