The Evaluation of ChatGPT-4's Success in Identifying Anatomical Landmarks in Ultrasound Images of Regional Anesthesia Techniques
试验速览
- 阶段
- 不适用
- 状态
- 已完成
- 入组人数
- 147
- 试验地点
- 1
- 主要终点
- accuracy of ChatGPT-4
研究概览
简要总结
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.
详细描述
Background and Rationale:
With the increasing use of ultrasound in regional anesthesia, techniques such as peripheral nerve blocks and fascial plane blocks have become more reliable and safer. Ultrasound guidance has significantly improved the success rate of regional anesthesia, reducing complications by enabling accurate visualization of relevant anatomical structures. However, successful ultrasound-guided blocks require thorough knowledge of sonoanatomy. Without this expertise, there is a risk of improper anesthetic placement, potentially leading to block failure or unintended complications.
Experienced anesthesiologists proficient in sonoanatomy can easily interpret ultrasound images, but those with limited experience often face difficulties. This highlights the need for educational tools that can aid in teaching and improving the identification of anatomical landmarks. The development of AI-based systems, such as ChatGPT-4, for this purpose could revolutionize the training of regional anesthesia techniques by providing real-time feedback on ultrasound images.
Primary Aim:
The primary objective of this study is to evaluate the accuracy and effectiveness of ChatGPT-4 in identifying sonoanatomical landmarks from ultrasound images during regional anesthesia procedures.
研究设计
- 研究类型
- Observational
- 观察模型
- Case Only
- 时间视角
- Prospective
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Patients aged 18 years or older.
- •Patients undergoing surgery.
- •Patients receiving any regional anesthesia technique under ultrasound guidance.
- •Patients who have signed an informed consent form.
排除标准
- •Patients under the age of
- •Patients without a history of surgery.
- •Patients who have not received any regional anesthesia technique under ultrasound guidance.
- •Patients who have not signed the required informed consent documents will not be included in the study.
结局指标
主要结局
accuracy of ChatGPT-4
时间窗: immediately after procedure
Accuracy will be defined as the AI model's ability to correctly identify key anatomical landmarks (e.g., nerves, muscles, blood vessels, and fascial planes) that are crucial for successful block performance, compared to the gold standard interpretations provided by an experienced anesthesiologist.
次要结局
- ChatGPT-4's accuracy in predicting the specific block being performed(immediately after procedure)
- ChatGPT-4's accuracy in assessing the success of the block(immediately after procedure)
研究者
Engin Ihsan Turan
anesthesiology and reanimation specialist
Kanuni Sultan Suleyman Training and Research Hospital