Thursday, December 5 | 12:35 p.m.-12:45 p.m. | R5A-SPCH-7 | Learning Center
AI can significantly enhance patient safety by identifying suspected misplacements of endotracheal tube (ETT) placements, according to a presentation in this session. Moreover, the tool significantly reduced wait times for radiological assessment, according to the group.
Axel Wismueller, MD, PhD, of the University of Rochester Medical Center in New York, will present a study of a commercially available model (aiOS, Aidoc) deployed as a computer-assisted triage tool in inpatient services of a large academic healthcare system between July 1, 2023 and December 31, 2023. A total of 10,709 frontal chest x-rays were analyzed. The researchers calculated the wait time for AI-notified cases with suspected malpositioned ETT findings and compared it with negative non-AI-notified cases, with wait time defined as the difference between the time of study acquisition completion to the time a radiologist opened the case for dictation.
The AI model provided prioritization notifications for 2.77% (297/10,412) of suspected positive cases for ETT malpositioning. The median wait time was 32.1 minutes (interquartile range: 104.2 minutes) for the suspected positive cases compared to 63.2 minutes (interquartile range: 170.9 minutes) for the suspected negative cases. The observed median wait time reduction was statistically significant (p-value < 0.05) at a 49.2% wait time reduction (31.1 minutes), according to the findings.
“The significant reduction in wait times for radiological assessment, as demonstrated by the 31.1-minute decrease in median response time, underscores the effectiveness of AI in prioritizing urgent cases in a clinical setting,” Wismueller and colleagues noted.
Check out this chest imaging Thursday afternoon poster discussion for all the details.
