通过使用格拉米安角场和深度卷积神经网络分析可穿戴传感器数据来检测和评估帕金森病的严重程度
Sayyed Mostafa Mostafavi1, Shovito Barua Soumma1, Daniel Peterson1
1College of Health Solutions, Arizona State University, Phoenix, AZ 85004, USA.
Sensors (Basel, Switzerland)
|September 19, 2025
概括
这项研究引入了一种使用格拉米安角场 (GAF) 和深度卷积神经网络 (CNN) 的新方法,用于诊断帕金森病 (PD) 并通过步态信号评估其严重程度. 该方法在PD诊断和严重程度估计方面取得了很高的准确性,可能使得诊断工具更短,更容易获得.
科学领域:
- 神经科学是一个神经科学.
- 生物医学工程 生物医学工程
- 机器学习 机器学习
背景情况:
- 帕金森病 (PD) 是一种流行的神经退行性疾病,影响全球数百万人,主要是老年人.
- 目前的PD诊断依赖于对运动症状 (如勃拉迪基尼西亚和性) 的主观临床评估.
- 需要客观,定量方法来早期检测PD和严重程度监测.
研究的目的:
- 开发和验证一种新的方法来诊断PD,并通过步行信号评估其严重程度.
- 利用格拉米安角场 (GAF) 和深层卷积神经网络 (CNN) 来增强PD检测.
- 探索短步信号记录的潜力,以进行可访问的PD评估.
主要方法:
- 利用格拉米安角场 (GAFs) 将时间序列步态数据转换为图像表示.
- 应用深层卷积神经网络 (CNN) 用于PD的分类和严重程度估计.
- 采集的步态数据使用压力传感器嵌入鞋底.
主要成果:
- 实现了PD的高诊断准确性,准确率为98.6%,真阳性率为99.2%,真阴性率为98.5%.
- 在步行信号和Hoehn和Yahr/Timed Up and Go (TUG) 测试成绩之间显示出强烈的相关性 (R2>0.8).
- 显示UPDRS和UPDRS电机分数的预测准确性较低 (R2 < 0.2).
- 通过使用短步行信号窗口 (只需10秒) 实现了有效的诊断和严重性评估.
结论:
- GAFs-CNN模型为帕金森病的诊断和严重程度评估提供了一个高度准确和客观的方法.
- 使用这种方法进行的步行分析显示出开发更短,更容易获得的PD监测工具的希望.
- 进一步的研究可以完善该模型,以更好地预测特定PD严重程度尺度,如UPDRS.
相关概念视频
Parkinson's Disease: Overview
1.8K
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...
1.8K
Neural Regulation
43.1K
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.
43.1K
Parkinson's Disease: Treatment
987
Neurodegenerative disorders, such as Parkinson's Disease (PD), involve the gradual and irreversible destruction of neurons in particular brain areas. These disorders exhibit standard features like proteinopathies, selective vulnerability of some neurons, and an interaction of intrinsic properties, genetics, and environmental influences in neural injury.
Parkinson's Disease is primarily a result of the loss of dopaminergic neurons in the substantia nigra pars compacta. The cornerstone of...
Parkinson's Disease is primarily a result of the loss of dopaminergic neurons in the substantia nigra pars compacta. The cornerstone of...
987


