Deep-learning algorithm can improve imaging quality of FAST

A deep-learning algorithm could improve the imaging quality of Focused Assessment with Sonography in Trauma (FAST) among novice users, according to a report published in JAMA Network Open.

A team led by Dr I-Min Chiu from National Sun Yat-sen University in Kaohsiung, Taiwan, found that artificial intelligence (AI) guidance improved FAST image quality scores among novices but also led to longer imaging times.

“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,” Chiu and colleagues wrote.

FAST could help with shorter time to operative care, shortened hospital length of stay, and lower medical costs as indicated in previous reports. However, the researchers pointed out ultrasound’s high operator dependence, as well as FAST being “among the hardest protocols” for interpreting the acquired images.

Chiu and colleagues wanted to see if AI guidance could lead to higher quality of FAST exams as performed by novice ultrasonography users.

They recruited 30 operators for the study. These included 10 registered nurses, 10 nurse practitioners, and 10 emergency medical technicians (EMTs) without prior experience in performing ultrasonography. After receiving training on how to perform the FAST exam, the participants were randomized to a group that included or did not include AI guidance. The operators were told to perform FAST examination over the Morrison pouch in 10 healthy patients in the same order to obtain a five-second clip of the standard view within three minutes.

The operators created a total of 300 ultrasonography scans. The researchers reported that the intraclass correlation coefficient (ICC) for diagnostic quality scores was 0.97, indicating “excellent” reliability. The team found that AI guidance led to higher quality scores among operators.

The team also found that AI guidance was tied to a higher quality score with an odds ratio (OR) of 0.40 (p = 0.005), as well as a higher rate of acceptable quality with an OR of 3.82 (p < 0.001).

Additionally, it also found that AI guidance was significantly associated with longer examination time with an OR of 14.36 (p = 0.02). The researchers noted that this trend was “mostly observed” in the first few rounds of operations.

Finally, in subgroup analysis, nurse practitioners and EMTs benefitted most from AI guidance. Both groups had acceptable quality rates exceeding 0.8 on a 0-to-1 scale. These subgroups without AI guidance each had quality rates just above 0.6. Although the nurses showed slight improvement with AI guidance, this did not achieve statistical significance.

The study authors called for further research in clinical deployment, writing that this will help fully evaluate AI’s potential benefits in helping manage patients with traumatic injury. AuntMinnie