使用人工智能模拟专家小组诊断胆囊炎的严重程度
Griffin H Olsen1, Emmett D Goodman2,3, Josiah G Aklilu2
1Intermountain Healthcare Delivery Institute, Intermountain Health, Salt Lake City, UT, USA.
Surgical endoscopy
|August 18, 2025
概括
人工智能模型可以使用帕克兰分级尺度 (PGS) 预测胆囊炎的严重程度,与专家的表现相匹配. 然而,尺度的主观性限制了其作为AI训练场所的真实性.
科学领域:
- 医学成像医学成像
- 在手术中使用人工智能.
- 手术预测结果的预测.
背景情况:
- 帕克兰分级尺度 (PGS) 评估胆囊炎的严重程度,有助于预测手术困难和并发症.
- 专家小组的共识减少了PGS评级的主观性,但需要大量的时间.
- 人工智能模型为基于图像的有效和一致的诊断评估提供了潜力.
研究的目的:
- 开发和评估人工智能模型,使用PGS进行自动化胆囊炎严重程度分级.
- 将AI模型的性能与专家外科小组的共识进行比较.
- 评估AI模型在分级胆囊炎严重程度方面的可解释性.
主要方法:
- 分析了腹腔镜胆囊切除术视频,由三个外科专家手动分级代表性.
- 评估者之间的变异性使用加权的科恩卡帕进行了评估.
- 为自动化PGS分级开发了两种AI模型,并评估了它们的准确性和可解释性.
主要成果:
- 专家小组的共识实现了高的评级者之间的可靠性 (kappa: 0.76-0.83).
- 与模型A (69%,kappa:0.62) 相比,AI模型B表现出更高的准确性 (72%,kappa:0.77),而不是专家的共识.
- 模型B的分级受到胆囊,肝脏和体外观的影响.
结论:
- 基于变压器的AI模型可以有效地预测PGS评级,性能与个人专家相比.
- PGS固有的主观性和变异性对其作为人工智能开发中的明确基础真理的使用存在局限性.
- 人工智能在标准化胆囊炎严重程度评估方面表现有前途,但需要进一步改进.
相关概念视频
Chronic Pancreatitis II: Collaborative Care
128
The management of chronic pancreatitis is multifaceted, involving a comprehensive approach that includes thorough assessment, diagnostic testing, and a variety of management strategies.
Assessment:
Assessment:
128
Appendicitis-II: Diagnostic Studies and Management
145
Diagnosing and managing appendicitis requires a structured and comprehensive approach that spans from initial assessment to postoperative care. Here is an overview of the process:
Diagnosing Appendicitis
It requires a multifaceted approach, starting with a detailed physical examination to pinpoint the location and nature of the pain and identify any associated symptoms. Laboratory tests play a crucial role. A complete Blood Count (CBC) typically reveals leukocytosis (an increased number of...
Diagnosing Appendicitis
It requires a multifaceted approach, starting with a detailed physical examination to pinpoint the location and nature of the pain and identify any associated symptoms. Laboratory tests play a crucial role. A complete Blood Count (CBC) typically reveals leukocytosis (an increased number of...
145


