一种算法方法来理解骨关节炎膝盖疼痛
Brandon G Hill1, Travis Byrum2, Anthony Zhou1
1Dartmouth Hitchcock Medical Center, Lebanon, New Hampshire.
JB & JS open access
|October 4, 2023
概括
深度学习准确地预测了X射线的膝关节骨关节炎疼痛,识别了传统分级之外的疼痛. 这种人工智能工具对了解膝关节骨关节炎的疼痛来源充满希望.
科学领域:
- 医疗成像中的人工智能
- 深度学习用于骨关节炎评估
- 膝关节疼痛的放射性分析
背景情况:
- 骨关节炎膝盖疼痛感知是复杂的,受关节内和外部因素的影响.
- 当前的评估方法可能无法完全捕捉患者的疼痛经历.
- 仅从X射线图来预测疼痛是一个重大的临床挑战.
研究的目的:
- 为了评估深度神经网络在预测骨关节炎膝关节疼痛和单个膝关节X射线图的症状方面的有效性.
- 为了确定AI是否能够识别标准放射分级中不明显的疼痛模式.
主要方法:
- 利用了超过5万张膝盖放射和来自骨关节炎倡议的相应膝盖损伤和骨关节炎结局得分 (KOOS) 数据.
- 训练有素的深度学习模型预测KOOS疼痛,症状和日常生活的分数从X光图像.
- 开发回归和分类模型来预测特定的分数和疼痛值.
主要成果:
- 深度学习模型的平均平方根误差为15.7 (疼痛),13.1 (症状) 和14.2 (日常生活).
- 该系统预测了高疼痛 (KOOS疼痛<40),曲线下的面积 (AUC) 为0.78.
- 准确地确定了X射线图 (Kellgren-Lawrence等级) 和报告的疼痛水平之间的差异.
结论:
- 一个深度神经网络可以预测骨关节炎膝关节疼痛和症状从单个X射线图与合理的准确性.
- 人工智能系统捕获了传统的凯尔格伦-劳伦斯分级所遗漏的疼痛和功能障碍细微差别.
- 对放射数据的深度学习为区分关节内膝关节疼痛与外部加重因素提供了潜力.
相关概念视频
01:25Analgesia and Pain Management
649
Pain is critical to various clinical pathologies, provoking an urgent need for effective management. Pain, whether acute or chronic, is a complex neurochemical process. Its alleviation depends on the type, with nonopioid analgesics effective for mild to moderate pain, such as musculoskeletal or inflammatory pain, while neuropathic pain responds best to anticonvulsants, tricyclic antidepressants, or serotonin/norepinephrine reuptake inhibitors. For severe acute or chronic pain, opioids may be...
649
01:23Knee Joint
1.9K
The knee joint is the most complicated joint in the body. It consists of three articulations– two tibiofemoral and one patellofemoral. As is characteristic of synovial joints, the knee joint has a thin articular capsule that partially surrounds this joint cavity. Additionally, several ligaments, muscles, and cartilaginous structures support the movement of the knee.
A total of seven ligaments support the knee joint. The patellar ligament, which is also attached to the quadriceps femoris...
A total of seven ligaments support the knee joint. The patellar ligament, which is also attached to the quadriceps femoris...
1.9K