基于卷积神经网络的早期帕金森病的检测,使用6分钟步行测试
Hyejin Choi1, Changhong Youm2, Hwayoung Park3
1Department of Health Sciences, The Graduate School of Dong-A University, Busan, Republic of Korea.
Scientific reports
|September 30, 2024
概括
早期诊断帕金森病 (PD) 是一个挑战. 一个卷积神经网络 (CNN) 用可穿戴传感器分析6分钟步行测试 (6MWT) 在识别PD患者方面取得了83.5%的准确性.
科学领域:
- 神经学 神经学
- 生物医学工程 生物医学工程
- 数据科学数据科学数据科学
背景情况:
- 帕金森病 (PD) 诊断是困难的,因为症状异质,特别是在早期阶段.
- 微妙的步态变化是PD的早期指标,但很难客观地检测到.
- 可穿戴式传感器为客观,定量评估运动功能的有希望的途径.
研究的目的:
- 为了评估卷积神经网络 (CNN) 的诊断准确性,使用可穿戴传感器的6分钟步行测试 (6MWT) 数据.
- 为了区分患有早期帕金森病 (PD) 的人与健康对照人.
- 为了确定特定的身体部分和传感器数据最有效的PD检测.
主要方法:
- 参与者 (78名早期PD患者,50名健康对照) 在6MWT期间佩戴了6个传感器.
- 时间序列传感器数据 (陀螺仪,加速度计) 被转化为图像表示.
- 卷积神经网络 (CNN) 模型经过训练和验证,根据传感器数据对PD进行分类.
主要成果:
- 来自腰椎的陀螺垂直元件产生了最高的分类准确度 (83.5%).
- 胸脊 (83.1%) 和右大腿 (79.5%) 段的高精度也被观察到.
- 这些发现突显了基于传感器的特定步态参数对于PD检测的潜力.
结论:
- 6MWT与CNN对可穿戴传感器数据的分析相结合,显示了早期PD诊断的巨大潜力.
- 这种方法可能使步态异常在进展过程中能够及时进行临床干预.
- 使用可穿戴技术的客观步态分析可以帮助监测PD症状和治疗反应.
更多相关视频
07:26Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking
Published on: September 26, 2019
7.8K
04:08Applying the RatWalker System for Gait Analysis in a Genetic Rat Model of Parkinson's Disease
Published on: January 18, 2021
2.8K
相关概念视频
Neural Regulation
39.2K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
39.2K
Parkinson's Disease: Overview
492
Neurodegenerative disorders are progressive diseases that cause irreversible damage and loss to neurons in specific brain areas. Examples of these disorders include Parkinson's disease, Alzheimer's disease, Multiple Sclerosis (MS), and Amyotrophic Lateral Sclerosis (ALS). These disorders share characteristics such as proteinopathies, selective neuronal vulnerability, and a complex interplay between genetic and environmental factors. The primary therapeutic goal for these conditions is...
492
