Evaluation of the impact of assistive artificial intelligence on ultrasound scanning for regional anaesthesia
Authors' conclusion
Use of an assistive AI device was associated with improved ultrasound image acquisition and interpretation.
Study context
- Population
- Anaesthetists who are non-experts in ultrasound-guided RA, scanning for six peripheral nerve blocks after a standardised teaching session126 scans assessed
- Participants
- 21 participants
- Comparison
- Ultrasound scanning with vs without an assistive artificial intelligence (AI) device
- Outcome
- Acquisition of the correct block view
Methodological detailswithin-participant comparison, expert assessment
- Within-participant comparison
- Expert assessment
Main finding
As reported in the abstract
Correct block view acquired
| Group | Value | Scans with correct view / scans assessed |
|---|---|---|
| With device | 90.3% | 56/62 |
| Without device | 75.1% | 47/62 |
Value
With device90.3%
Without device75.1%
Scans with correct view / scans assessed
With device56/62
Without device47/62
- With device vs Without device: P = 0.031 — two data points lost
Further findings
Correct identification of sono-anatomical structures on the view
P = 0.002
Structures correctly identified / structures assessed With device 188/212 · Without device 161/208
Participant confidence, expert global performance score, scan time
- No significant overall difference with vs without the device
Original publication
Evaluation of the impact of assistive artificial intelligence on ultrasound scanning for regional anaesthesia. Br J Anaesth. Published 8 September 2022. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →