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

Despite much promising research in the area of artificial intelligence formedical image diagnosis, there has been no large-scale validation study done inThailand to confirm the accuracy and utility of such algorithms when applied tolocal datasets. Here we present a wide-reaching development and testing of adeep learning algorithm for automated thoracic disease detection, utilizing421,859 local chest radiographs. Our study shows that convolutional neuralnetworks can achieve remarkable performance in detecting 13 common abnormalityconditions on chest X-ray, and the incorporation of local images into thetraining set is key to the model's success. This paper presents astate-of-the-art model for CXR abnormality detection, reaching an average AUROCof 0.91. This model, if integrated to the workflow, can result in up to 55.6%work reduction for medical practitioners in the CXR analysis process. Our workemphasizes the importance of investing in local research of medical diagnosisalgorithms to ensure safe and efficient usage within the intended region.

Local Adaptation Improves Accuracy of Deep Learning Model for Automated X-Ray Thoracic Disease Detection : A Thai Study