English

The pitfalls of using open data to develop deep learning solutions for COVID-19 detection in chest X-rays

Computer Vision and Pattern Recognition 2021-09-17 v1 Machine Learning Image and Video Processing

Abstract

Since the emergence of COVID-19, deep learning models have been developed to identify COVID-19 from chest X-rays. With little to no direct access to hospital data, the AI community relies heavily on public data comprising numerous data sources. Model performance results have been exceptional when training and testing on open-source data, surpassing the reported capabilities of AI in pneumonia-detection prior to the COVID-19 outbreak. In this study impactful models are trained on a widely used open-source data and tested on an external test set and a hospital dataset, for the task of classifying chest X-rays into one of three classes: COVID-19, non-COVID pneumonia and no-pneumonia. Classification performance of the models investigated is evaluated through ROC curves, confusion matrices and standard classification metrics. Explainability modules are implemented to explore the image features most important to classification. Data analysis and model evaluations show that the popular open-source dataset COVIDx is not representative of the real clinical problem and that results from testing on this are inflated. Dependence on open-source data can leave models vulnerable to bias and confounding variables, requiring careful analysis to develop clinically useful/viable AI tools for COVID-19 detection in chest X-rays.

Keywords

Cite

@article{arxiv.2109.08020,
  title  = {The pitfalls of using open data to develop deep learning solutions for COVID-19 detection in chest X-rays},
  author = {Rachael Harkness and Geoff Hall and Alejandro F Frangi and Nishant Ravikumar and Kieran Zucker},
  journal= {arXiv preprint arXiv:2109.08020},
  year   = {2021}
}

Comments

To be published in MedInfo 21 - 18th World Congress on Medical and Health Informatics; 5 pages, 5 figures

R2 v1 2026-06-24T06:02:20.544Z