P336 Variability between anaesthetists and artificial intelligence in identification of anatomical structures for ultrasound guided regional anaesthesia: a cross-sectional study in an academic department in Johannesburg, South Africa

<h3></h3> <b>Please confirm that an ethics committee approval has been applied for or granted</b>: Yes: I’m uploading the Ethics Committee Approval as a PDF file with this abstract submission Application for ESRA Abstract Prizes <h3>Background and Aims</h3> Accurate ultrasound-guided identification of anatomical structures is crucial for regional anaesthesia. This study compared artificial intelligence (AI) with human clinicians in identifying ‘Plan A’ nerve block structures to assess AI’s potential for training and clinical assistance, particularly in resource-limited settings. Plan A nerve blocks include Erector Spinae Plane (ESP), Rectus Sheath, Interscalene, Axillary Brachial Plexus, Femoral Nerve, Popliteal Sciatic and Distal Femoral Triangle. <h3>Methods</h3> This qualitative, cross-sectional study utilized 35 ultrasound images across 7 ‘Plan A’ nerve blocks. 20 registrars, 5 consultants, and an AI system (ScanNav™ Anatomy PNB, Intelligent Ultrasound, Cardiff, UK) identified 125 anatomical structures each, totaling 3250 observations, against expert ground truth. <h3>Results</h3> The AI system achieved superior overall accuracy (94%) compared to 25 participants, 5 consultants (79%) and 20 registrars (59%) in anatomical structure identification. Expert annotation comparatively obtained an overall accuracy of 98%. While consultants showed high accuracy for many structures, both human groups struggled with specific nerves (e.g., Median Nerve: consultants 36%, registrars 16%). AI maintained high accuracy even for structures poorly identified by humans, such as the Fascia Iliaca (AI 80%, consultants 28%, registrars 24%) and Radial Nerve (AI 100%, consultants 56%, registrars 25%). <h3>Conclusions</h3> AI demonstrates superior accuracy in identifying anatomical structures for Plan A nerve blocks. This highlights a significant training gap among registrars and underscores AI’s utility as a robust tool for assisting and training clinicians in regional anaesthesia, especially in resource-limited environments where access to expert lead training is limited.