MétaCan
Menu
Back to cohort
Record W4414189846 · doi:10.1016/j.imu.2025.101691

FedDeepInsight—A privacy-first federated learning architecture for medical data

2025· article· en· W4414189846 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueInformatics in Medicine Unlocked · 2025
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsInstitute of Infection and Immunity
FundersNederlandse Brandwonden StichtingNederlandse Organisatie voor Wetenschappelijk OnderzoekHealth~HollandNational Weather Association
KeywordsDifferential privacyFederated learningDeep learningDimensionality reductionArchitectureInformation privacyStability (learning theory)Data transformationData modeling

Abstract

fetched live from OpenAlex

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.161
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow), Open science
Consensus categoriesOpen science
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.727
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.161
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.002
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0410.072
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.036
GPT teacher head0.323
Teacher spread0.287 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it