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

TL;DR

This paper critically examines the limitations of using open-source COVID-19 chest X-ray datasets for deep learning, revealing that models trained on such data may not generalize well to real clinical settings and are prone to bias.

Contribution

The study highlights the pitfalls of relying on open-source datasets like COVIDx for COVID-19 detection, emphasizing the need for careful validation on diverse and representative data.

Findings

Models trained on COVIDx perform poorly on external and hospital datasets.

Open-source datasets may contain biases that inflate model performance.

Careful analysis is required to develop clinically useful AI tools.

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.