FirsthandHealth
medRxiv PreprintsInternational20 November 2026

A Blockchain-Enabled Federated Ensemble Framework for Privacy-Preserving Mortality Prediction Across Heterogeneous Healthcare Systems

This is an official announcement record

Firsthand records what medRxiv Preprints announced and links to the original. The wording below is theirs, not ours.

Objective: To test whether a smart contract that admits hospital-trained models to a shared mortality model only after peer hospitals verify their performance can exclude poisoned or substituted models, and at what cost. Design: Retrospective simulation study of a federated learning protocol. Methodology: In the Blockchain-Enabled Federated Ensemble (BFE), hospitals committed SHA-256 digests of locally trained XGBoost and random-forest models to a Solidity contract; peers posted digest-bound validation AUROCs, and the contract admitted models with a median peer AUROC of at least 0.70. Admitted
Source: medRxiv Preprints
Read the official announcement

Opens www.medrxiv.org

More from medRxiv Preprints

This content is for informational purposes only and is not medical advice. It is not intended to diagnose, treat, cure, or prevent any disease. Consult a healthcare professional before starting any supplement, treatment, or program: especially if you are pregnant, nursing, taking medication, or managing a health condition.