Perspective on Bias in Biomedical AI: Preventing Downstream Healthcare Disparities

• URL: http://arxiv.org/abs/2604.14514v1
• Date: Thu, 16 Apr 2026 01:09:36 GMT
• Title: Perspective on Bias in Biomedical AI: Preventing Downstream Healthcare Disparities
• Abstract summary: A vast number of studies focus on collecting omics data but the demographic information associated with these datasets is often not reported in the studies.<n>Analysis of large-scale datasets commonly used for model training, such as CellxGene and GEO, reveals substantial population bias where European-ancestry data dominates.<n>We propose a community-wide focus on three foundational principles: Provenance, Openness, and Evaluation Transparency to improve equity and robustness in biomedical AI.
• Score: 1.2798311689567483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Healthcare disparities persist across socioeconomic boundaries, often attributed to unequal access to screening, diagnostics, and therapeutics. However, this perspective highlights that critical biases can emerge much earlier, during data collection and research prioritization, long before clinical implementation in cases where the focus of the studies and the data that is collected is at the molecular level. A vast number of studies focus on collecting omics data but the demographic information associated with these datasets is often not reported in the studies, and when it is reported, it shows big biases. An automated analysis of 4719 PubMed-indexed omics publications from 2015 to 2024 reveals that only a small fraction report ancestry or ethnicity information, with ancestry reporting improving slightly. Analysis of large-scale datasets commonly used for model training, such as CellxGene and GEO, reveals substantial population bias where European-ancestry data dominates. As biomedical foundation models become central to biomedical discovery with a paradigm in which base models are pretrained on large datasets and reusing them time and again for many different downstream tasks, they risk perpetuating or amplifying these early-stage biases, leading to cascading inequities that regulatory interventions cannot fully reverse. We propose a community-wide focus on three foundational principles: Provenance, Openness, and Evaluation Transparency to improve equity and robustness in biomedical AI. This approach aims to foster biomedical innovation that more effectively serves underserved populations and improves health outcomes.

Related papers

• MedFlow: Class-Aware Multi-Scale Generation for Medical Time-Series Synthesis [61.211117385840396]
  We propose MedFlow, a class-aware flow matching framework for medical time-series synthesis.<n>MedFlow employs a vector-quantized multi-scale tokenizer to represent medical sequences at complementary temporal resolutions.<n> Token Marginal Guidance, which incorporates class-conditional token statistics directly into the flow matching process, steers generation toward class-specific regions.
  arXiv  Detail & Related papers  (2026-09-04T07:02:12Z)
• Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency [52.50039435394964]
  We systematically evaluate foundation models for regression-based tasks.<n>We extract patch-level features from whole slide images (WSI) using five state-of-the-art foundation models.<n>Models are trained to predict continuous HRD scores based on these extracted features across breast, endometrial, and lung cancer cohorts.
  arXiv  Detail & Related papers  (2026-01-29T14:06:50Z)
• Who Does Your Algorithm Fail? Investigating Age and Ethnic Bias in the MAMA-MIA Dataset [8.774604259603304]
  We audit the fairness of the automated segmentation labels provided in the breast cancer tumor segmentation dataset MAMA-MIA.<n>Our analysis reveals an intrinsic age-related bias against younger patients that continues to persist even after controlling for confounding factors, such as data source.
  arXiv  Detail & Related papers  (2025-10-31T12:20:31Z)
• Biomedical Foundation Model: A Survey [84.26268124754792]
  Foundation models are large-scale pre-trained models that learn from extensive unlabeled datasets.<n>These models can be adapted to various applications such as question answering and visual understanding.<n>This survey explores the potential of foundation models across diverse domains within biomedical fields.
  arXiv  Detail & Related papers  (2025-03-03T22:42:00Z)
• Using Pre-training and Interaction Modeling for ancestry-specific disease prediction in UK Biobank [69.90493129893112]
  Recent genome-wide association studies (GWAS) have uncovered the genetic basis of complex traits, but show an under-representation of non-European descent individuals. Here, we assess whether we can improve disease prediction across diverse ancestries using multiomic data.
  arXiv  Detail & Related papers  (2024-04-26T16:39:50Z)
• Time-aware Heterogeneous Graph Transformer with Adaptive Attention Merging for Health Event Prediction [6.578298085691462]
  We introduce a novel heterogeneous graph learning model designed to assimilate disease domain knowledge and elucidate the intricate relationships between drugs and diseases.<n>When evaluated on two healthcare datasets, our approach demonstrated notable enhancements in both prediction accuracy and interpretability.
  arXiv  Detail & Related papers  (2024-04-23T08:01:30Z)
• MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentation [58.93221876843639]
  This paper introduces a novel, end-to-end diffusion-based risk prediction model, named MedDiffusion. It enhances risk prediction performance by creating synthetic patient data during training to enlarge sample space. It discerns hidden relationships between patient visits using a step-wise attention mechanism, enabling the model to automatically retain the most vital information for generating high-quality data.
  arXiv  Detail & Related papers  (2023-10-04T01:36:30Z)
• Federated Learning Enables Big Data for Rare Cancer Boundary Detection [98.5549882883963]
  We present findings from the largest Federated ML study to-date, involving data from 71 healthcare institutions across 6 continents. We generate an automatic tumor boundary detector for the rare disease of glioblastoma. We demonstrate a 33% improvement over a publicly trained model to delineate the surgically targetable tumor, and 23% improvement over the tumor's entire extent.
  arXiv  Detail & Related papers  (2022-04-22T17:27:00Z)
• The Health Gym: Synthetic Health-Related Datasets for the Development of Reinforcement Learning Algorithms [2.032684842401705]
  Health Gym is a collection of synthetic medical datasets that can be freely accessed to prototype, evaluate, and compare machine learning algorithms. The datasets were created using a novel generative adversarial network (GAN) The risk of sensitive information disclosure associated with the public distribution of the synthetic datasets is estimated to be very low.
  arXiv  Detail & Related papers  (2022-03-12T07:28:02Z)
• Potential sources of dataset bias complicate investigation of underdiagnosis by machine learning algorithms [20.50071537200745]
  Seyyed-Kalantari et al. find that models trained on three chest X-ray datasets yield disparities in false-positive rates. The study concludes that the models exhibit and potentially even amplify systematic underdiagnosis.
  arXiv  Detail & Related papers  (2022-01-19T20:51:38Z)
• Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype prediction [102.23901690661916]
  Low-dimensional embedding spaces can be derived from the UK Biobank population dataset to enhance data-scarce prediction of health indicators, lifestyle and demographic characteristics. Performances gains from semisupervison approaches will probably become an important ingredient for various medical data science applications.
  arXiv  Detail & Related papers  (2021-10-12T16:25:50Z)
• Combining Graph Neural Networks and Spatio-temporal Disease Models to Predict COVID-19 Cases in Germany [0.0]
  Several experts have called for the necessity to account for human mobility to explain the spread of COVID-19. Most statistical or epidemiological models cannot directly incorporate unstructured data sources, including data that may encode human mobility. We propose a trade-off between both research directions and present a novel learning approach that combines the advantages of statistical regression and machine learning models.
  arXiv  Detail & Related papers  (2021-01-03T16:39:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.