Shirzadi Mehdi, Martínez Mónica Rojas, Alonso Joan Francesc, Serna Leidy Yanet, Chaler Joaquim, Mañanas Miguel Angel, Marateb Hamid Reza
Automatic Control Department (ESAII), Biomedical Engineering Research Centre (CREB), Universitat Politècnica de Catalunya-Barcelona Tech (UPC), 08028 Barcelona, Spain.
EUSES-Bellvitge, Universitat de Girona, Universitat de Barcelona, ENTI, 08907 Barcelona, Spain.
Diagnostics (Basel). 2024 Oct 10;14(20):2255. doi: 10.3390/diagnostics14202255.
Innovative algorithms for wearable devices and garments are critical for diagnosing and monitoring disease (such as lateral epicondylitis (LE)) progression. LE affects individuals across various professions and causes daily problems.
We analyzed signals from the forearm muscles of 14 healthy controls and 14 LE patients using high-density surface electromyography. We discerned significant differences between groups by employing phase-amplitude coupling (PAC) features. Our study leveraged PAC, Daubechies wavelet with four vanishing moments (db4), and state-of-the-art techniques to train a neural network for the subject's label prediction.
Remarkably, PAC features achieved 100% specificity and sensitivity in predicting unseen subjects, while state-of-the-art features lagged with only 35.71% sensitivity and 28.57% specificity, and db4 with 78.57% sensitivity and 85.71 specificity. PAC significantly outperformed the state-of-the-art features (-value < 0.001) with a large effect size. However, no significant difference was found between PAC and db4 (-value = 0.147). Also, the Jeffries-Matusita (JM) distance of the PAC was significantly higher than other features (-value < 0.001), with a large effect size, suggesting PAC features as robust predictors of neuromuscular diseases, offering a profound understanding of disease pathology and new avenues for interpretation. We evaluated the generalization ability of the PAC model using 99.9% confidence intervals and Bayesian credible intervals to quantify prediction uncertainty across subjects. Both methods demonstrated high reliability, with an expected accuracy of 89% in larger, more diverse populations.
This study's implications might extend beyond LE, paving the way for enhanced diagnostic tools and deeper insights into the complexities of neuromuscular disorders.
用于可穿戴设备和服装的创新算法对于诊断和监测疾病（如外侧上髁炎（LE））的进展至关重要。LE影响各行各业的人，并导致日常问题。
我们使用高密度表面肌电图分析了14名健康对照者和14名LE患者前臂肌肉的信号。我们通过采用相位-振幅耦合（PAC）特征来辨别组间的显著差异。我们的研究利用PAC、具有四个消失矩的Daubechies小波（db4）和最先进的技术来训练神经网络以进行受试者标签预测。
值得注意的是，PAC特征在预测未见过的受试者时实现了100%的特异性和敏感性，而最先进的特征则滞后，敏感性仅为35.71%，特异性为28.57%，db4的敏感性为78.57%，特异性为85.71%。PAC显著优于最先进的特征（p值<0.001），效应量很大。然而，PAC和db4之间未发现显著差异（p值=0.147）。此外，PAC的杰弗里斯-马图西塔（JM）距离显著高于其他特征（p值<0.001），效应量很大，这表明PAC特征是神经肌肉疾病的可靠预测指标，为疾病病理学提供了深刻理解和新的解释途径。我们使用99.9%的置信区间和贝叶斯可信区间评估了PAC模型的泛化能力，以量化跨受试者的预测不确定性。两种方法都显示出高可靠性，在更大、更多样化的人群中预期准确率为89%。
本研究的意义可能超出LE，为增强诊断工具和更深入了解神经肌肉疾病的复杂性铺平道路。
