背景:神经退行性疾病(NDD)由于其衰弱的性质和有限的治疗选择而提出了重大挑战。准确及时的诊断对于优化患者护理和治疗策略至关重要。步态分析,利用可穿戴传感器,在评估与NDD相关的运动异常方面显示出了希望。
目的:研究问题1在多大程度上分析双肢在时频域中的相互作用可以作为准确分类NDD的合适方法?研究问题2彩色编码图像的利用效果如何,结合深度迁移学习模型,对于NDD的分类?
方法:使用GaitNDD数据库,包括亨廷顿病患者的录音,肌萎缩侧索硬化,帕金森病,和健康的控制。步态信号经过信号准备,小波相干分析,和用于特征增强的主成分分析。深度迁移学习模型(AlexNet,GoogLeNet,SqueezeNet)用于分类。性能指标,包括准确性,灵敏度,特异性,精度,和F1得分,使用5倍交叉验证进行评估。
结果:模型的分类性能因使用的时间窗口而异。对于5秒的步态信号段,AlexNet的准确率为95.91%,而GoogLeNet和SqueezeNet的准确率分别为96.49%和92.73%,分别。对于10秒段,AlexNet优于其他模型,准确率为99.20%,而GoogLeNet和SqueezeNet的准确率为96.75%和95.00%,分别。统计检验证实了所提取特征的显著性,表明它们对分类的辨别能力。
结论:与以前的研究相比,提出的方法表现出优异的性能,为NDD的自动诊断提供非侵入性和具有成本效益的方法。通过使用小波相干性分析步行过程中两条腿之间的相互作用,利用深度迁移学习模型,实现了对NDD的准确分类。
BACKGROUND: Neurodegenerative diseases (NDDs) pose significant challenges due to their debilitating nature and limited therapeutic options. Accurate and timely diagnosis is crucial for optimizing patient care and treatment strategies. Gait analysis, utilizing wearable sensors, has shown promise in assessing motor abnormalities associated with NDDs.
OBJECTIVE: Research Question 1 To what extent can analyzing the interaction of both limbs in the time-frequency domain serve as a suitable methodology for accurately classifying NDDs? Research Question 2 How effective is the utilization of color-coded images, in conjunction with deep transfer learning models, for the classification of NDDs?
METHODS: GaitNDD database was used, comprising recordings from patients with Huntington\'s disease, amyotrophic lateral sclerosis, Parkinson\'s disease, and healthy controls. The gait signals underwent signal preparation, wavelet coherence analysis, and principal component analysis for feature enhancement. Deep transfer learning models (AlexNet, GoogLeNet, SqueezeNet) were employed for classification. Performance metrics, including accuracy, sensitivity, specificity, precision, and F1 score, were evaluated using 5-fold cross-validation.
RESULTS: The classification performance of the models varied depending on the time window used. For 5-second gait signal segments, AlexNet achieved an accuracy of 95.91 %, while GoogLeNet and SqueezeNet achieved accuracies of 96.49 % and 92.73 %, respectively. For 10-second segments, AlexNet outperformed other models with an accuracy of 99.20 %, while GoogLeNet and SqueezeNet achieved accuracies of 96.75 % and 95.00 %, respectively. Statistical tests confirmed the significance of the extracted features, indicating their discriminative power for classification.
CONCLUSIONS: The proposed method demonstrated superior performance compared to previous studies, offering a non-invasive and cost-effective approach for the automated diagnosis of NDDs. By analyzing the interaction between both legs during walking using wavelet coherence, and utilizing deep transfer learning models, accurate classification of NDDs was achieved.