Federated Learning for Privacy-Preserving Hospital Readmission Prediction in Regional Hospitals

Aminah, Siti; Bellini, Marco

Research article · pp. 15-29

Federated Learning for Privacy-Preserving Hospital Readmission Prediction in Regional Hospitals

Siti Aminah¹, Marco Bellini²

¹ Institut Teknologi Samudra

² Università di Città Nuova

Received9 May 2026

Revised23 Jul 2026

Accepted22 Aug 2026

Published21 Sep 2026

Abstract

Regional hospitals hold valuable patient data but cannot share it because of privacy rules. We train a 30-day readmission model across nine hospitals using federated averaging with differential privacy, so raw records never leave each site. The federated model achieves an AUC of 0.81, compared with 0.73 for the average single-hospital model, at a privacy budget of epsilon 3. We release the training pipeline and a governance checklist that hospital IT teams can adopt.

Keywords

federated learning readmission differential privacy health informatics

Metadata for indexing

Google Scholar tags XML exports

These tags are in this page's <head>. Google Scholar reads them to index the article.

<meta name="citation_title" content="Federated Learning for Privacy-Preserving Hospital Readmission Prediction in Regional Hospitals">
<meta name="citation_author" content="Aminah, Siti">
<meta name="citation_author_institution" content="Institut Teknologi Samudra">
<meta name="citation_author" content="Bellini, Marco">
<meta name="citation_author_institution" content="Università di Città Nuova">
<meta name="citation_journal_title" content="JURNAL UJI COBA">
<meta name="citation_journal_abbrev" content="JUC">
<meta name="citation_issn" content="1234-273X">
<meta name="citation_publisher" content="Karoteh Utama Publisher">
<meta name="citation_volume" content="1">
<meta name="citation_issue" content="1">
<meta name="citation_firstpage" content="15">
<meta name="citation_lastpage" content="29">
<meta name="citation_publication_date" content="2026/09/21">
<meta name="citation_date" content="2026/09/21">
<meta name="citation_keywords" content="federated learning; readmission; differential privacy; health informatics">
<meta name="citation_language" content="en">
<meta name="citation_abstract_html_url" content="https://uji.purwantoro.my.id/article/2">
<meta name="citation_pdf_url" content="https://uji.purwantoro.my.id/article/2/download/2">
<meta name="DC.Title" content="Federated Learning for Privacy-Preserving Hospital Readmission Prediction in Regional Hospitals">
<meta name="DC.Creator.PersonalName" content="Siti Aminah">
<meta name="DC.Creator.PersonalName" content="Marco Bellini">
<meta name="DC.Date.issued" content="2026-09-21">
<meta name="DC.Identifier.URI" content="https://uji.purwantoro.my.id/article/2">
<meta name="DC.Rights" content="https://creativecommons.org/licenses/by/4.0/">
<meta name="DC.Type" content="Text.Serial.Journal">
<meta name="DC.Type.articleType" content="AI in Health">