MIMIC-III

MIMIC-III is a clinical benchmark dataset that contains de-identified health data for patients and is used to evaluate the reliability and performance of federated learning in a medical context.

Papers using MIMIC-III (5)

FedEHR-Gen: Federated Synthetic Time-Series EHR Generation via Latent Space Alignment and Distribution-Aware Aggregation2026Federated Learning with Layer Skipping: Efficient Training of Large Language Models for Healthcare NLP2025Reliability and Performance Assessment of Federated Learning on Clinical Benchmark Data2020 · 2 citesExploratory Analysis of Federated Learning Methods with Differential Privacy on MIMIC-III2023 · 1 citesFLICU: A Federated Learning Workflow for Intensive Care Unit Mortality Prediction2022