A federated learning and recalibration pipeline for clinical prediction across heterogeneous regions: 30-day mortality after acute myocardial infarction
Abstract
Abstract Background Federated learning (FL) enables individual institutions to retain their data during distributed model development and validation, limiting privacy risk. We aimed to assess regional heterogeneity and the transportability of locally developed prediction models for 30-day mortality after acute myocardial infarction (AMI), and to determine whether FL can match centralized learning while supporting the development, validation, and updating of prediction models across regions without sharing patient-level data. Methods We predicted 30-day mortality among 40,830 patients with AMI across 16 regions in the GUSTO-I trial. Logistic regression models were developed under three approaches: (1) FL— each institution shared only model coefficients for aggregation, followed by a lightweight federated recalibration of the model intercept (calibration-in-the-large), using only aggregate statistics; (2) centralized learning—patient-level data were pooled centrally; and (3) local modeling—training of 16 local models. Each approach included logistic models without regularization and with L1, L2, and Elastic Net penalties. Performance was evaluated by the area under the receiver operating characteristic curve (AUROC) and calibration. Results Within their development regions (stratified five-fold cross-validation), the models achieved AUROC values ranging from 0.73 to 0.85, with local models generally underperforming compared to the FL and centralized models. Applying local…
How strong is the evidence?
Evidence Hub reads this as a randomized trial, done in people. Its evidence level is 2 of 5 (High · randomized trial). Randomized trials of a reasonable size are the strongest single-study design. Reported size: 40,830 participants or records.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.