AI aids nonphysicians in obtaining diagnostic-quality ultrasound images in the ED
Artificial intelligence can aid nonphysicians in obtaining diagnostic-quality ultrasound images in the emergency department, according to research published Tuesday in JAMA Network Open [1].
The Focused Assessment with Sonography in Trauma, or FAST, protocol has shown promise in helping to quickly triage patients, both shortening lengths of stay and reducing medical costs. However, it can come with a steep learning curve, previous research has shown.
Taiwanese researchers recently explored the use of AI to aid novices in this approach. They found encouraging early results after testing out the intervention.
“The diagnostic quality score and the rate of acceptable clips were significantly higher with AI guidance,” corresponding author Chi-Yung Cheng, MD, with the Department of Emergency Medicine, Kaohsiung Chang Gung Memorial Hospital, and colleagues concluded. “Although initially it may take longer to complete an examination with AI guidance, it is expected that the learning curve will be lower for novices practicing FAST.”
For the research letter, Cheng et al. recruited 30 novice operators, split evenly between registered nurses, nurse practitioners, and EMTs with no prior sonography experience. They randomly split the group into those with AI assistance and those without, integrating the deep learning-based guidance into an application that captures ultrasound images and provides real-time feedback.
Operators were instructed to obtain images of the body’s Morrison pouch, and three expert echocardiographers assessed the images on a scale from 1-5. Deep learning-based guidance was associated with higher such scores and rates of acceptable image quality compared to the group that did not have AI assistance, the authors noted.
“This study showed that the DL algorithm can guide novices to obtain satisfactory diagnostic images over the Morison pouch,” Cheng and colleagues wrote, cautioning that the analysis was performed in a lab rather than a real trauma setting. “To fully evaluate the potential benefits of using AI in the management of patients with traumatic injury, further research in clinical deployment is necessary,” they added later.
Marty Stempniak has covered healthcare since 2012, with his byline appearing in the American Hospital Association's member magazine, Modern Healthcare and McKnight's. Prior to that, he wrote about village government and local business for his hometown newspaper in Oak Park, Illinois. He won a Peter Lisagor and Gold EXCEL awards in 2017 for his coverage of the opioid epidemic.