Raw Electromyography Signals Research Articles

Analyzing the Impact of Accumulated Training Shots on Electromyography Parameters in Trained Archery Athletes: Exploring Fatigue and Its Association with Training Practices

Background: Accumulated training shots throughout a session may induce changes in electromyography (EMG) parameters of the primary muscles involved in movement in archery athletes. Thus, the aim of this study was two-fold: (i) analyze the impact of 50 and 100 archery shots on a single session on the EMG parameters of trained archery athletes; and (ii) explore the effects of training routines of the athletes to cope with fatigue induced by the accumulated shots on the EMG parameters. Methods: They were divided into two groups: those who regularly performed ≤100 shots per training session (n = 13) and those who performed >100 shots per session (n = 7). The participants were exposed to a condition involving 100 archery shots, with measurements taken at baseline, after 50, and after 100 shots. EMG was used to measure the electric potential of the deltoid (middle and posterior), trapezius (upper, middle, and lower), and infraspinatus during isometric contraction. The collected outcomes included the mean and maximal amplitude of EMG root mean square (EMGRMS, µV) and the median frequency of the raw surface EMG signal power spectrum (EMGMED, Hz). Results: The results showed significant differences for most of the analyzed muscles analyzed, specifically in the deltoid, infraspinatus, and trapezius (p < 0.05). Conclusions: Our study suggests that in most of the muscles analyzed, EMG parameters—particularly mean and maximal EMGRMS—tend to increase from baseline to 50 shots, with significant declines observed after 100 shots, indicating muscle fatigue. The training routines of the athletes do not appear to significantly influence their response to fatigue conditions.

The comparison and processing of Electromyography (EMG) signals under different actions

The experiment first investigates the working principle and the applications of Electromyography (EMG). Then, the effect of electrode location and electrode size on the EMG signal is explored by the raw data and theory. The reasons for choosing generic surface Ag/AgCl adhesive electrodes are also described. After obtaining the raw EMG signals, suitable data processing methods, such as Root Mean Square (RMS) and digital filtering are applied to generate signals that can drive the motor of a prosthetic arm. The results obtained by the two methods are also compared, where RMS can provide larger peak and mean values, and the digital filtering method can minimise the phase shift. Finally, the limitations of the EMG for prostheses are also analysed by three aspects: different flexion forces, individual finger motion and different reference locations.

Feature extraction and classification of different hand movements from the emg signal using linear discriminant analysis classifier

In biomedical research, Electromyography (EMG) data play a crucial role as a bridge between human motions and machine interpretation, offering valuable insights into muscle activation. EMG signals give vital information on hand movements in the context of applications like gesture recognition, prosthetic control, and rehabilitation. This paper describes the classification of EMG signals based on muscle motions, which makes it simpler to identify distinct gestures or movements. A Linear Discriminant Analysis (LDA) classifier is used to differentiate between various classes of muscle activity. In order to record EMG signals during hand motions, surface electrodes are carefully positioned on pertinent muscles. Muscle activity may be tracked in real time with these non-invasive electrodes. In order to extract meaningful information from these signals, which are complex and frequently contaminated by noise, strong feature extraction techniques are needed. When working with noisy signals, denoising is a commonly used approach to restoring the original quality of the source data. It attempts to maintain relevant information by reducing noise in the raw EMG signals. In order to retrieve only the pertinent information from the original EMG signal data, any unnecessary noise must first be removed. Through the identification of key characteristics in the time, frequency, and time-frequency domains, it transforms unstructured EMG data. This procedure improves the next step of classification, which is the identification and classification of patterns in the EMG signals. Ultimately, the obtained information is employed to classify signals by the Linear Discriminant Analysis (LDA) classifier, demonstrating a distinction between various muscle motions with over 80% accuracy.

An Ensemble of Long Short-Term Memory Networks with an Attention Mechanism for Upper Limb Electromyography Signal Classification

Advancing cutting-edge techniques to accurately classify electromyography (EMG) signals are of paramount importance given their extensive implications and uses. While recent studies in the literature present promising findings, a significant potential still exists for substantial enhancement. Motivated by this need, our current paper introduces a novel ensemble neural network approach for time series classification, specifically focusing on the classification of upper limb EMG signals. Our proposed technique integrates long short-term memory networks (LSTM) and attention mechanisms, leveraging their capabilities to achieve accurate classification. We provide a thorough explanation of the architecture and methodology, considering the unique characteristics and challenges posed by EMG signals. Furthermore, we outline the preprocessing steps employed to transform raw EMG signals into a suitable format for classification. To evaluate the effectiveness of our proposed technique, we compare its performance with a baseline LSTM classifier. The obtained numerical results demonstrate the superiority of our method. Remarkably, the method we propose attains an average accuracy of 91.5%, with all motion classifications surpassing the 90% threshold.

Classification of Kinematic and Electromyographic Signals Associated with Pathological Tremor Using Machine and Deep Learning.

Peripheral Electrical Stimulation (PES) of afferent pathways has received increased interest as a solution to reduce pathological tremors with minimal side effects. Closed-loop PES systems might present some advantages in reducing tremors, but further developments are required in order to reliably detect pathological tremors to accurately enable the stimulation only if a tremor is present. This study explores different machine learning (K-Nearest Neighbors, Random Forest and Support Vector Machines) and deep learning (Long Short-Term Memory neural networks) models in order to provide a binary (Tremor; No Tremor) classification of kinematic (angle displacement) and electromyography (EMG) signals recorded from patients diagnosed with essential tremors and healthy subjects. Three types of signal sequences without any feature extraction were used as inputs for the classifiers: kinematics (wrist flexion-extension angle), raw EMG and EMG envelopes from wrist flexor and extensor muscles. All the models showed high classification scores (Tremor vs. No Tremor) for the different input data modalities, ranging from 0.8 to 0.99 for the f1 score. The LSTM models achieved 0.98 f1 scores for the classification of raw EMG signals, showing high potential to detect tremors without any processed features or preliminary information. These models may be explored in real-time closed-loop PES strategies to detect tremors and enable stimulation with minimal signal processing steps.

Surface electromyography changes of male athletes during 2000 m rowing ergometer test

This study aimed to investigate the changes in surface electromyography (EMG) in four anatomical segments of three muscles during a 2000 m rowing ergometer test. 19 healthy male rowers were requested to perform the test. Surface electrodes were attached to their vast medialis (VAM), erector spinae (ERS) and latissimus dorsi (LD) muscles. Raw EMG signals were presented at five different distance points: start (D0), 500 m (D1), 1000 m (D2), 1500 m (D3) and 2000 m (D4). The mean velocity and power were greater during 0–500 m and 1500–2000 m phases compared to 500–1000 m and 1000–1500 m phases (p < 0.01). Integrated Electromyography (iEMG) of VAM was significantly higher at the start and 2000 m compared to consecutive points (p < 0.05). The peak root mean square (pRMS) of ERS muscles was significantly higher at the start and 2000 m (p < 0.05). The frequency domain indexes mean frequency (MNF) and median frequency (MDF) of all muscles were significantly reduced at 1500 m compared to 1000 m (p < 0.05). However, no significant changes were observed in time domain indexes of LD muscles at any distance points (p > 0.05). A “fast start-speed maintains-final sprint” pacing pattern was observed during the 2000 m all-out rowing ergometer test. The EMG activation rates of VAM and ERS muscles were greater at the start and final phases, contributing to the increase in power. The decline in MNF and MDF of all three muscles at 1500 m could be related to greater muscle fatigue at this point. When using EMG to analyze endurance exercise, the results were dependent on the length of the test. Although not all EMG indexes were sensitive enough to detect these changes, combing them with different indicators for a comprehensive analysis might be considered.

Electromyography-Based, Robust Hand Motion Classification Employing Temporal Multi-Channel Vision Transformers

With an increasing use of robotic and bionic devices for the execution of everyday life, complex tasks, Electromyography (EMG) based interfaces are being explored as candidate technologies for facilitating an intuitive interaction with such devices. However, EMG-based interfaces typically require appropriate features to be extracted from the raw EMG signals using a plethora of feature extraction methods to achieve excellent performance in practical applications. To select an appropriate feature set that will lead to significant EMG-based decoding performance, a deep understanding of available methods and the human musculoskeletal system is needed. To overcome this issue, researchers have proposed the use of deep learning methods for automatically extracting complex features directly from the raw EMG data. In this work, we propose Temporal Multi-Channel Vision Transformers as a deep learning technique that has the potential to achieve dexterous control of robots and bionic hands. The performance of this method is evaluated and compared with other well-known methods, employing the open-access Ninapro dataset.

A pilot study of the Earable device to measure facial muscle and eye movement tasks among healthy volunteers.

The Earable device is a behind-the-ear wearable originally developed to measure cognitive function. Since Earable measures electroencephalography (EEG), electromyography (EMG), and electrooculography (EOG), it may also have the potential to objectively quantify facial muscle and eye movement activities relevant in the assessment of neuromuscular disorders. As an initial step to developing a digital assessment in neuromuscular disorders, a pilot study was conducted to determine whether the Earable device could be utilized to objectively measure facial muscle and eye movements intended to be representative of Performance Outcome Assessments, (PerfOs) with tasks designed to model clinical PerfOs, referred to as mock-PerfO activities. The specific aims of this study were: To determine whether the Earable raw EMG, EOG, and EEG signals could be processed to extract features describing these waveforms; To determine Earable feature data quality, test re-test reliability, and statistical properties; To determine whether features derived from Earable could be used to determine the difference between various facial muscle and eye movement activities; and, To determine what features and feature types are important for mock-PerfO activity level classification. A total of N = 10 healthy volunteers participated in the study. Each study participant performed 16 mock-PerfOs activities, including talking, chewing, swallowing, eye closure, gazing in different directions, puffing cheeks, chewing an apple, and making various facial expressions. Each activity was repeated four times in the morning and four times at night. A total of 161 summary features were extracted from the EEG, EMG, and EOG bio-sensor data. Feature vectors were used as input to machine learning models to classify the mock-PerfO activities, and model performance was evaluated on a held-out test set. Additionally, a convolutional neural network (CNN) was used to classify low-level representations of the raw bio-sensor data for each task, and model performance was correspondingly evaluated and compared directly to feature classification performance. The model's prediction accuracy on the Earable device's classification ability was quantitatively assessed. Study results indicate that Earable can potentially quantify different aspects of facial and eye movements and may be used to differentiate mock-PerfO activities. Specially, Earable was found to differentiate talking, chewing, and swallowing tasks from other tasks with observed F1 scores >0.9. While EMG features contribute to classification accuracy for all tasks, EOG features are important for classifying gaze tasks. Finally, we found that analysis with summary features outperformed a CNN for activity classification. We believe Earable may be used to measure cranial muscle activity relevant for neuromuscular disorder assessment. Classification performance of mock-PerfO activities with summary features enables a strategy for detecting disease-specific signals relative to controls, as well as the monitoring of intra-subject treatment responses. Further testing is needed to evaluate the Earable device in clinical populations and clinical development settings.

Machine Learning-Based Diabetic Neuropathy and Previous Foot Ulceration Patients Detection Using Electromyography and Ground Reaction Forces during Gait.

Diabetic neuropathy (DN) is one of the prevalent forms of neuropathy that involves alterations in biomechanical changes in the human gait. Diabetic foot ulceration (DFU) is one of the pervasive types of complications that arise due to DN. In the literature, for the last 50 years, researchers have been trying to observe the biomechanical changes due to DN and DFU by studying muscle electromyography (EMG) and ground reaction forces (GRF). However, the literature is contradictory. In such a scenario, we propose using Machine learning techniques to identify DN and DFU patients by using EMG and GRF data. We collected a dataset from the literature which involves three patient groups: Control (n = 6), DN (n = 6), and previous history of DFU (n = 9) and collected three lower limb muscles EMG (tibialis anterior (TA), vastus lateralis (VL), gastrocnemius lateralis (GL)), and three GRF components (GRFx, GRFy, and GRFz). Raw EMG and GRF signals were preprocessed, and different feature extraction techniques were applied to extract the best features from the signals. The extracted feature list was ranked using four different feature ranking techniques, and highly correlated features were removed. In this study, we considered different combinations of muscles and GRF components to find the best performing feature list for the identification of DN and DFU. We trained eight different conventional ML models: Discriminant analysis classifier (DAC), Ensemble classification model (ECM), Kernel classification model (KCM), k-nearest neighbor model (KNN), Linear classification model (LCM), Naive Bayes classifier (NBC), Support vector machine classifier (SVM), and Binary decision classification tree (BDC), to find the best-performing algorithm and optimized that model. We trained the optimized the ML algorithm for different combinations of muscles and GRF component features, and the performance matrix was evaluated. Our study found the KNN algorithm performed well in identifying DN and DFU, and we optimized it before training. We found the best accuracy of 96.18% for EMG analysis using the top 22 features from the chi-square feature ranking technique for features from GL and VL muscles combined. In the GRF analysis, the model showed 98.68% accuracy using the top 7 features from the Feature selection using neighborhood component analysis for the feature combinations from the GRFx-GRFz signal. In conclusion, our study has shown a potential solution for ML application in DN and DFU patient identification using EMG and GRF parameters. With careful signal preprocessing with strategic feature extraction from the biomechanical parameters, optimization of the ML model can provide a potential solution in the diagnosis and stratification of DN and DFU patients from the EMG and GRF signals.

Classification of Parkinson’s Disease Using EMG Signals from Different Upper Limb Movements Based on Multiclass Support Vector Machine

Parkinson’s disease (PD) is the second most common neurodegenerative disease that affects a wide range of productive individuals worldwide. The common approach to diagnose PD is through clinical assessment of the patient, which is highly subjective and time consuming. Electromyography (EMG) can be taken as a cheap way of PD diagnosis. However, highly experienced experts are required to interpret the signals. The manual procedures are complex, time-consuming, and prone to error resulting in misdiagnosis. In this research, an automatic system for detection and classification of PD stages using EMG signals acquired from different upper limb movements is proposed. In addition, effective upper limb movement for the identification of PD has been investigated. The data required for training and testing the system was collected from flexor carpi radialis and biceps brachii muscles of 15 PD patients and 10 healthy control subjects at Jimma University Medical Center. The raw EMG signal was preprocessed and frequency and time-domain features were extracted. A multiclass support vector machine model was then trained for four-class classification (normal, early, moderate, and advanced PD levels). The performance of the system was evaluated using different performance evaluators and a promising result has been obtained. 90%, 91.7%, 95%, and 96.6% overall classification accuracies were obtained for elbow flexion by 90-degrees without load, elbow flexion by 90-degrees with load, touching the shoulder, and wrist pronation, respectively. A user-friendly interface has been also developed for ease of use of the automatic PD classification system.

A Review on EMG Signal Classification and Applications

Electromyography (EMG) signals are muscles signals that enable the identification of human movements without the need of complex human kinematics calculations. Researchers prefer EMG signals as input signals to control prosthetic arms and exoskeleton robots. However, the proper algorithm to classify human movements from raw EMG signals has been an interesting and challenging topic to researchers. Various studies have been carried out to produce EMG-based human movement classification that gives high accuracy and high reliability. In this paper, the methods used in EMG signal acquisition and processing are reviewed. The different types of feature extraction techniques preferred by researchers are also discussed, including some combination and comparison of feature extraction techniques. This paper also reviews the different types of classifiers favored by researchers to recognize human movements based on EMG signals. The current applications of EMG signals are also reviewed.

Neuromuscular Adjustments of the Quadriceps Muscle After Eccentric Resistance and Concentric Resistance Training

Introduction: Deficiency in the neural control of movement is associated with poor posture and skeletal muscle injuries. Exercise training is commonly reported as an intervention to improve neuromuscular activity. However, maximizing the effectiveness of exercise interventions for improving neural control of movement has been less investigated. The purpose of the current study was to examine improvement in neuromuscular activity (e.g., muscle fiber conduction velocity) and quadriceps function after eccentric resistance training versus concentric training. Materials and Methods: A total of 24 men participated in this study and were randomly divided into eccentric training (n=12) and concentric training groups (n=12). Maximal voluntary isometric contraction (MIVC) of quadriceps, vertical jumping, and multichannel surface electromyography (EMG) signals were recorded before and 12 weeks after resistance eccentric and concentric training. Muscle fiber conduction velocity (MFCV) and root mean square (RMS) were computed using raw EMG signals. Results: The percentage increases in MVIC and vertical jumping after eccentric resistance training were significantly higher than those after concentric training (P<0.05). Likewise, eccentric exercise resulted in a higher increase in MFCV and RMS of EMG than concentric exercise (P<0.05). Conclusion: A higher increase in neuromuscular activity and quadriceps performance observed after eccentric exercise may indicate that eccentric resistance training is more effective in improving neuromuscular activity and muscle function.

Hardware Implementation for Lower Limb Surface EMG Measurement and Analysis Using Explainable AI for Activity Recognition

Electromyography (EMG) signals are gaining popularity for several biomedical applications, including pattern recognition, disease detection, human-machine interfaces, medical image processing, and robotic limb or exoskeleton fabrication. In this study, a two-channel data acquisition system for measuring EMG signals is proposed for human lower limb activity recognition. Five leg activities have been accomplished to measure EMG signals from two lower limb muscles to validate the developed hardware. Five subjects (3 males and 2 females) were chosen to acquire EMG signals during these activities. The raw EMG signal was first denoised using a hybrid of Wavelet Decomposition with Ensemble Empirical Mode Decomposition (WD-EEMD) approach to classify the recorded EMG dataset. Then, eight time-domain features were extracted using the overlapping windowing technique. An investigation into the comparative effectiveness of several classifiers is presented, although it was hard to distinguish how the classifiers predicted the activities. Having a trustworthy explanation for the outcomes of these classifiers would be quite beneficial overall. An approach known as Explainable Artificial Intelligence (XAI) was introduced to produce trustworthy predictive modelling results and applied the XAI technique known as Local Interpretable Model-Agnostic Explanations (LIME) to a straightforward human interpretation. LIME investigates how extracted features are anticipated and which features are most responsible for each action. The accuracy of the Extra Tree Classifier gives the highest accuracy of the other studied algorithms for identifying different human lower limb activities from sEMG signals.

Reliability Analysis for Finger Movement Recognition With Raw Electromyographic Signal by Evidential Convolutional Networks.

Hand gesture recognition with surface electromyography (sEMG) is indispensable for Muscle-Gesture-Computer Interface. The usual focus of it is upon performance evaluation involving the accuracy and robustness of hand gesture recognition. However, addressing the reliability of such classifiers has been absent, to our best knowledge. This may be due to the lack of consensus on the definition of model reliability in this field. An uncertainty-aware model has the potential to self-evaluate the quality of its inference, thereby making it more reliable. Moreover, uncertainty-based rejection has been shown to improve the performance of sEMG-based hand gesture recognition. Therefore, we first define model reliability here as the quality of its uncertainty estimation and propose an offline framework to quantify it. To promote reliability analysis, we propose a novel end-to-end uncertainty-aware finger movement classifier, i.e., evidential convolutional neural network (ECNN), and illustrate the advantages of its multidimensional uncertainties such as vacuity and dissonance. Extensive comparisons of accuracy and reliability are conducted on NinaPro Database 5, exercise A, across CNN and three variants of ECNN based on different training strategies. The results of classifying 12 finger movements over 10 subjects show that the best mean accuracy achieved by ECNN is 76.34%, which is slightly higher than the state-of-the-art performance. Furthermore, ECNN variants are more reliable than CNN in general, where the highest improvement of reliability of 19.33% is observed. This work demonstrates the potential of ECNN and recommends using the proposed reliability analysis as a supplementary measure for studying sEMG-based hand gesture recognition.

Differences in Muscle Fatigability of Vastus Medialis between Sexes Using Surface Electromyographic Power Spectral Analysis in Healthy Adults.

ABSTRACTObjectives:With a relatively high percentage of type I fibers in the vastus medialis (VM), its fatigability may be more sensitive to the effects of muscle activity in the quadriceps. However, sex-related differences in the muscle fatigability of the VM remain unknown. The purpose of the present study was to assess the differences in fatigability of the VM between healthy adult men and women.Methods:Surface electromyographic (EMG) activities of VM oblique (VMO) and VM long (VML) were recorded during sustained isometric contraction on a leg press machine. The results of EMG power spectral analysis were compared between healthy adult men and women. The decline in the median frequency (MF), defined as MF slope, was calculated using spectrum analysis after fast Fourier transform of the raw EMG signals of VMO and VML.Results:The endurance time and the MF slopes of the VMO and VML were significantly longer and lower, respectively, in women than in men. The present results demonstrated that both VMO and VML are more fatigue-resistant in women than in men.Conclusions:Understanding the sex differences in fatigability could help to design more effective exercise regimens for VMO and VML in healthy individuals. A similar approach should be considered when prescribing practical exercise regimens for patients with muscle atrophy.

Electromyography Based Decoding of Dexterous, In-Hand Manipulation Motions With Temporal Multichannel Vision Transformers.

Electromyography (EMG) signals have been used in designing muscle-machine interfaces (MuMIs) for various applications, ranging from entertainment (EMG controlled games) to human assistance and human augmentation (EMG controlled prostheses and exoskeletons). For this, classical machine learning methods such as Random Forest (RF) models have been used to decode EMG signals. However, these methods depend on several stages of signal pre-processing and extraction of hand-crafted features so as to obtain the desired output. In this work, we propose EMG based frameworks for the decoding of object motions in the execution of dexterous, in-hand manipulation tasks using raw EMG signals input and two novel deep learning (DL) techniques called Temporal Multi-Channel Transformers and Vision Transformers. The results obtained are compared, in terms of accuracy and speed of decoding the motion, with RF-based models and Convolutional Neural Networks as a benchmark. The models are trained for 11 subjects in a motion-object specific and motion-object generic way, using the 10-fold cross-validation procedure. This study shows that the performance of MuMIs can be improved by employing DL-based models with raw myoelectric activations instead of developing DL or classic machine learning models with hand-crafted features.

Comparing Machine Learning Methods and Feature Extraction Techniques for the EMG Based Decoding of Human Intention.

With an increasing number of robotic and prosthetic devices, there is a need for intuitive Muscle-Machine Interfaces (MuMIs) that allow the user to have an embodied interaction with the devices they are controlling. Such MuMIs can be developed using machine learning based methods that utilize myoelectric activations from the muscles of the user to decode their intention. However, the choice of the learning method is subjective and depends on the features extracted from the raw Electromyography signals as well as on the intended application. In this work, we compare the performance of five machine learning methods and eight time-domain feature extraction techniques in discriminating between different gestures executed by the user of an EMG based MuMI. From the results, it can be seen that the Willison Amplitude performs consistently better for all the machine learning methods compared in this study, while the Zero Crossings achieves the worst results for the Decision Trees and the Random Forests and the Variance offers the worst performance for all the other learning methods. The Random Forests method is shown to achieve the best results in terms of achieved accuracies (has the lowest variance between subjects). In order to experimentally validate the efficiency of the Random Forest classifier and the Willison Amplitude technique, a series of gestures were decoded in a real-time manner from the myoelectric activations of the operator and they were used to control a robot hand.

Electromyography Signal Analysis and Classification using Time-Frequency Representations and Deep Learning.

Analysis and classification of electromyography (EMG) signals are crucial for rehabilitation and motor control. This study investigates electromyogram (EMG) time-frequency representations and then creates conventional and deep learning models for EMG signal classification. Firstly, a dataset of single-channel surface EMG signals has been recorded for four subjects to differentiate between forearm flexion and extension. Then, different time-frequency EMG representations have been used to build conventional and deep learning models for EMG classification. We compared the performance of pre-trained convolutional neural network models, namely GoogLeNet, SqueezeNet and AlexNet, and achieved accuracies of 92.71%, 90.63% and 87.5%, respectively. Also, data augmentation techniques on the levels of raw EMG signals and their time- frequency representations helped improve the accuracy of GoogLeNet to 96.88%. Furthermore, our approach demonstrated superior performance on another publicly available 10-class EMG dataset, and also using traditional classifiers trained on hand-crafted features.

Musculoskeletal Neural Network path generator for a virtual upper-limb active controlled orthosis.

In this paper, a non-parametric model of the neuromusculoskeletal system for the biceps brachii is presented. The model serves to generate angular paths for the control of a virtual active orthosis. The path generator uses a differential neural network (DNN) identifier that obtains the reference angular position and velocities using the raw electromyographic (EMG) signals as input. The model is validated using experimental data. The training and closed-loop implementation of the proposed model are described. The control strategy ensures that the user reaches a set-point with a predefined position constraint and that the device follows the natural reference path that corresponds to the raw EMG signal.

Differences in fatigability of vastus medialis muscle between patients with limb symmetry index of

BackgroundA limb symmetry index (LSI) of ≥90% for the quadriceps is recommended for return to sports activity after anterior cruciate ligament reconstruction (ACLR). However, there is no information on differences in muscle fatigability between patients with LSI of <90% and ≥90%. The aim of this study was to assess the difference in quadriceps muscle fatigability on the involved side between post-ACLR patients with LSI of <90% and ≥90%. We hypothesized that there were differences between the two groups in muscle fatigability on the involved side reflecting difference in muscle fiber composition in the vastus medialis (VM) muscle. MethodsThe study subjects were 18 adult men who had undergone ACLR followed by rehabilitation therapy. LSI was <90% in 10 and ≥90% in 8 adult men. Surface electromyography (EMG) of the VM muscle was recorded during sustained quadriceps muscle isometric contraction. The median frequency (MF) was computed from the raw EMG signal using fast Fourier transform spectrum analysis. The MF slope was also calculated. ResultsThere were no differences in anthropometric characteristics, time since ACLR, anterior tibial translation and peak torque of knee extension on the involved side between the two groups. However, MF slope was significantly lower in the LSI ≥ 90% group than the <90% group. ConclusionOur results demonstrated fatigue-resistant vastus medialis in post-ACLR patients with LSI ≥90% compared to those with LSI <90%. The finding adds support to the use of ≥90% as the cutoff value for LSI for return of post-ACLR patients to sports activity.