# Limitations of Public Chest Radiography Datasets for Artificial Intelligence: Label Quality, Domain Shift, Bias and Evaluation Challenges

arXiv: https://arxiv.org/abs/2509.15107 · HTML: https://mlsanity.com/paper/2509.15107/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 18 Sep 2025.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT](https://mlsanity.com/paper/2004.09167/) (2020)
- [PadChest: A large chest x-ray image dataset with multi-label annotated reports](https://mlsanity.com/paper/1901.07441/) (2019)
- [A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises](https://mlsanity.com/paper/2008.09104/) (2020)
- [Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning](https://mlsanity.com/paper/1602.03409/) (2016)
- [Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans](https://mlsanity.com/paper/2008.06388/) (2020)
- [CheXclusion: Fairness gaps in deep chest X-ray classifiers](https://mlsanity.com/paper/2003.00827/) (2020)
- [CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats](https://mlsanity.com/paper/2405.19538/) (2024)
- [COVID-19 Image Data Collection: Prospective Predictions Are the Future](https://mlsanity.com/paper/2006.11988/) (2020)
- [Deep Learning for Chest X-ray Analysis: A Survey](https://mlsanity.com/paper/2103.08700/) (2021)
- [NegBio: a high-performance tool for negation and uncertainty detection in radiology reports](https://mlsanity.com/paper/1712.05898/) (2017)
- [A Closer Look at AUROC and AUPRC under Class Imbalance](https://mlsanity.com/paper/2401.06091/) (2024)
- [Deep Learning Predicts Hip Fracture using Confounding Patient and Healthcare Variables](https://mlsanity.com/paper/1811.03695/) (2018)
- [A Decade's Battle on Dataset Bias: Are We There Yet?](https://mlsanity.com/paper/2403.08632/) (2024)
- [Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection](https://mlsanity.com/paper/2003.10769/) (2020)
- [Exploring large scale public medical image datasets](https://mlsanity.com/paper/1907.12720/) (2019)
- [VisualCheXbert: Addressing the Discrepancy Between Radiology Report Labels and Image Labels](https://mlsanity.com/paper/2102.11467/) (2021)
- [Quantifying and Leveraging Classification Uncertainty for Chest Radiograph Assessment](https://mlsanity.com/paper/1906.07775/) (2019)
- [CheXpert++: Approximating the CheXpert labeler for Speed,Differentiability, and Probabilistic Output](https://mlsanity.com/paper/2006.15229/) (2020)
- [Automatic dataset shift identification to support safe deployment of medical imaging AI](https://mlsanity.com/paper/2411.07940/) (2024)
- [Higher Chest X-ray Resolution Improves Classification Performance](https://mlsanity.com/paper/2306.06051/) (2023)
- [Understanding Dataset Bias in Medical Imaging: A Case Study on Chest X-rays](https://mlsanity.com/paper/2507.07722/) (2025)

## Built on by (most cited first, 2 of 2)

- [CLARiTy: A Vision Transformer for Multi-Label Classification and Weakly-Supervised Localization of Chest X-ray Pathologies](https://mlsanity.com/paper/2512.16700/) (2025)
- [Look What the Probes Dragged In! Real-World Chest X-ray Shortcuts in MedCLIP](https://mlsanity.com/paper/2608.12086/) (2026)

## Abstract (arXiv)

Artificial intelligence has shown significant promise in chest radiography, where deep learning models can approach radiologist-level diagnostic performance. Progress has been accelerated by large public datasets such as MIMIC-CXR, ChestX-ray14, PadChest, and CheXpert, which provide hundreds of thousands of labelled images with pathology annotations. However, these datasets also present important limitations. Automated label extraction from radiology reports introduces errors, particularly in handling uncertainty and negation, and radiologist review frequently disagrees with assigned labels. In addition, domain shift and population bias restrict model generalisability, while evaluation practices often overlook clinically meaningful measures. We conduct a systematic analysis of these challenges, focusing on label quality, dataset bias, and domain shift. Our cross-dataset domain shift evaluation across multiple model architectures revealed substantial external performance degradation, with pronounced reductions in AUPRC and F1 scores relative to internal testing. To assess dataset bias, we trained a source-classification model that distinguished datasets with near-perfect accuracy, and performed subgroup analyses showing reduced performance for minority age and sex groups. Finally, expert review by two board-certified radiologists identified significant disagreement with public dataset labels. Our findings highlight important clinical weaknesses of current benchmarks and emphasise the need for clinician-validated datasets and fairer evaluation frameworks.