1
|
Li N, Ou J, He H, He J, Zhang L, Peng Z, Zhong J, Jiang N. Exploration of a machine learning approach for diagnosing sarcopenia among Chinese community-dwelling older adults using sEMG-based data. J Neuroeng Rehabil 2024; 21:69. [PMID: 38725065 PMCID: PMC11080130 DOI: 10.1186/s12984-024-01369-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2024] [Accepted: 04/25/2024] [Indexed: 05/13/2024] Open
Abstract
BACKGROUND In the practical application of sarcopenia screening, there is a need for faster, time-saving, and community-friendly detection methods. The primary purpose of this study was to perform sarcopenia screening in community-dwelling older adults and investigate whether surface electromyogram (sEMG) from hand grip could potentially be used to detect sarcopenia using machine learning (ML) methods with reasonable features extracted from sEMG signals. The secondary aim was to provide the interpretability of the obtained ML models using a novel feature importance estimation method. METHODS A total of 158 community-dwelling older residents (≥ 60 years old) were recruited. After screening through the diagnostic criteria of the Asian Working Group for Sarcopenia in 2019 (AWGS 2019) and data quality check, participants were assigned to the healthy group (n = 45) and the sarcopenic group (n = 48). sEMG signals from six forearm muscles were recorded during the hand grip task at 20% maximal voluntary contraction (MVC) and 50% MVC. After filtering recorded signals, nine representative features were extracted, including six time-domain features plus three time-frequency domain features. Then, a voting classifier ensembled by a support vector machine (SVM), a random forest (RF), and a gradient boosting machine (GBM) was implemented to classify healthy versus sarcopenic participants. Finally, the SHapley Additive exPlanations (SHAP) method was utilized to investigate feature importance during classification. RESULTS Seven out of the nine features exhibited statistically significant differences between healthy and sarcopenic participants in both 20% and 50% MVC tests. Using these features, the voting classifier achieved 80% sensitivity and 73% accuracy through a five-fold cross-validation. Such performance was better than each of the SVM, RF, and GBM models alone. Lastly, SHAP results revealed that the wavelength (WL) and the kurtosis of continuous wavelet transform coefficients (CWT_kurtosis) had the highest feature impact scores. CONCLUSION This study proposed a method for community-based sarcopenia screening using sEMG signals of forearm muscles. Using a voting classifier with nine representative features, the accuracy exceeds 70% and the sensitivity exceeds 75%, indicating moderate classification performance. Interpretable results obtained from the SHAP model suggest that motor unit (MU) activation mode may be a key factor affecting sarcopenia.
Collapse
Affiliation(s)
- Na Li
- The National Clinical Research Center for Geriatrics, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China
- Medical Equipment Innovation Research Center, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China
- The Med-X Center for Manufacturing, Sichuan University, Chengdu, Sichuan, 610041, China
| | - Jiarui Ou
- College of Computer Science, Sichuan University, Chengdu, 610065, China
| | - Haoru He
- The National Clinical Research Center for Geriatrics, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China
- Medical Equipment Innovation Research Center, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China
- The Med-X Center for Manufacturing, Sichuan University, Chengdu, Sichuan, 610041, China
| | - Jiayuan He
- The National Clinical Research Center for Geriatrics, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China
- Medical Equipment Innovation Research Center, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China
- The Med-X Center for Manufacturing, Sichuan University, Chengdu, Sichuan, 610041, China
| | - Le Zhang
- College of Computer Science, Sichuan University, Chengdu, 610065, China
| | - Zhengchun Peng
- School of Electronic Information and ElectricaEngineering, Shanghaijiao Tong University, Shanghai, 200240, China
| | - Junwen Zhong
- Department of Electromechanical Engineering and Centre for Artificial Intelligence and Robotics, University of Macau, Macau, SAR, 999078, China
| | - Ning Jiang
- The National Clinical Research Center for Geriatrics, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China.
- Medical Equipment Innovation Research Center, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China.
- The Med-X Center for Manufacturing, Sichuan University, Chengdu, Sichuan, 610041, China.
| |
Collapse
|
2
|
Huang C, Chen M, Li X, Zhang Y, Li S, Zhou P. Neurophysiological Factors Affecting Muscle Innervation Zone Estimation Using Surface EMG: A Simulation Study. BIOSENSORS-BASEL 2021; 11:bios11100356. [PMID: 34677312 PMCID: PMC8534086 DOI: 10.3390/bios11100356] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/16/2021] [Revised: 09/16/2021] [Accepted: 09/24/2021] [Indexed: 11/16/2022]
Abstract
Surface electromyography (EMG) recorded by a linear or 2-dimensional electrode array can be used to estimate the location of muscle innervation zones (IZ). There are various neurophysiological factors that may influence surface EMG and thus potentially compromise muscle IZ estimation. The objective of this study was to evaluate how surface-EMG-based IZ estimation might be affected by different factors, including varying degrees of motor unit (MU) synchronization in the case of single or double IZs. The study was performed by implementing a model simulating surface EMG activity. Three different MU synchronization conditions were simulated, namely no synchronization, medium level synchronization, and complete synchronization analog to M wave. Surface EMG signals recorded by a 2-dimensional electrode array were simulated from a muscle with single and double IZs, respectively. For each situation, the IZ was estimated from surface EMG and compared with the one used in the model for performance evaluation. For the muscle with only one IZ, the estimated IZ location from surface EMG was consistent with the one used in the model for all the three MU synchronization conditions. For the muscle with double IZs, at least one IZ was appropriately estimated from interference surface EMG when there was no MU synchronization. However, the estimated IZ was different from either of the two IZ locations used in the model for the other two MU synchronization conditions. For muscles with a single IZ, MU synchronization has little effect on IZ estimation from electrode array surface EMG. However, caution is required for multiple IZ muscles since MU synchronization might lead to false IZ estimation.
Collapse
Affiliation(s)
- Chengjun Huang
- Guangdong Work Injury Rehabilitation Center, Guangzhou 510970, China;
- Department of Physical Medicine and Rehabilitation, University of Texas Health Science Center at Houston, Houston, TX 77030, USA;
| | - Maoqi Chen
- Faculty of Rehabilitation Engineering, University of Health and Rehabilitation Sciences, Qingdao 266024, China;
| | - Xiaoyan Li
- Department of Bioengineering, University of Maryland, College Park, MD 20742, USA;
- Department of Neurology, Medical College of Wisconsin, Milwaukee, WI 53226, USA
| | - Yingchun Zhang
- Department of Biomedical Engineering, University of Houston, Houston, TX 77204, USA;
| | - Sheng Li
- Department of Physical Medicine and Rehabilitation, University of Texas Health Science Center at Houston, Houston, TX 77030, USA;
| | - Ping Zhou
- Faculty of Rehabilitation Engineering, University of Health and Rehabilitation Sciences, Qingdao 266024, China;
- Correspondence:
| |
Collapse
|
3
|
Muscle Fiber Diameter and Density Alterations after Stroke Examined by Single-Fiber EMG. Neural Plast 2021; 2021:3045990. [PMID: 34434227 PMCID: PMC8380495 DOI: 10.1155/2021/3045990] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2021] [Revised: 07/01/2021] [Accepted: 07/30/2021] [Indexed: 11/18/2022] Open
Abstract
This study presents single-fiber electromyography (EMG) analysis for assessment of paretic muscle changes after stroke. Single-fiber action potentials (SFAPs) were recorded from the first dorsal interosseous (FDI) muscle bilaterally in 12 individuals with hemiparetic stroke. The SFAP parameters, including the negative peak duration and the peak-peak amplitude, were measured and further used to estimate muscle fiber diameter through a model based on the quadratic function. The SFAP parameters, fiber density, and muscle fiber diameter derived from the model were compared between the paretic and contralateral muscles. The results show that SFAPs recorded from the paretic muscle had significantly smaller negative peak duration than that from the contralateral muscle. As a result, the derived muscle fiber diameter of the paretic muscle was significantly smaller than that of the contralateral muscle. The fiber density of the paretic muscle was significantly higher than that of the contralateral muscle. These results provide further evidence of remodeled motor units after stroke and suggest that paretic muscle weakness can be due to both complex central and peripheral neuromuscular alterations.
Collapse
|
4
|
Beretta-Piccoli M, Cescon C, Barbero M, D’Antona G. Identification of muscle innervation zones using linear electrode arrays: a fundamental step to measure fibers conduction velocity. ARAB JOURNAL OF BASIC AND APPLIED SCIENCES 2021. [DOI: 10.1080/25765299.2021.1894731] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022] Open
Affiliation(s)
- Matteo Beretta-Piccoli
- Rehabilitation Research Laboratory, Department of Business Economics, Health and Social Care, University of Applied Sciences and Arts of Southern Switzerland, SUPSI, Manno, Switzerland
- Criams-Sport Medicine Centre Voghera, University of Pavia, Pavia, Italy
| | - Corrado Cescon
- Rehabilitation Research Laboratory, Department of Business Economics, Health and Social Care, University of Applied Sciences and Arts of Southern Switzerland, SUPSI, Manno, Switzerland
| | - Marco Barbero
- Rehabilitation Research Laboratory, Department of Business Economics, Health and Social Care, University of Applied Sciences and Arts of Southern Switzerland, SUPSI, Manno, Switzerland
| | - Giuseppe D’Antona
- Criams-Sport Medicine Centre Voghera, University of Pavia, Pavia, Italy
- Department of Public Health, Experimental and Forensic medicine, University of Pavia, Pavia, Italy
| |
Collapse
|
5
|
Separation of interference surface electromyogram into propagating and non-propagating components. Biomed Signal Process Control 2019. [DOI: 10.1016/j.bspc.2019.04.016] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
|
6
|
Ye X, Beck TW, Wages NP. Prolonged passive static stretching-induced innervation zone shift in biceps brachii. Appl Physiol Nutr Metab 2015; 40:482-8. [DOI: 10.1139/apnm-2014-0546] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
Abstract
The purpose of this study was to examine the influence of a bout of repeated and prolonged passive static stretching on the innervation zone (IZ) location of the human biceps brachii muscle. Eleven men performed 12 sets of 100-s passive stretches on their biceps brachii. Before (Pre) and immediately after (Post) the stretching intervention, isometric strength was tested during the maximal voluntary contractions (MVCs) of the forearm flexors. The subjects also performed several separate isometric forearm flexion muscle actions at 30%, 50%, and 70% of their predetermined MVCs for examining the locations of the IZ at different contraction intensities. The IZ was identified through multi-channel surface electromyographic (EMG) recordings from a linear electrode array. The stretching intervention induced an average of 10% isometric strength loss for the forearm flexors (mean ± SD: Pre-MVC vs. Post-MVC = 332.12 ± 59.40 N vs. 299.53 ± 70.51 N; p < 0.001). In addition, the average IZ shift was nearly 4.5 mm in average in the proximal direction. However, this shift was not specific to the contraction intensity. We believe that the IZ shift was caused by the elongation of the entire muscle-tendon unit in the proximal direction. Therefore, caution should be taken when using surface EMG technique to examine possible changes in the EMG variables after a stretching protocol, as these variables can be contaminated by the shift of the IZ.
Collapse
Affiliation(s)
- Xin Ye
- Biophysics Laboratory, Department of Health and Exercise Science, University of Oklahoma, Norman, OK 73019, USA
- Biophysics Laboratory, Department of Health and Exercise Science, University of Oklahoma, Norman, OK 73019, USA
| | - Travis W. Beck
- Biophysics Laboratory, Department of Health and Exercise Science, University of Oklahoma, Norman, OK 73019, USA
- Biophysics Laboratory, Department of Health and Exercise Science, University of Oklahoma, Norman, OK 73019, USA
| | - Nathan P. Wages
- Biophysics Laboratory, Department of Health and Exercise Science, University of Oklahoma, Norman, OK 73019, USA
- Biophysics Laboratory, Department of Health and Exercise Science, University of Oklahoma, Norman, OK 73019, USA
| |
Collapse
|
7
|
Wu P, Chawla A, Spinner RJ, Yu C, Yaszemski MJ, Windebank AJ, Wang H. Key changes in denervated muscles and their impact on regeneration and reinnervation. Neural Regen Res 2014; 9:1796-809. [PMID: 25422641 PMCID: PMC4239769 DOI: 10.4103/1673-5374.143424] [Citation(s) in RCA: 58] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 08/11/2014] [Indexed: 11/29/2022] Open
Abstract
The neuromuscular junction becomes progressively less receptive to regenerating axons if nerve repair is delayed for a long period of time. It is difficult to ascertain the denervated muscle's residual receptivity by time alone. Other sensitive markers that closely correlate with the extent of denervation should be found. After a denervated muscle develops a fibrillation potential, muscle fiber conduction velocity, muscle fiber diameter, muscle wet weight, and maximal isometric force all decrease; remodeling increases neuromuscular junction fragmentation and plantar area, and expression of myogenesis-related genes is initially up-regulated and then down-regulated. All these changes correlate with both the time course and degree of denervation. The nature and time course of these denervation changes in muscle are reviewed from the literature to explore their roles in assessing both the degree of detrimental changes and the potential success of a nerve repair. Fibrillation potential amplitude, muscle fiber conduction velocity, muscle fiber diameter, mRNA expression levels of myogenic regulatory factors and nicotinic acetylcholine receptor could all reflect the severity and length of denervation and the receptiveness of denervated muscle to regenerating axons, which could possibly offer an important clue for surgical choices and predict the outcomes of delayed nerve repair.
Collapse
Affiliation(s)
- Peng Wu
- Department of Neurologic Surgery, Mayo Clinic, Rochester, MN, USA ; Department of Hand Surgery, Huashan Hospital, Fudan University, Shanghai, China ; Department of Orthopedic Surgery, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang Province, China
| | - Aditya Chawla
- Department of Neurologic Surgery, Mayo Clinic, Rochester, MN, USA ; Department of Orthopedic Surgery, Wake Forest School of Medicine, Winston-Salem, NC, USA
| | - Robert J Spinner
- Department of Neurologic Surgery, Mayo Clinic, Rochester, MN, USA
| | - Cong Yu
- Department of Hand Surgery, Huashan Hospital, Fudan University, Shanghai, China
| | - Michael J Yaszemski
- Departments of Orthopedic Surgery and Biomedical Engineering, Mayo Clinic, Rochester, MN, USA
| | | | - Huan Wang
- Department of Neurologic Surgery, Mayo Clinic, Rochester, MN, USA ; Shanghai Key Laboratory of Peripheral Nerve and Microsurgery, Shanghai, China
| |
Collapse
|
8
|
Klaver-KrÓl EG, Rasker JJ, Henriquez NR, Verheijen WG, Zwarts MJ. Muscle fiber velocity and electromyographic signs of fatigue in fibromyalgia. Muscle Nerve 2012; 46:738-45. [DOI: 10.1002/mus.23382] [Citation(s) in RCA: 11] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
|
9
|
Al-Mulla MR, Sepulveda F, Colley M. A review of non-invasive techniques to detect and predict localised muscle fatigue. SENSORS (BASEL, SWITZERLAND) 2011; 11:3545-94. [PMID: 22163810 PMCID: PMC3231314 DOI: 10.3390/s110403545] [Citation(s) in RCA: 167] [Impact Index Per Article: 12.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/07/2011] [Revised: 03/01/2011] [Accepted: 03/21/2011] [Indexed: 11/16/2022]
Abstract
Muscle fatigue is an established area of research and various types of muscle fatigue have been investigated in order to fully understand the condition. This paper gives an overview of the various non-invasive techniques available for use in automated fatigue detection, such as mechanomyography, electromyography, near-infrared spectroscopy and ultrasound for both isometric and non-isometric contractions. Various signal analysis methods are compared by illustrating their applicability in real-time settings. This paper will be of interest to researchers who wish to select the most appropriate methodology for research on muscle fatigue detection or prediction, or for the development of devices that can be used in, e.g., sports scenarios to improve performance or prevent injury. To date, research on localised muscle fatigue focuses mainly on the clinical side. There is very little research carried out on the implementation of detecting/predicting fatigue using an autonomous system, although recent research on automating the process of localised muscle fatigue detection/prediction shows promising results.
Collapse
Affiliation(s)
- Mohamed R. Al-Mulla
- School of Computer Science and Electronic Engineering, University of Essex, Colchester, UK; E-Mails: (F.S.); (M.C.)
| | - Francisco Sepulveda
- School of Computer Science and Electronic Engineering, University of Essex, Colchester, UK; E-Mails: (F.S.); (M.C.)
| | - Martin Colley
- School of Computer Science and Electronic Engineering, University of Essex, Colchester, UK; E-Mails: (F.S.); (M.C.)
| |
Collapse
|
10
|
Nishihara K, Chiba Y, Suzuki Y, Moriyama H, Kanemura N, Ito T, Takayanagi K, Gomi T. Effect of position of electrodes relative to the innervation zone onsurface EMG. J Med Eng Technol 2010; 34:141-7. [PMID: 20059306 DOI: 10.3109/03091900903480754] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/11/2023]
Abstract
We investigated the effect of the position of electrodes relative to the innervation zone (IZ) of the biceps brachii muscle during isometric elbow flexion using eight-channel surface array electrodes. We estimated the location of the IZ near the centre of the muscle in 20 male subjects. The pulse peaks from electromyogram (EMG) waveforms were detected for each channel and averaged, the triphasic pulse was determined, and the peak values of the first and third phases were compared. The results showed significantly greater pulse values for the first phase when the electrode placement was proximal to the estimated IZ, and for the third phase when the electrode placement was distal to the estimated IZ. Using this method, the positional relationship between electrodes and IZ can be determined using a surface EMG waveform recorded with a pair of bipolar electrodes. This method may be clinically useful in confirming the reliability of a recorded surface EMG.
Collapse
Affiliation(s)
- K Nishihara
- Department of Physical Therapy, Saitama Prefectural University, 820 Sannomiya, Koshigaya, Saitama, 343-8540, Japan.
| | | | | | | | | | | | | | | |
Collapse
|
11
|
Innervation zone location of the biceps brachii, a comparison between genders and correlation with anthropometric measurements. J Electromyogr Kinesiol 2010; 20:76-80. [DOI: 10.1016/j.jelekin.2008.09.009] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2008] [Revised: 09/12/2008] [Accepted: 09/15/2008] [Indexed: 11/23/2022] Open
|
12
|
An examination of innervation zone movement with increases in isometric torque production. Clin Neurophysiol 2008; 119:2795-9. [PMID: 18996046 DOI: 10.1016/j.clinph.2008.09.021] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2008] [Revised: 09/12/2008] [Accepted: 09/20/2008] [Indexed: 11/22/2022]
Abstract
OBJECTIVE To determine, with more precision than in previous investigations, if the innervation zone (IZ) for the biceps brachii can move with increases in isometric torque, and if so, whether or not that movement is influenced by differences in joint angle. METHODS Twenty-three participants (mean age=21.7 years) performed isometric contractions of the forearm flexors at 20, 40, 60, 80, and 100% of their maximal voluntary contraction (MVC) at three separate elbow joint angles (90, 120, and 150 degrees ). During each contraction, 16 channels of bipolar surface electromyographic (EMG) signals were recorded from the biceps brachii using a linear electrode array. For each joint angle, movement of the IZ with increases in torque was identified by a change in the EMG channel that was over the IZ. RESULTS For each joint angle, the IZ shifted proximally (2.3 channels) with increases in torque from 20 to 100% MVC. With an interelectrode distance of 2.5mm, this 2.3-channel shift reflects a 4.5-7.0mm movement of the IZ. CONCLUSION The IZ shifts proximally 4.5-7.0mm with increases in isometric torque, independent of joint angle. SIGNIFICANCE These findings suggested that if isometric contractions are performed at different torque levels, the electrodes should be placed at least 7mm from the IZ.
Collapse
|