MétaCan
Menu
Back to cohort
Record W4392672760 · doi:10.1016/j.ebiom.2024.105047

Drop the shortcuts: image augmentation improves fairness and decreases AI detection of race and other demographics from medical images

2024· article· en· W4392672760 on OpenAlexfundno aff
Ryan Wang, Po‐Chih Kuo, Li-Ching Chen, Kenneth P. Seastedt, Judy Wawira Gichoya, Leo Anthony Celi

Bibliographic record

VenueEBioMedicine · 2024
Typearticle
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsnot available
FundersNational Institute on Minority Health and Health DisparitiesNational Institute on AgingNational Institute of Biomedical Imaging and BioengineeringFogarty International CenterCanadian Institutes of Health ResearchNational Institutes of HealthGenentechIXICOH. Lundbeck A/SServierEisaiGordon and Betty Moore FoundationNorthern California Institute for Research and EducationF. Hoffmann-La RocheRadiological Society of North AmericaBioClinicaPfizerBiogenNational Heart, Lung, and Blood InstituteNovartis Pharmaceuticals CorporationU.S. Department of DefenseEli Lilly and CompanyBristol-Myers SquibbAlzheimer's Disease Neuroimaging InitiativeMeso Scale DiagnosticsAlzheimer's AssociationNational Science FoundationUniversity of Southern CaliforniaNational Science and Technology Council
KeywordsDemographicsMedicineMagnetic resonance imagingArtificial intelligenceComputer scienceMachine learningDemographyRadiology

Abstract

fetched live from OpenAlex

BACKGROUND: It has been shown that AI models can learn race on medical images, leading to algorithmic bias. Our aim in this study was to enhance the fairness of medical image models by eliminating bias related to race, age, and sex. We hypothesise models may be learning demographics via shortcut learning and combat this using image augmentation. METHODS: This study included 44,953 patients who identified as Asian, Black, or White (mean age, 60.68 years ±18.21; 23,499 women) for a total of 194,359 chest X-rays (CXRs) from MIMIC-CXR database. The included CheXpert images comprised 45,095 patients (mean age 63.10 years ±18.14; 20,437 women) for a total of 134,300 CXRs were used for external validation. We also collected 1195 3D brain magnetic resonance imaging (MRI) data from the ADNI database, which included 273 participants with an average age of 76.97 years ±14.22, and 142 females. DL models were trained on either non-augmented or augmented images and assessed using disparity metrics. The features learned by the models were analysed using task transfer experiments and model visualisation techniques. FINDINGS: In the detection of radiological findings, training a model using augmented CXR images was shown to reduce disparities in error rate among racial groups (-5.45%), age groups (-13.94%), and sex (-22.22%). For AD detection, the model trained with augmented MRI images was shown 53.11% and 31.01% reduction of disparities in error rate among age and sex groups, respectively. Image augmentation led to a reduction in the model's ability to identify demographic attributes and resulted in the model trained for clinical purposes incorporating fewer demographic features. INTERPRETATION: The model trained using the augmented images was less likely to be influenced by demographic information in detecting image labels. These results demonstrate that the proposed augmentation scheme could enhance the fairness of interpretations by DL models when dealing with data from patients with different demographic backgrounds. FUNDING: National Science and Technology Council (Taiwan), National Institutes of Health.

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.640
Threshold uncertainty score0.471

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.001
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
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 head0.400
Teacher spread0.364 · 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 designBench or experimental
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

Citations25
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueEBioMedicineSame topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207