AI and Tracheal Tube Positioning: RAIQC Contributes to Key Evaluation Study
31 March 2025
Accurate tracheal tube placement is vital for patients requiring mechanical ventilation. Misplaced tubes can lead to severe complications, including hypoxia and respiratory failure. The AI algorithm, integrated within the GE Healthcare software, uses a chest radiograph to highlight the tracheal tube’s outline, indicate the carina's position, and measure the distance between the tube tip and carina. This tool aims to improve the clinician's ability to assess tube positioning accurately.
The study, which took place on the RAIQC platform, used a large, retrospective dataset of chest radiographs. RAIQC facilitated the evaluation by providing a comprehensive platform for remotely assessing and comparing the AI algorithm's performance. The radiographs used in the study included both well-positioned and mispositioned tracheal tubes, with expert radiologists providing the reference standard.
Key findings from the study showed that the AI algorithm demonstrated strong agreement with the reference standard, with a mean difference of just 0.046 mm between the AI output and expert radiologists' measurements. The AI tool demonstrated a high level of accuracy, with its measurements closely matching those of expert radiologists. It also performed consistently across a range of cases, with only minor discrepancies occurring in borderline misplacements. These findings suggest that AI could play a valuable role in supporting clinical assessments of tracheal tube positioning.
RAIQC played a central role in facilitating this study by providing the platform for expert image review, supporting data organisation, and assisting in analysis. By enabling structured evaluations of AI tools, RAIQC continues to support research that informs the integration of AI into medical imaging.
This study contributes to the growing body of evidence on AI’s role in radiology. As hospitals seek to enhance diagnostic accuracy and efficiency, AI-driven tools like GE Critical Care Suite 2.0 may become valuable assets in critical care settings. Further research will help define the best approaches for implementing AI in clinical practice.
A link to the paper posted on the British Journal of Anaesthesia can be accessed here for free: https://authors.elsevier.com/
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.