Learning curve analysis of artificial intelligence-assisted ultrasound for teaching popliteal fossa sciatic nerve block to novice anesthesiologists: a pilot randomized educational study

Background Artificial intelligence (AI)-assisted ultrasound may improve ultrasound-guided regional nerve blocks, but its effect on novice learning curves is unclear. Methods In this pilot randomized educational study (June–August 2025), inexperienced anesthesiology residents from Shanghai General Hospital were assigned to AI-assisted or conventional training groups. The AI group used an ultrasound system with an AI module and received additional ethics and principles training, while the conventional group received standard training. Image acquisition and interpretation, debriefing time, trainee speaking time, and feedback were evaluated. Results Twenty-one trainee anesthesiologists were recruited (AI, n = 10; conventional, n = 11). The group-level cumulative sum (CUSUM) analysis identified an estimated turning point (TP) at approximately 12 attempts in the AI group. No comparable TP was identified within the 15-attempt training period in the conventional group. No statistically significant between-group differences were detected in participant-level phase-specific success rates (all P > 0.05). Compared with the conventional group, the AI group reported higher post-training feedback scores for training content (4.7 ± 0.5 vs . 3.6 ± 1.0, P = 0.0076), satisfaction (4.9 ± 0.3 vs . 3.5 ± 0.8, P < 0.0001), and confidence (5.0 ± 0.0 vs . 4.5 ± 0.7, P = 0.0216). Compared with the conventional group, the AI group also had a shorter participant-level mean debriefing time (7.33 ± 0.34 vs . 10.65 ± 0.61 min, P < 0.0001) and a greater proportion of trainee speaking time during debriefing (69.5% (65.70, 70.55) vs . 49.0% (46.70, 49.70), P < 0.0001). Conclusions AI-assisted ultrasound training might enhance post-training feedback, increase satisfaction and confidence, and reduce debriefing time among inexperienced anesthesiology residents, suggesting its potential utility in the medical education of ultrasound.