English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Since the emergence of COVID-19, deep learning models have been developed toidentify COVID-19 from chest X-rays. With little to no direct access tohospital data, the AI community relies heavily on public data comprisingnumerous data sources. Model performance results have been exceptional whentraining and testing on open-source data, surpassing the reported capabilitiesof AI in pneumonia-detection prior to the COVID-19 outbreak. In this studyimpactful models are trained on a widely used open-source data and tested on anexternal test set and a hospital dataset, for the task of classifying chestX-rays into one of three classes: COVID-19, non-COVID pneumonia andno-pneumonia. Classification performance of the models investigated isevaluated through ROC curves, confusion matrices and standard classificationmetrics. Explainability modules are implemented to explore the image featuresmost important to classification. Data analysis and model evaluations show thatthe popular open-source dataset COVIDx is not representative of the realclinical problem and that results from testing on this are inflated. Dependenceon open-source data can leave models vulnerable to bias and confoundingvariables, requiring careful analysis to develop clinically useful/viable AItools for COVID-19 detection in chest X-rays.

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