MétaCan
Menu
Back to cohort
Record W4407599026 · doi:10.1038/s41746-025-01499-0

Self-supervised identification and elimination of harmful datasets in distributed machine learning for medical image analysis

2025· article· en· W4407599026 on OpenAlexafffund
Raissa Souza, Emma A. M. Stanley, Anthony Winder, Chris Kang, Kimberly Amador, Erik Y. Ohara, Gabrielle Dagasso, Richard Camicioli, Oury Monchi, Zahinoor Ismail, Matthias Wilms, Nils D. Forkert

Bibliographic record

Venuenpj Digital Medicine · 2025
Typearticle
Languageen
FieldMedicine
TopicCOVID-19 diagnosis using AI
Canadian institutionsInstitut Universitaire de Gériatrie de MontréalHotchkiss Brain InstituteAlberta Children's HospitalWomen and Children’s Health Research InstituteUniversité de MontréalUniversity of AlbertaUniversity of Calgary
FundersParkinson Association of AlbertaParkinson VerenigingConsortium canadien en neurodégénérescence associée au vieillissementAlzheimer's Disease Neuroimaging Initiative
KeywordsIdentification (biology)Computer scienceArtificial intelligenceMachine learningPattern recognition (psychology)Image (mathematics)Biology

Abstract

fetched live from OpenAlex

Distributed learning enables collaborative machine learning model training without requiring cross-institutional data sharing, thereby addressing privacy concerns. However, local quality control variability can negatively impact model performance while systematic human visual inspection is time-consuming and may violate the goal of keeping data inaccessible outside acquisition centers. This work proposes a novel self-supervised method to identify and eliminate harmful data during distributed learning model training fully-automatically. Harmful data is defined as samples that, when included in training, increase misdiagnosis rates. The method was tested using neuroimaging data from 83 centers for Parkinson's disease classification with simulated inclusion of a few harmful data samples. The proposed method reliably identified harmful images, with centers providing only harmful datasets being easier to identify than single harmful images within otherwise good datasets. While only evaluated using neuroimaging data, the presented method is application-agnostic and presents a step towards automated quality control in distributed learning.

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 imitation

Not 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.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.013
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.004
Threshold uncertainty score0.023

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.013
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0010.002
Open science0.0020.003
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0010.001

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.

Opus teacher head0.014
GPT teacher head0.333
Teacher spread0.319 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations1
Published2025
Admission routes2
Has abstractyes

Explore more

Same venuenpj Digital MedicineSame topicCOVID-19 diagnosis using AIFrench-language works237,207