ArticleEBioMedicine2023
Algorithmic encoding of protected characteristics in chest X-ray disease detection models.
Article in EBioMedicine, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 31 papers.
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
31 citing papers in PubMed.
- AI alignment in medical imaging: Unveiling hidden biases through counterfactual analysis.PLOS digital health · 2026Article
- Encoding Versus Linear Use of Patient Characteristics in Chest X-Ray Foundation Models on MIMIC-CXR.Diagnostics (Basel, Switzerland) · 2026Article
- Detecting dataset bias in medical AI using a generalized and modality agnostic auditing approach.NPJ digital medicine · 2026Article
- FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging With FairLoRA.IEEE transactions on medical imaging · 2026Article
- Distinct visual biases affect humans and artificial intelligence in medical imaging diagnoses.NPJ digital medicine · 2025Review
- Detecting Sociodemographic Biases in the Content and Quality of Large Language Model-Generated Nursing Care: Cross-Sectional Simulation Study.Journal of medical Internet research · 2025Article
- Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic Data.Research square · 2025Article
- FairICP: identifying biases and increasing transparency at the point of care in post-implementation clinical decision support using inductive conformal prediction.Journal of the American Medical Informatics Association : JAMIA · 2025Article
- DREAM: A framework for discovering mechanisms underlying AI prediction of protected attributes.medRxiv : the preprint server for health sciences · 2025Article
- An investigation into the causes of race bias in artificial intelligence-based cine cardiac magnetic resonance segmentation.European heart journal. Digital health · 2025Article
- Demographic bias of expert-level vision-language foundation models in medical imaging.Science advances · 2025Article
- Towards realistic simulation of disease progression in the visual cortex with CNNs.Scientific reports · 2025Article
- Governance for anti-racist AI in healthcare: integrating racism-related stress in psychiatric algorithms for Black Americans.Frontiers in digital health · 2025Article
- The risk of shortcutting in deep learning algorithms for medical imaging research.Scientific reports · 2024Article
- Towards objective and systematic evaluation of bias in artificial intelligence for medical imaging.Journal of the American Medical Informatics Association : JAMIA · 2024Article
- Addressing fairness issues in deep learning-based medical image analysis: a systematic review.NPJ digital medicine · 2024Review
- HarmonyTM: multi-center data harmonization applied to distributed learning for Parkinson's disease classification.Journal of medical imaging (Bellingham, Wash.) · 2024Article
- Acquisition parameters influence AI recognition of race in chest x-rays and mitigating these factors reduces underdiagnosis bias.Nature communications · 2024Article
- Detecting Algorithmic Errors and Patient Harms for AI-Enabled Medical Devices in Randomized Controlled Trials: Protocol for a Systematic Review.JMIR research protocols · 2024Article
- [Ethics and artificial intelligence].Radiologie (Heidelberg, Germany) · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
backgroundIt has been rightfully emphasized that the use of AI for clinical decision making could amplify health disparities. An algorithm may encode protected characteristics, and then use this information for making predictions due to undesirable correlations in the (historical) training data. It remains unclear how we can establish whether such information is actually used. Besides the scarcity of data from underserved populations, very little is known about how dataset biases manifest in predictive models and how this may result in disparate performance. This article aims to shed some light on these issues by exploring methodology for subgroup analysis in image-based disease detection models.
methodsWe utilize two publicly available chest X-ray datasets, CheXpert and MIMIC-CXR, to study performance disparities across race and biological sex in deep learning models. We explore test set resampling, transfer learning, multitask learning, and model inspection to assess the relationship between the encoding of protected characteristics and disease detection performance across subgroups.
findingsWe confirm subgroup disparities in terms of shifted true and false positive rates which are partially removed after correcting for population and prevalence shifts in the test sets. We find that transfer learning alone is insufficient for establishing whether specific patient information is used for making predictions. The proposed combination of test-set resampling, multitask learning, and model inspection reveals valuable insights about the way protected characteristics are encoded in the feature representations of deep neural networks.
interpretationSubgroup analysis is key for identifying performance disparities of AI models, but statistical differences across subgroups need to be taken into account when analyzing potential biases in disease detection. The proposed methodology provides a comprehensive framework for subgroup analysis enabling further research into the underlying causes of disparities.
fundingEuropean Research Council Horizon 2020, UK Research and Innovation.
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.