ArticleNature medicine2024
The limits of fair medical imaging AI in real-world generalization.
Article in Nature medicine, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 127 papers, 5 of them syntheses 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
127 citing papers in PubMed, 5 syntheses or guidelines pooled it.
- Radiomics-Based AI for the Diagnosis and Prognosis of Vessels Encapsulating Tumor Clusters in Hepatocellular Carcinoma: Systematic Review and Meta-Analysis.Journal of medical Internet research · 2026Pooled it
- Deep learning for the diagnosis of lumbar disc herniation: a systematic review and meta-analysis.BMC medical imaging · 2026Pooled it
- Artificial Intelligence in Schizophrenia Spectrum Disorders: Current Use and Future Perspectives. A Systematic Mapping Literature Review.Alpha psychiatry · 2026Pooled it
- Trends and methods in intensive care unit (ICU) research using machine learning: latent dirichlet allocation (LDA)-based thematic literature review.BMC medical informatics and decision making · 2025Pooled it
- Stage-stratified benefits of AI-radiomics PET in early Alzheimer's disease: a systematic review and meta-analysis.Frontiers in neurologyPooled it
- Improving racial fairness in brain age models using style-transfer synthesis.bioRxiv : the preprint server for biology · 2026Article
- Perspectives on the Limits and Clinical Alignment of Medical AI from Population Statistics to Individual Care.Bioengineering (Basel, Switzerland) · 2026Article
- Data distribution impacts the performance and generalisability of contrastive learning-based foundation models of electrocardiograms.PLOS digital health · 2026Article
- Echo Chambers: Bias and Representation in Cardiac Imaging Datasets for Artificial Intelligence.Current cardiology reports · 2026Review
- AI agents in cancer imaging: Concepts, advances, and clinical perspectives.Chinese journal of cancer research = Chung-kuo yen cheng yen chiu · 2026Article
- Artificial Intelligence in Prehospital Tele-Emergency Medicine: A Survey of Acceptance and Attitudes.Healthcare (Basel, Switzerland) · 2026Article
- [Application of hybrid attention guided dual-path residual learning in magnetic resonance imaging diagnosis].Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi · 2026Article
- Navigating the Artificial Intelligence Revolution in Clinical Neurology: A New Multidisciplinary Task Force Within the European Academy of Neurology.European journal of neurology · 2026Article
- Divergent impacts of explainable AI for dermatological diagnosis on clinicians versus lay people.Nature medicine · 2026Article
- AI alignment in medical imaging: Unveiling hidden biases through counterfactual analysis.PLOS digital health · 2026Article
- Bias and Fairness Across the Healthcare AI Lifecycle: A Clinician-Oriented Review.Balkan medical journal · 2026Review
- CLEAR: an auditable foundation model for radiology grounded in clinical concepts.Nature biomedical engineering · 2026Article
- Demonstrating the real-world impact of an artificial intelligence tool in radiology: are we focusing our efforts in the proper direction?European radiology · 2026Article
- RCAF for patient-level thyroid ultrasound malignancy prediction under leakage-free evaluation and calibration.Scientific reports · 2026Article
- Evaluation of AI developed for rib fracture detection in identifying vertebral fractures on abdominal CT.BMC musculoskeletal disorders · 2026Article
67 more citing papers are in PubMed but not listed here.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
Abstract
As artificial intelligence (AI) rapidly approaches human-level performance in medical imaging, it is crucial that it does not exacerbate or propagate healthcare disparities. Previous research established AI's capacity to infer demographic data from chest X-rays, leading to a key concern: do models using demographic shortcuts have unfair predictions across subpopulations? In this study, we conducted a thorough investigation into the extent to which medical AI uses demographic encodings, focusing on potential fairness discrepancies within both in-distribution training sets and external test sets. Our analysis covers three key medical imaging disciplines-radiology, dermatology and ophthalmology-and incorporates data from six global chest X-ray datasets. We confirm that medical imaging AI leverages demographic shortcuts in disease classification. Although correcting shortcuts algorithmically effectively addresses fairness gaps to create 'locally optimal' models within the original data distribution, this optimality is not true in new test settings. Surprisingly, we found that models with less encoding of demographic attributes are often most 'globally optimal', exhibiting better fairness during model evaluation in new test environments. Our work establishes best practices for medical imaging models that maintain their performance and fairness in deployments beyond their initial training contexts, underscoring critical considerations for AI clinical deployments across populations and sites.
Indexed as
Identifiers
What OpenQuestion 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 OpenQuestion graph.