The paper introduces the first federated learning framework for infant movement analysis, specifically targeting General Movement Assessment using skeletal motion data. It employs Monte Carlo Dropout to estimate predictive uncertainty and proposes an Uncertainty-Aware Federated Averaging (UA‑FedAvg) strategy that weights client updates by this uncertainty. Experiments with three clients show that federated learning outperforms local models and approaches centralized training performance, with UA‑FedAvg generally surpassing standard FedAvg.
arXiv:2607. 19524v1 Announce Type: cross Abstract: Federated learning (FL) offers a promising approach to privacy-preserving clinical risk prediction, but its deployment remains limited by restricted data sharing, client heterogeneity, class imbalance, and the lack of realistic tabular electronic health record (EHR) benchmarks.
arXiv:2506.15626v3 Announce Type: replace-cross Abstract: $\textbf{Objective:}$ Brain-predicted age difference (BrainAGE) is a neuroimaging biomarker reflecting brain health. However, training robust...
arXiv:2507. 21018v2 Announce Type: replace-cross Abstract: Automated assessment of human motion plays a vital role in rehabilitation, enabling objective evaluation of patient performance and progress.
arXiv:2608. 03498v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative model training across distributed healthcare institutions without centralising sensitive patient data.
arXiv:2607. 08595v1 Announce Type: new Abstract: Cardiovascular disease risk prediction models often rely on data from a single institution or centrally pooled datasets.
arXiv:2608. 09240v1 Announce Type: cross Abstract: Multimodal federated learning (FL) supports collaborative modeling in privacy-sensitive health-sensing and medical settings, but realistic deployments often exhibit dual-axis modality missingness: clients have different modality sets, and individual samples may contain only subsets of the modalities available locally.
arXiv:2606. 23871v1 Announce Type: new Abstract: Survival analysis is central to clinical decision-making, yet reliable time-to-event models require large, diverse cohorts that are rarely available at a single institution, while privacy regulations restrict the centralization of patient data.
The paper introduces REMIND, a clustering‑based keypoint‑selection method that uses training dynamics to detect and filter noisy annotations in 2D pose estimation for preterm infants. Applied to the NeoPose dataset of 46 clinical videos, REMIND achieves up to 93% AUC across three pose‑estimation architectures, demonstrating robust learning without prior noise assumptions. This work is the first to explicitly tackle label noise in neonatal pose estimation, enabling more reliable monitoring of infant motor development in real clinical settings.
Federated Learning (FL) enables collaborative model training across distributed healthcare institutions without centralising sensitive patient data. However, real-world healthcare federations are often characterised not only by non-IID data, but also by heterogeneous clinical objectives and partially overlapping feature spaces.
arXiv:2604.01997v2 Announce Type: replace Abstract: Gait analysis provides an objective characterization of locomotor function and is widely used to support diagnosis and rehabilitation monitoring ac...
The FedSurg Challenge is the first international effort to evaluate Federated Learning (FL) for surgical vision, using a multi‑center dataset of laparoscopic appendectomies. Three participant models were tested for generalization to an unseen clinical center and for center‑specific adaptation, compared against centralized, Swarm Learning, and parameter‑efficient fine‑tuning baselines. The study found that temporal modeling most consistently improves generalization, but overall performance remains low (26.31% F1‑score on the unseen center), highlighting the need for structured personalized FL and revealing limitations of current approaches.
Fed-ReMasker is a federated learning approach that adapts the ReMasker masked autoencoder for tabular data imputation, specifically addressing feature-level missingness where entire features are absent at some centers. The method enables centers to impute unobserved features by leveraging knowledge from collaborating institutions. In benchmark tests on synthetic and real-world datasets, Fed-ReMasker achieves the lowest imputation error in the majority of scenarios and remains robust to client heterogeneity, closely matching the performance of a centralized model.