Evaluation of ChatGPT-4's Success Sonoanatomy

Summary

Aim and Importance:

Regional anesthesia techniques have advanced significantly with the advent of ultrasound guidance. Peripheral nerve blocks and fascial plane blocks can now be performed safely and effectively under ultrasound visualization. Research has shown that ultrasound use significantly improves block success rates. However, accurate application requires in-depth knowledge of sonoanatomy, as failure to identify critical structures may result in incorrect anesthetic placement or failed blocks. While experienced anesthesiologists can easily identify these anatomical landmarks, those less familiar with sonoanatomy may find it challenging.

This study aims to evaluate the effectiveness of ChatGPT-4 in identifying sonoanatomical structures in ultrasound images. A secondary objective is to assess whether artificial intelligence can evaluate the accuracy of regional anesthesia applications.

Expected Benefits and Risks:

The primary benefit is to explore the potential of AI-based systems in improving the learning and application of sonoanatomy, which may help anesthesiologists perform more accurate and successful blocks. We believe that the findings could contribute to regional anesthesia training. The study poses no risks to participants.

Study Type, Scope, and Design:

This prospective, observational study will be conducted at Health Sciences University Istanbul Kanuni Sultan Süleyman Education and Research Hospital. Ultrasound images from patients aged 18 and older undergoing regional anesthesia under ultrasound guidance will be photographed, without collecting personal data. Detailed images of the ultrasound-guided block steps will be captured. The position and orientation of the ultrasound probe will be documented for the AI model.

A customized GPT-4 model will be developed to evaluate the sonoanatomical structures in the provided ultrasound images based on the probe's position and orientation. Additionally, the AI model will predict which block is being performed and assess the success of the block by analyzing the images. An experienced anesthesiologist will evaluate the accuracy of the AI's predictions.

Conditions

• Regional Anesthesia

Interventions

OTHER

Sonoanatomical Structure Identification

ChatGPT-4 will analyze the ultrasound images to identify key anatomical landmarks such as nerves, muscles, blood vessels, and fascial planes that are critical for successful regional anesthesia. These structures will be labeled and compared to the expert anesthesiologist's assessment to determine accuracy.

OTHER

Block Type Prediction

Based on the ultrasound images and the position of the probe, ChatGPT-4 will predict the type of regional anesthesia block being performed (e.g., supraclavicular block, femoral nerve block). These predictions will be compared to the actual block performed to evaluate the AI's accuracy.

OTHER

Block Success Assessment

After analyzing the ultrasound images from the block application, ChatGPT-4 will assess whether the block was successfully administered. This assessment will be based on the correct placement of the needle, the spread of the anesthetic, and proximity to target structures. The AI's evaluation of block success will be compared to the expert anesthesiologist's judgment.

Sponsors & Collaborators

• Kanuni Sultan Suleyman Training and Research Hospital

  lead OTHER

Principal Investigators

• Engin ihsan Turan, Specialist · Health Science University İstanbul Kanuni Sultan Süleyman Education and Training Hospital

Eligibility

Min Age

18 Years

Sex

ALL

Healthy Volunteers

No

Timeline & Regulatory

Start

2024-10-17

Primary Completion

2025-02-15

Completion

2025-02-16

Countries

• Turkey (Türkiye)

Study Locations