基于语音分析和可解释机器学习的帕金森病的非侵入性检测
Huanqing Xu1, Wei Xie2, Mingzhen Pang3
1The School of Medical Information Engineering, Anhui University of Chinese Medicine, Hefei, China.
Frontiers in aging neuroscience
|May 15, 2025
概括
这项研究开发了一种机器学习模型,使用语音分析来早期检测帕金森病 (PD). 该模型使用诸如和闪之类的声学特征准确识别PD,提供一种非侵入性诊断工具.
科学领域:
- 神经科学是一个神经科学.
- 计算语言学 计算语言学
- 生物医学工程 生物医学工程
背景情况:
- 帕金森病 (PD) 是一种进展性神经退行性疾病,影响运动和语言功能.
- 早期发现PD对于改善患者的治疗结果和生活质量至关重要.
- 非侵入性语音分析为早期PD诊断提供了一个有希望的途径.
研究的目的:
- 开发一种可解释的机器学习模型,使用语音录音预测帕金森病.
- 为了确定PD的关键声学特征.
- 建立一种可靠的,非侵入性的方法来早期检测PD.
主要方法:
- 分析患有PD和没有PD的个体的语音录音,提取基本频率 (Fo),动,闪,噪音和声调比率 (NHR) 和非线性动态复杂度度等特征.
- 应用合成少数群体过量采样技术 (SMOTE) 来解决阶级不平衡问题.
- 实现和评估机器学习算法,包括随机森林和梯度提升,使用准确度,回忆,F1分数和AUC-ROC进行评估.
- 使用夏普利添加式解释 (SHAP) 进行模型解释性和特征重要性评估.
主要成果:
- 语音不稳定性特征 (,闪,NHR) 和非线性指标 (RPDE,PPE) 是PD的高度预测.
- 随机森林和梯度增强模型实现了卓越的性能,AUC-ROC为0.98和召回为0.95.
- SHAP分析确定了基本的频率变化和波与噪声比为区分PD患者的关键.
结论:
- 使用语音记录的机器学习模型可以准确预测帕金森病.
- 随机森林和梯度提升模型在PD检测方面表现出色.
- 语音分析,特别是侧重于声学不稳定性和非线性动态,为早期PD诊断提供了强大的非侵入性工具.
相关概念视频
Parkinson's Disease: Treatment
163
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...
163
Neural Regulation
39.0K
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.
39.0K
Parkinson's Disease: Overview
360
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...
360


