MétaCan
Menu
Back to cohort
Record W4386437708 · doi:10.1093/jamia/ocad171

Image-encoded biological and non-biological variables may be used as shortcuts in deep learning models trained on multisite neuroimaging data

2023· article· en· W4386437708 on OpenAlexafffund
Raissa Souza, Matthias Wilms, Milton Camacho, G. Bruce Pike, Richard Camicioli, Oury Monchi, Nils D. Forkert

Bibliographic record

VenueJournal of the American Medical Informatics Association · 2023
Typearticle
Languageen
FieldMedicine
TopicParkinson's Disease Mechanisms and Treatments
Canadian institutionsInstitut Universitaire de Gériatrie de MontréalAlberta Children's HospitalWomen and Children’s Health Research InstituteUniversité de MontréalUniversity of AlbertaUniversity of Calgary
FundersCanadian Institutes of Health ResearchCanadian Open Neuroscience PlatformCanada Research ChairsParkinson VerenigingConsortium canadien en neurodégénérescence associée au vieillissementNatural Sciences and Engineering Research Council of CanadaParkinson Association of AlbertaHotchkiss Brain Institute, University of Calgary
KeywordsArtificial intelligenceComputer sciencePreprocessorPattern recognition (psychology)NeuroimagingLogistic regressionMagnetic resonance imagingJacobian matrix and determinantMedical imagingMachine learningMathematicsRadiologyMedicine

Abstract

fetched live from OpenAlex

OBJECTIVE: This work investigates if deep learning (DL) models can classify originating site locations directly from magnetic resonance imaging (MRI) scans with and without correction for intensity differences. MATERIAL AND METHODS: A large database of 1880 T1-weighted MRI scans collected across 41 sites originally for Parkinson's disease (PD) classification was used to classify sites in this study. Forty-six percent of the datasets are from PD patients, while 54% are from healthy participants. After preprocessing the T1-weighted scans, 2 additional data types were generated: intensity-harmonized T1-weighted scans and log-Jacobian deformation maps resulting from nonlinear atlas registration. Corresponding DL models were trained to classify sites for each data type. Additionally, logistic regression models were used to investigate the contribution of biological (age, sex, disease status) and non-biological (scanner type) variables to the models' decision. RESULTS: A comparison of the 3 different types of data revealed that DL models trained using T1-weighted and intensity-harmonized T1-weighted scans can classify sites with an accuracy of 85%, while the model using log-Jacobian deformation maps achieved a site classification accuracy of 54%. Disease status and scanner type were found to be significant confounders. DISCUSSION: Our results demonstrate that MRI scans encode relevant site-specific information that models could use as shortcuts that cannot be removed using simple intensity harmonization methods. CONCLUSION: The ability of DL models to exploit site-specific biases as shortcuts raises concerns about their reliability, generalization, and deployability in clinical settings.

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 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)0.002
metaresearch head score (Gemma)0.004
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.693
Threshold uncertainty score0.509

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.004
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
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 head0.056
GPT teacher head0.327
Teacher spread0.271 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
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

Citations14
Published2023
Admission routes2
Has abstractyes

Explore more

Same venueJournal of the American Medical Informatics AssociationSame topicParkinson's Disease Mechanisms and TreatmentsFrench-language works237,207