This prospective observational study aims to evaluate the agreement between artificial intelligence (AI)-assisted target point identification and experienced anesthesiologists during ultrasound-guided axillary brachial plexus block.
Ultrasound guidance is widely used in regional anesthesia to improve block success and safety. However, accurate identification of anatomical structures and optimal injection points remains operator-dependent. Artificial intelligence-based systems have the potential to assist clinicians by identifying anatomical landmarks in real time.
In this study, AI-generated target points will be compared with those determined by experienced anesthesiologists. The level of agreement between the two methods will be analyzed. Secondary outcomes will include block performance parameters and image quality.
The findings of this study may contribute to understanding the clinical utility of AI in ultrasound-guided regional anesthesia.
Age between 18 and 80 years
American Society of Anesthesiologists (ASA) physical status I-III
Patients scheduled for upper extremity surgery under ultrasound-guided axillary brachial plexus block as part of routine clinical practice
Ability to obtain adequate real-time ultrasound imaging of the axillary region prior to block performance
Inability to clearly visualize the axillary artery and at least one peripheral nerve (median, ulnar, radial, or musculocutaneous) on ultrasound imaging
Presence of significant ultrasound artifacts impairing image interpretation
History of previous surgery in the axillary region causing anatomical distortion
Anatomical deformities or significant anatomical variations in the axillary region
Adult patients aged 18-80 years with American Society of Anesthesiologists (ASA) physical status I-III undergoing upper extremity surgery under ultrasound-guided axillary brachial plexus block in routine clinical practice. Only patients with adequate real-time ultrasound imaging of the axillary region allowing identification of relevant anatomical structures will be included.
Case-only
Prospective
Ultrasound-Guided Axillary Brachial Plexus Block (Routine Clinical Practice)
Procedure/SurgeryUltrasound-guided axillary brachial plexus block performed as part of routine clinical care. No additional intervention is introduced for the purposes of the study. Real-time ultrasound images obtained during the procedure will be analyzed by an artificial intelligence system and experienced anesthesiologists.
Agreement in Target Point Identification Between Artificial Intelligence and Anesthesiologists
Agreement between artificial intelligence (AI) and experienced anesthesiologists in identifying target injection points will be evaluated using the intraclass correlation coefficient (ICC). Target points will be defined using coordinate-based measurements on real-time ultrasound images.
Proportion of Measurements Within Clinically Acceptable Agreement
The proportion of target point measurements with a difference of ≤5 mm between AI and anesthesiologists will be calculated. A difference of ≤5 mm will be considered clinically acceptable agreement.
Agreement in Nerve Identification
Agreement between AI and anesthesiologists in identifying peripheral nerves (median, ulnar, radial, and musculocutaneous) will be evaluated using Cohen's kappa coefficient.
Spatial Difference Between Target Points
The absolute distance (in millimeters) between AI-generated and anesthesiologist-defined target points will be calculated for each measurement.
Click on the lead sponsor to view all of their trials.
This trial is not recruiting at the moment. You can still explore other options:
