Evaluation of Chest X-Ray AI Engine

CSC Lead: Laurence

CXR often go unreported for days, or are never reported. This has the potential to lead to missed or delayed diagnoses, and often means CXR reporting is performed by non-radiologists in the acute setting. A large proportion of CXR are normal, meaning already-stretched radiology departments must make time to analyse data that will not lead to a change in management or diagnosis. AI has the potential to ameliorate some of these challenges through improving accuracy and efficiency of CXR reporting.

We evaluated a commercial product which analyses chest x-rays. The evaluation performed was of a retrospective dataset (n=~20 000 scans) to understand the product’s technical performance. This project is now concluded and the results provided to the interested clinicians. There are no current plans to begin the prospective trial for this product, but when such a time arrives the project will be re-started.

Clinical lead: Vicky Goh,Carolyn Horst


References:
1) https://www.rcr.ac.uk/posts/new-reports-put-uk-radiologist-shortages-focus
2) Clinical Radiology UK workforce census 2020 report, The Royal College of Radiologists
3) https://www.england.nhs.uk/statistics/wp-content/uploads/sites/2/2018/06/Provisional-Monthly-Diagnostic-Imaging-Dataset-Statistics2018-06-21.pdf