一个初步的机械信息机器学习框架,用于客观评估帕金森病和康复结果
Amirali Hanifi1, Roozbeh Abedini-Nassab1, Mohammed N Ashtiani2
1Faculty of Mechanical Engineering, Tarbiat Modares University, Tehran 14115-111, Iran.
Diagnostics (Basel, Switzerland)
|November 27, 2025
概括
一个新的机器学习 (ML) 框架使用强力板数据客观地评估帕金森病 (PD) 运动控制和康复结果. 这种方法可以检测出传统统计数据所忽略的微妙的姿势变化,显示出个性化的PD护理的前景.
科学领域:
- 生物力学 生物力学
- 机器学习 机器学习
- 康复科学 康复科学 康复科学
背景情况:
- 由于有限的非侵入性方法,对帕金森病 (PD) 康复结果的客观评估具有挑战性.
- 现有的方法往往无法捕捉微妙的,非线性运动控制适应.
- 强力板数据提供了丰富的关于姿势控制和步态动态的信息.
研究的目的:
- 开发和验证机械知情机器学习 (ML) 框架,用于客观评估PD中的运动控制.
- 评估框架在有针对性的康复干预后检测微妙改善的能力.
- 将基于ML的分析与传统的统计方法进行比较,以检测PD患者的变化.
主要方法:
- 一组12名PD患者和6名健康对照人接受了干预前后的强力板测试.
- 与姿势摇摆和压力中心 (COP) 动态相关的特征被提取和选择.
- 减小维度 (t-SNE) 和K-意味着对已识别的组级模式进行集群.
- SHAP值和科恩的d定量化特征重要性和效果大小.
主要成果:
- K-意味着在PD患者中成功分离了干预前和干预后的状态,改善转向健康的对照群.
- 机器学习框架表现出强大的集群性能 (轮 0.77-0.79).
- 关键特征 (RMS-SML,PL-SAP) 显示了很大的效果大小,使PD患者与对照患者区分开来.
- 经过ML方法检测到群体内的显著变化,与传统的统计测试不同 (p > 0.05).
结论:
- 基于机械的初步ML框架有效地使用强力板数据检测PD相关的运动缺陷.
- 该框架对康复所引起的微妙,非线性姿势适应是敏感的.
- 需要在更大的队列中进行进一步的验证,以确认其在PD康复评估中的临床实用性.
相关概念视频
Parkinson's Disease: Treatment
953
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...
953
Parkinson's Disease: Overview
1.7K
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...
1.7K


