RAIQC News - RAIQC used for the evaluation of GE Healthcare's AI tool for the detection of pneumothoraces

RAIQC used for the evaluation of GE Healthcare's AI tool for the detection of pneumothoraces

23 July 2024

RAIQC’s team is pleased to be listed in a new scientific paper published in the Emergency Medicine Journal, part of the British Medical Journal authored by Professor Alex Novak at Oxford University Hospitals. This paper publishes the findings of a study led by Prof Novak of an evaluation of an AI tool for the detection of pneumothoraces in patient chest X-rays. A pneumothorax (PTX) is a collapsed lung and occurs when air leaks into the space between your lung and chest wall.

The PTX AI tool was developed by GE Healthcare as part of their Critical Care Suite of AI software for assessing X-ray images and is deployed on GE Healthcare’s digital X-ray machines so can assess images as they are captured. The study demonstrates the effectiveness of the AI tool in improving the detection and reporting of PTX in patients being assessed for PTX. The improvement conferred by the AI is most marked in junior clinicians. RAIQC’s contribution to this project, which was run under the National Consortium for Intelligent Medical Imaging led by Oxford University, in which RAIQC was a partner, included input into the study design, providing a configured reporting for the clinical “readers” to assess the AI images and collation and evaluation of the study results. The RAIQC reader tool allowed clinicians at six NHS hospitals across the UK at Berkshire, Buckingham, Cornwall, Frimley, Glasgow and Oxford to review and score images online. This study provides evidence that AI-assisted image interpretation may be used to improve the diagnostic performance of clinicians, especially those more junior, in detecting pathological findings such as PTX.

We congratulate Professor Alex Novak and the entire study team in completing and publishing this important study. You can access the published version of the article by clicking here: https://emj.bmj.com/content/early/2024/07/15/emermed-2023-213620

Diagram showing flow of images and activities undertaken by radiologists during reader study

About RAIQC

RAIQC is a web-based platform that simulates day-to-day practice, allowing healthcare professionals, students and educators to review and report on diagnostic quality medical images in a secure online environment. Using over 6000 real-world clinical cases, RAIQC offers structured reporting study lists for training and assessment for individuals and healthcare providers across a range of imaging modalities and disease areas. The platform also provides hosting for clinical research and AI validation studies that require review of medical imaging.

For more information visit www.raiqc.com or email info@raiqc.com.

RAIQC Ltd is registered in England and Wales with company number 09863569 and its registered address at 1 & 3 Kings Meadow, Osney Mead, Oxford, OX2 0DP.