FedDeepInsight—A privacy-first federated learning architecture for medical data
Bibliographic record
Abstract
Medical data, hospital patient-specific data, are highly sensitive to privacy and are essential for research in the biomedical field. Although there are many new approaches to creating databases that ensure data must be FAIR and GDPR compliant, these approaches require the intervention of secured data handlers. To address this gap, this study investigates and designs a standardized Federated Learning (FL) architecture for medical data. Specifically, we examine traditional and novel methods for preprocessing, handling, and utilizing such data in FL. We develop “FedDeepInsight”, a novel data transformation framework that enables tabular data augmentation and transformation into image data prior to neural network training and FL. Additionally, we analyze how the type of dataset influences the performance of federated learning algorithms and machine learning models in terms of accuracy and efficiency. Our results indicate that FedAvg is the most reliable aggregation algorithm, providing superior accuracy, stability, and convergence, and FedYogi is also viable with well-tuned hyperparameters. For privacy protection, we recommend Differential Privacy (DP) with calibrated noise multipliers and initial upper and lower bounds for stability. Ultimately, we emerge as a promising solution for secure, privacy-preserving federation learning in healthcare.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".