Classification of needle-EMG resting potentials by machine learning
Classification of needle-EMG resting potentials by machine learning
复制标题
通过机器学习对针肌电图静息电位进行分类
DOI：
10.1002/mus.26363
复制
发表时间：
2018
期刊：
影响因子：
3.4
通讯作者：
Kaji Ryuji
中科院分区：
文献类型：
--
作者：
Nodera Hiroyuki;Osaki Yusuke;Yamazaki Hiroki;Mori Atsuko;Izumi Yuishin;Kaji Ryuji
简介：音频信号特征在针肌电图 (EMG) 中的诊断重要性已得到充分证实。鉴于最近人工智能音频识别的出现，我们假设特征静息肌电信号的提取和机器学习算法的应用可以帮助对各种肌电放电进行分类。方法：6类静息肌电信号的数据文件被分为2-s段。使用机器学习算法提取特征特征（分别为 384 个和 4,367 个特征），对 6 种放电类型进行分类。结果：在 841 个音频文件中，对于较小的特征集，观察到了 90.4% 的最佳总体准确率。在特征类中，梅尔频率倒谱系数（MFCC）相关特征对于正确分类很有用。结论：我们表明，通过特征提取和机器学习的结合，针肌电图静息信号可以令人满意地分类，这可以应用于临床环境。肌肉神经59：224-228，2019
Introduction: The diagnostic importance of audio signal characteristics in needle electromyography (EMG) is well established. Given the recent advent of audio‐sound identification by artificial intelligence, we hypothesized that the extraction of characteristic resting EMG signals and application of machine learning algorithms could help classify various EMG discharges.Methods: Data files of 6 classes of resting EMG signals were divided into 2‐s segments. Extraction of characteristic features (384 and 4,367 features each) was used to classify the 6 types of discharges using machine learning algorithms.Results: Across 841 audio files, the best overall accuracy of 90.4% was observed for the smaller feature set. Among the feature classes, mel‐frequency cepstral coefficients (MFCC)‐related features were useful in correct classification.Conclusions: We showed that needle EMG resting signals were satisfactorily classifiable by the combination of feature extraction and machine learning, and this can be applied to clinical settings.Muscle Nerve59:224–228, 2019