ArticleNature communications2023
Detecting shortcut learning for fair medical AI using shortcut testing.
Article in Nature communications, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 49 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
49 citing papers in PubMed.
- Large language model-based triage to identify antiretroviral therapy adherence barriers and risk levels in patient messages.JAMIA open · 2026Article
- Multicohort Evaluation of Acquisition Confounding in Single-Site Lung-CT Malignancy Classification with Frozen Foundation-Model Features.Journal of imaging informatics in medicine · 2026Article
- Improving racial fairness in brain age models using style-transfer synthesis.bioRxiv : the preprint server for biology · 2026Article
- Deceptive bias measurement in deep learning: Assessing shortcut reliance in TCGA cancer models.PLOS digital health · 2026Article
- Evaluating sex bias in artificial intelligence-based echocardiographic analysis: a retrospective study on individuals with normal cardiac function and patients with systolic and diastolic dysfunction.Cardiovascular ultrasound · 2026Article
- Bias and Fairness Across the Healthcare AI Lifecycle: A Clinician-Oriented Review.Balkan medical journal · 2026Review
- Cross-task interpretability through unified modeling reveals a universal shortcut bias in neoantigen prediction.Cell genomics · 2026Article
- Encoding Versus Linear Use of Patient Characteristics in Chest X-Ray Foundation Models on MIMIC-CXR.Diagnostics (Basel, Switzerland) · 2026Article
- Attention guided fair artificial intelligence modeling for skin cancer diagnosis.NPJ digital medicine · 2026Article
- Photoacoustic device fingerprints induce bias in deep learning models.Scientific reports · 2026Article
- Towards robust foundation models for digital pathology.Nature communications · 2026Article
- Transfer learning for T-cell response prediction.BMC bioinformatics · 2026Article
- CNN-Based Classification ofBiosensors · 2026Article
- Deep learning model for body weight estimation from computed tomography scout images incorporating sex and height.Radiological physics and technology · 2026Article
- The limits of debiased clinical language models for cross-hospital generalization.Scientific reports · 2026Article
- Optimizing treatment strategies for femoral neck fractures using a machine learning model.Journal of orthopaedic surgery and research · 2026Article
- RoentMod: a synthetic chest X-ray modification model to identify and correct image interpretation model shortcuts.NPJ digital medicine · 2026Article
- Contrast-free identification of glioma blood-brain barrier status via generative diffusion AI and non-contrast MRI.Nature communications · 2026Article
- Artificial intelligence-enhanced echocardiography in cardiovascular disease management.Nature reviews. Cardiology · 2026Review
- Network biology to artificial intelligence: building the next generation of predictive drug discovery.Frontiers in immunology · 2026Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
6 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Machine learning (ML) holds great promise for improving healthcare, but it is critical to ensure that its use will not propagate or amplify health disparities. An important step is to characterize the (un)fairness of ML models-their tendency to perform differently across subgroups of the population-and to understand its underlying mechanisms. One potential driver of algorithmic unfairness, shortcut learning, arises when ML models base predictions on improper correlations in the training data. Diagnosing this phenomenon is difficult as sensitive attributes may be causally linked with disease. Using multitask learning, we propose a method to directly test for the presence of shortcut learning in clinical ML systems and demonstrate its application to clinical tasks in radiology and dermatology. Finally, our approach reveals instances when shortcutting is not responsible for unfairness, highlighting the need for a holistic approach to fairness mitigation in medical AI.
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.