ArticleScience advances2025
Demographic bias of expert-level vision-language foundation models in medical imaging.
Article in Science advances, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 23 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
23 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Artificial intelligence for fracture detection on computed tomography: a comprehensive systematic review and meta-analysis of diagnostic test accuracy in non-commercial and commercial solutions.Emergency radiology · 2026Pooled it
- AI for Health Care Quality and Patient Safety: Scoping Review of Diagnostic, Predictive, and Decision Support Applications.Journal of medical Internet research · 2026Article
- Educating minds with generative AI.Communications psychology · 2026Review
- Data distribution impacts the performance and generalisability of contrastive learning-based foundation models of electrocardiograms.PLOS digital health · 2026Article
- Demographic Confounding in Voice-Based Parkinson Disease Screening: Methodological Analysis of the Bridge2AI Voice Dataset.Journal of medical Internet research · 2026Article
- Generative AI, foundation models and large language models in radiation therapy physics: Clinical applications, challenges, and future directions.Medical physics · 2026Review
- Encoding Versus Linear Use of Patient Characteristics in Chest X-Ray Foundation Models on MIMIC-CXR.Diagnostics (Basel, Switzerland) · 2026Article
- Multimodal Deep Learning Approaches for Lung Disease Detection: A Review.Medicina (Kaunas, Lithuania) · 2026Review
- Overview of State-of-the-Art Learning-Based Classification Methods in Medical Imaging.Annals of biomedical engineering · 2026Review
- Clinical artificial intelligence applications of vision-language foundation models.PLOS digital health · 2026Review
- Centering the marginalized: AI-driven strategies for advancing health equity in rare disease care.Patterns (New York, N.Y.) · 2026Review
- Article
- Foundation models for X-ray interpretation: a narrative review of current techniques and future perspectives in diagnostic imaging.Quantitative imaging in medicine and surgery · 2026Review
- General-Purpose Models for the Chemical Sciences: LLMs and Beyond.Chemical reviews · 2026Review
- Cross-modal bias in medical vision-language models: a pipeline-aware framework for mechanisms, evaluation, and mitigation.Frontiers in digital health · 2026Review
- Benchmarking Vision LLMs in fetal ultrasound interpretation: a five-point expert evaluation of standard vs. custom prompts.Biomedical engineering online · 2025Article
- Unbiased Artificial Intelligence: Addressing Bias in Computational Pathology.Mayo Clinic proceedings. Digital health · 2025Review
- Performance of Large Language Models and Top-Decile Doctors on an Undergraduate Ophthalmology Examination.Cureus · 2025Article
- IHRAS: Automated Medical Report Generation from Chest X-Rays via Classification, Segmentation, and LLMs.Bioengineering (Basel, Switzerland) · 2025Article
- Shortcut learning leads to sex bias in deep learning models for photoacoustic tomography.International journal of computer assisted radiology and surgery · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
9 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Advances in artificial intelligence (AI) have achieved expert-level performance in medical imaging applications. Notably, self-supervised vision-language foundation models can detect a broad spectrum of pathologies without relying on explicit training annotations. However, it is crucial to ensure that these AI models do not mirror or amplify human biases, disadvantaging historically marginalized groups such as females or Black patients. In this study, we investigate the algorithmic fairness of state-of-the-art vision-language foundation models in chest x-ray diagnosis across five globally sourced datasets. Our findings reveal that compared to board-certified radiologists, these foundation models consistently underdiagnose marginalized groups, with even higher rates seen in intersectional subgroups such as Black female patients. Such biases present over a wide range of pathologies and demographic attributes. Further analysis of the model embedding uncovers its substantial encoding of demographic information. Deploying medical AI systems with biases can intensify preexisting care disparities, posing potential challenges to equitable healthcare access and raising ethical questions about their clinical applications.
Indexed as
Identifiers
What Socratic holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the Socratic graph.