Aug 2026· Natural Resources for Human Health· Vol 6, pp. 60-74· 0 citations
TL;DR
FedTwin-X is presented, a federated architecture in which every participating hospital maintains a patient digital twin: a persistent latent state assembled from irregular vital-sign and laboratory streams, chest radiographs, twelve-lead electrocardiograms and free-text notes.
Abstract
Clinical risk models seldom fail for want of a better algorithm. They fail because the records that would make them dependable sit behind institutional and statutory walls, because a single snapshot cannot describe a physiology that shifts within hours and because a clinician will not act on a number that arrives with no reason attached. This paper treats those three failures as one design problem. We present FedTwin-X, a federated architecture in which every participating hospital maintains a patient digital twin: a persistent latent state assembled from irregular vital-sign and laboratory streams, chest radiographs, twelve-lead electrocardiograms and free-text notes. Modality-specific foundation encoders stay frozen throughout; only low-rank adapters are trained and only those adapters cross the network. Updates are protected by secure aggregation together with client-level differential privacy under Rényi accounting, so no individual site contribution is ever observable in the clear. Because the trainable parameter counts falls by more than an order of magnitude, the noise required for a given privacy budget falls with it, a coupling that turns parameter-efficient adaptation from a convenience into a privacy mechanism. Each prediction is emitted alongside four artefacts: a modality attribution, a temporal attribution over the twin trajectory, a sparse activation over forty-eight clinical concepts and a counterfactual roll-out of the twin under a hypothetical intervention. We describe an evaluation over three cohorts drawn from MIMIC-IV, MIMIC-CXR, the eICU Collaborative Research Database and PTB-XL, partitioned into twenty-two clients along genuine institutional boundaries. On forty-eight-hour deterioration prediction the architecture is designed to operate within roughly two AUROC points of an unconstrained centralised model while halving calibration error and reducing uplink traffic by a factor of twenty-two.
A framework in which hospitals train a shared risk-prediction model without exchanging raw records is presented, which combines federated averaging, record-level differential privacy (DP), secure aggregation, and site-specific model calibration, and it is evaluated on four dimensions: predictive accuracy, privacy leaka...
Hospitals cannot pool patient records, and federated learning is widely proposed as the remedy. Most evidence comes from simulated federations cut from one dataset, which understates the difficulty because every shard shares one measurement process. We instead used a cardiology cohort of 920 patients collected independ...
Abdul Ahad· Natural Resources for Human...· 0 citations
This work demonstrates that strong privacy protection and state-of-the-art prediction performance are not mutually exclusive, thereby offering a practical and scalable solution for collaborative healthcare analytics.
Lukesh Thakur· Journal of Machine Learning...· 0 citations
Aegis is proposed, a principled client-side defense that breaks this dilemma without perturbing patient data or modifying the FL protocol, offering a practical privacy primitive for medical FL.
Chao-Yu Zhang, Shang-Hao Shi, Heng Jin et al.· arXiv.org· 0 citations
Machine learning in healthcare struggles for one main reason: good data are hard to come by. Medical records are sensitive, and the rules on sharing them between hospitals are strict. A common workaround is the use of synthetic data, that is, artificial records that copy the statistics of real ones; however, on its own...