Machine learning-empowered sleep staging classification using multi-modality signals.

The goal is to enhance an automated sleep staging system's performance by leveraging the diverse signals captured through multi-modal polysomnography recordings. Three modalities of PSG signals, namely electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG), were considered to obtain the optimal fusions of the PSG signals, where 63 features were extracted. These include frequency-based, time-based, statistical-based, entropy-based, and non-linear-based features. We adopted the ReliefF (ReF) feature selection algorithms to find the suitable parts for each signal and superposition of PSG signals. Twelve top features were selected while correlated with the extracted feature sets' sleep stages. The selected features were fed into the AdaBoost with Random Forest (ADB + RF) classifier to validate the chosen segments and classify the sleep stages. This study's experiments were investigated by obtaining two testing schemes: epoch-wise testing and subject-wise testing. The suggested research was conducted using three publicly available datasets: ISRUC-Sleep subgroup1 (ISRUC-SG1), sleep-EDF(S-EDF), Physio bank CAP sleep database (PB-CAPSDB), and S-EDF-78 respectively. This work demonstrated that the proposed fusion strategy overestimates the common individual usage of PSG signals.

Combining enhanced spectral resolution of EMG and a deep learning approach for knee pathology diagnosis.

Knee osteoarthritis (OA) is a prevalent, debilitating joint condition primarily affecting the elderly. This investigation aims to develop an electromyography (EMG)-based method for diagnosing knee pathologies. EMG signals of the muscles surrounding the knee joint were examined and recorded. The principal components of the proposed method were preprocessing, high-order spectral analysis (HOSA), and diagnosis/recognition through deep learning. EMG signals from individuals with normal and OA knees while walking were extracted from a publicly available database. This examination focused on the quadriceps femoris, the medial gastrocnemius, the rectus femoris, the semitendinosus, and the vastus medialis. Filtration and rectification were utilized beforehand to eradicate noise and smooth EMG signals. Signals' higher-order spectra were analyzed with HOSA to obtain information about nonlinear interactions and phase coupling. Initially, the bicoherence representation of EMG signals was devised. The resulting images were fed into a deep-learning system for identification and analysis. A deep learning algorithm using adapted ResNet101 CNN model examined the images to determine whether the EMG signals were conventional or indicative of knee osteoarthritis. The validated test results demonstrated high accuracy and robust metrics, indicating that the proposed method is effective. The medial gastrocnemius (MG) muscle was able to distinguish Knee osteoarthritis (KOA) patients from normal with 96.3±1.7% accuracy and 0.994±0.008 AUC. MG has the highest prediction accuracy of KOA and can be used as the muscle of interest in future analysis. Despite the proposed method's superiority, some limitations still require special consideration and will be addressed in future research.

Study on Gesture Recognition Method with Two-Stream Residual Network Fusing sEMG Signals and Acceleration Signals.

Currently, surface EMG signals have a wide range of applications in human-computer interaction systems. However, selecting features for gesture recognition models based on traditional machine learning can be challenging and may not yield satisfactory results. Considering the strong nonlinear generalization ability of neural networks, this paper proposes a two-stream residual network model with an attention mechanism for gesture recognition. One branch processes surface EMG signals, while the other processes hand acceleration signals. Segmented networks are utilized to fully extract the physiological and kinematic features of the hand. To enhance the model's capacity to learn crucial information, we introduce an attention mechanism after global average pooling. This mechanism strengthens relevant features and weakens irrelevant ones. Finally, the deep features obtained from the two branches of learning are fused to further improve the accuracy of multi-gesture recognition. The experiments conducted on the NinaPro DB2 public dataset resulted in a recognition accuracy of 88.25% for 49 gestures. This demonstrates that our network model can effectively capture gesture features, enhancing accuracy and robustness across various gestures. This approach to multi-source information fusion is expected to provide more accurate and real-time commands for exoskeleton robots and myoelectric prosthetic control systems, thereby enhancing the user experience and the naturalness of robot operation.

Measuring Surface Electromyography with Textile Electrodes in a Smart Leg Sleeve.

This paper presents the design, development, and validation of a novel e-textile leg sleeve for non-invasive Surface Electromyography (sEMG) monitoring. This wearable device incorporates e-textile sensors for sEMG signal acquisition from the lower limb muscles, specifically the anterior tibialis and lateral gastrocnemius. Validation was conducted by performing a comparative study with eleven healthy volunteers to evaluate the performance of the e-textile sleeve in acquiring sEMG signals compared to traditional Ag/AgCl electrodes. The results demonstrated strong agreement between the e-textile and conventional methods in measuring descriptive metrics of the signals, including area, power, mean, and root mean square. The paired data t-test did not reveal any statistically significant differences, and the Bland-Altman analysis indicated negligible bias between the measures recorded using the two methods. In addition, this study evaluated the wearability and comfort of the e-textile sleeve using the Comfort Rating Scale (CRS). Overall, the scores confirmed that the proposed device is highly wearable and comfortable, highlighting its suitability for everyday use in patient care.

Developing a Novel Prosthetic Hand with Wireless Wearable Sensor Technology Based on User Perspectives: A Pilot Study.

Myoelectric hands are beneficial tools in the daily activities of people with upper-limb deficiencies. Because traditional myoelectric hands rely on detecting muscle activity in residual limbs, they are not suitable for individuals with short stumps or paralyzed limbs. Therefore, we developed a novel electric prosthetic hand that functions without myoelectricity, utilizing wearable wireless sensor technology for control. As a preliminary evaluation, our prototype hand with wireless button sensors was compared with a conventional myoelectric hand (Ottobock). Ten healthy therapists were enrolled in this study. The hands were fixed to their forearms, myoelectric hand muscle activity sensors were attached to the wrist extensor and flexor muscles, and wireless button sensors for the prostheses were attached to each user's trunk. Clinical evaluations were performed using the Simple Test for Evaluating Hand Function and the Action Research Arm Test. The fatigue degree was evaluated using the modified Borg scale before and after the tests. While no statistically significant differences were observed between the two hands across the tests, the change in the Borg scale was notably smaller for our prosthetic hand (p = 0.045). Compared with the Ottobock hand, the proposed hand prosthesis has potential for widespread applications in people with upper-limb deficiencies.

Rectified Latent Variable Model-Based EMG Factorization of Inhibitory Muscle Synergy Components Related to Aging, Expertise and Force-Tempo Variations.

Muscle synergy has been widely acknowledged as a possible strategy of neuromotor control, but current research has ignored the potential inhibitory components in muscle synergies. Our study aims to identify and characterize the inhibitory components within motor modules derived from electromyography (EMG), investigate the impact of aging and motor expertise on these components, and better understand the nervous system's adaptions to varying task demands. We utilized a rectified latent variable model (RLVM) to factorize motor modules with inhibitory components from EMG signals recorded from ten expert pianists when they played scales and pieces at different tempo-force combinations. We found that older participants showed a higher proportion of inhibitory components compared with the younger group. Senior experts had a higher proportion of inhibitory components on the left hand, and most inhibitory components became less negative with increased tempo or decreased force. Our results demonstrated that the inhibitory components in muscle synergies could be shaped by aging and expertise, and also took part in motor control for adapting to different conditions in complex tasks.

Mapping Method of Human Arm Motion Based on Surface Electromyography Signals.

This paper investigates a method for precise mapping of human arm movements using sEMG signals. A multi-channel approach captures the sEMG signals, which, combined with the accurately calculated joint angles from an Inertial Measurement Unit, allows for action recognition and mapping through deep learning algorithms. Firstly, signal acquisition and processing were carried out, which involved acquiring data from various movements (hand gestures, single-degree-of-freedom joint movements, and continuous joint actions) and sensor placement. Then, interference signals were filtered out through filters, and the signals were preprocessed using normalization and moving averages to obtain sEMG signals with obvious features. Additionally, this paper constructs a hybrid network model, combining Convolutional Neural Networks and Artificial Neural Networks, and employs a multi-feature fusion algorithm to enhance the accuracy of gesture recognition. Furthermore, a nonlinear fitting between sEMG signals and joint angles was established based on a backpropagation neural network, incorporating momentum term and adaptive learning rate adjustments. Finally, based on the gesture recognition and joint angle prediction model, prosthetic arm control experiments were conducted, achieving highly accurate arm movement prediction and execution. This paper not only validates the potential application of sEMG signals in the precise control of robotic arms but also lays a solid foundation for the development of more intuitive and responsive prostheses and assistive devices.

Research on a Calculation Model of Ankle-Joint-Torque-Based sEMG.

The purpose of this article is to establish a prediction model of joint movements and realize the prediction of joint movemenst, and the research results are of reference value for the development of the rehabilitation equipment. This will be carried out by analyzing the impact of surface electromyography (sEMG) on ankle movements and using the Hill model as a framework for calculating ankle joint torque. The table and scheme used in the experiments were based on physiological parameters obtained through the model. Data analysis was performed on ankle joint angle signal, movement signal, and sEMG data from nine subjects during dorsiflexion/flexion, varus, and internal/external rotation. The Hill model was employed to determine 16 physiological parameters which were optimized using a genetic algorithm. Three experiments were carried out to identify the optimal model to calculate torque and root mean square error. The optimized model precisely calculated torque and had a root mean square error of under 1.4 in comparison to the measured torque. Ankle movement models predict torque patterns with accuracy, thereby providing a solid theoretical basis for ankle rehabilitation control. The optimized model provides a theoretical foundation for precise ankle torque forecasts, thereby improving the efficacy of rehabilitation robots for the ankle.

Context-informed incremental learning improves both the performance and resilience of myoelectric control.

Despite its rich history of success in controlling powered prostheses and emerging commercial interests in ubiquitous computing, myoelectric control continues to suffer from a lack of robustness. In particular, EMG-based systems often degrade over prolonged use resulting in tedious recalibration sessions, user frustration, and device abandonment. Unsupervised adaptation is one proposed solution that updates a model's parameters over time based on its own predictions during real-time use to maintain robustness without requiring additional user input or dedicated recalibration. However, these strategies can actually accelerate performance deterioration when they begin to classify (and thus adapt) incorrectly, defeating their own purpose. To overcome these limitations, we propose a novel adaptive learning strategy, Context-Informed Incremental Learning (CIIL), that leverages in situ context to better inform the prediction of pseudo-labels. In this work, we evaluate these CIIL strategies in an online target acquisition task for two use cases: (1) when there is a lack of training data and (2) when a drastic and enduring alteration in the input space has occurred. A total of 32 participants were evaluated across the two experiments. The results show that the CIIL strategies significantly outperform the current state-of-the-art unsupervised high-confidence adaptation and outperform models trained with the conventional screen-guided training approach, even after a 45-degree electrode shift (p < 0.05). Consequently, CIIL has substantial implications for the future of myoelectric control, potentially reducing the training burden while bolstering model robustness, and leading to improved real-time control.

Evaluation of functional interaction masseter and sternocleidomastoid muscles affected by TMJ dysfunction.

OBJECTIVE: Aim: To evaluate the functional connection and the bioelectrical state of the m.masseter and m. sternocleidomastoid using functional tests before and after treatment. PATIENTS AND METHODS: Materials and Methods: The sample consisted of 21 individuals with temporomandibular joint dysfunction. Examinations were carried out before and after treatment using repositioning splint therapy and in seated/standing positions. RESULTS: Results: M. masseter - p=0.072 before treatment and p=0.821 after treatment. Symmetry is also maintained after treatment. After treatment, a significant difference is noted at the level of significance p<0.001 for the right chewing muscle. In seated and standing positions before treatment did not reveal a statistically significant difference (p=0.07, p=0.143) and after (p=0.272, p=0.623).M. sternocleidomastoid- p<0.001 when comparing right and left sides. After treatment, there was no difference between the right and left sides (p=0.169). No statistical difference was found when assessing indicators separately for the right and left muscles in seated and standing positions (p=0.304, p=0.611, p=0.089, p=0.869). When comparing the bioelectric potentials of the right muscle before, after treatment, a statistically significant difference was found p=0.001. CONCLUSION: Conclusions: Biostatistical analysis of the indicators of bioelectrical activity of m. masseter and sternocleidomastoid indicates no changes in muscle microvolt indicators with changes in body position in patients. However, repositioning splint therapy is associated with reduced muscle tone in initially more spasmodic muscles. It is worth noting that the symmetry of interaction between muscles improves.

Highly stretchable and customizable microneedle electrode arrays for intramuscular electromyography.

Stretchable three-dimensional (3D) penetrating microelectrode arrays have potential utility in various fields, including neuroscience, tissue engineering, and wearable bioelectronics. These 3D microelectrode arrays can penetrate and conform to dynamically deforming tissues, thereby facilitating targeted sensing and stimulation of interior regions in a minimally invasive manner. However, fabricating custom stretchable 3D microelectrode arrays presents material integration and patterning challenges. In this study, we present the design, fabrication, and applications of stretchable microneedle electrode arrays (SMNEAs) for sensing local intramuscular electromyography signals ex vivo. We use a unique hybrid fabrication scheme based on laser micromachining, microfabrication, and transfer printing to enable scalable fabrication of individually addressable SMNEA with high device stretchability (60 to 90%). The electrode geometries and recording regions, impedance, array layout, and length distribution are highly customizable. We demonstrate the use of SMNEAs as bioelectronic interfaces in recording intramuscular electromyography from various muscle groups in the buccal mass of Aplysia.

The role of electrodiagnosis in focal neuropathies.

Electrodiagnostic (EDX) testing plays an important role in confirming a mononeuropathy, localizing the site of nerve injury, defining the pathophysiology, and assessing the severity and prognosis. The combination of nerve conduction studies (NCS) and needle electromyography findings provides the necessary information to fully assess a nerve. The pattern of NCS abnormalities reflects the underlying pathophysiology, with focal slowing or conduction block in neuropraxic injuries and reduced amplitudes in axonotmetic injuries. Needle electromyography findings, including spontaneous activity and voluntary motor unit potential changes, complement the NCS findings and further characterize chronicity and degree of axon loss and reinnervation. EDX is used as an objective marker to follow the progression of a mononeuropathy over time.

A comprehensive dataset on biomechanics and motor control during human walking with discrete mechanical perturbations.

Background: Humans have a remarkable capability to maintain balance while walking. There is, however, a lack of publicly available research data on reactive responses to destabilizing perturbations during gait. Methods: Here, we share a comprehensive dataset collected from 10 participants who experienced random perturbations while walking on an instrumented treadmill. Each participant performed six 5-min walking trials at a rate of 1.2 m/s, during which rapid belt speed perturbations could occur during the participant's stance phase. Each gait cycle had a 17% probability of being perturbed. The perturbations consisted of an increase of belt speed by 0.75 m/s, delivered with equal probability at 10%, 20%, 30%, 40%, 50%, 60%, 70%, or 80% of the stance phase. Data were recorded using motion capture with 25 markers, eight inertial measurement units (IMUs), and electromyography (EMG) from the tibialis anterior (TA), soleus (SOL), lateral gastrocnemius (LG), rectus femoris (RF), vastus lateralis (VL), vastus medialis (VM), biceps femoris (BF), and gluteus maximus (GM). The full protocol is described in detail. Results: We provide marker trajectories, force plate data, EMG data, and belt speed information for all trials and participants. IMU data is provided for most participants. This data can be useful for identifying neural feedback control in human gait, biologically inspired control systems for robots, and the development of clinical applications.

Preliminary Study on Effects of Neck Exoskeleton Structural Design in Patients With Amyotrophic Lateral Sclerosis.

Neck muscle weakness due to amyotrophic lateral sclerosis (ALS) can result in dropped head syndrome, adversely impacting the quality of life of those affected. Static neck collars are currently prescribed to hold the head in a fixed upright position. However, these braces are uncomfortable and do not allow any voluntary head-neck movements. By contrast, powered neck exoskeletons have the potential to enable head-neck movements. Our group has recently improved the mechanical structure of a state-of-the-art neck exoskeleton through a weighted optimization. To evaluate the effect of the structural changes, we conducted an experiment in which patients with ALS were asked to perform head-neck tracking tasks while using the two versions of the neck exoskeleton. We found that the neck muscle activation was significantly reduced when assisted by the structurally enhanced design compared to no assistance provided. The improved structure also improved kinematics tracking performance, allowing users to better achieve the desired head poses. In comparison, the previous design did not help reduce the muscle effort required to perform these tasks and even slightly worsened the kinematic tracking performance. It was also found that biomechanical benefits gained from using the structurally improved design were consistent across participants with both mild and severe neck weakness. Furthermore, we observed that participants preferred to use the powered neck exoskeletons to voluntarily move their heads and make eye contact during a conversation task rather than remain in a fixed upright position. Each of these findings highlights the importance of the structural design of neck exoskeletons in achieving desired biomechanical benefits and suggests that neck exoskeletons can be a viable method to improve the daily life of patients with ALS.

A multifaceted suite of metrics for comparative myoelectric prosthesis controller research.

Upper limb robotic (myoelectric) prostheses are technologically advanced, but challenging to use. In response, substantial research is being done to develop person-specific prosthesis controllers that can predict a user's intended movements. Most studies that test and compare new controllers rely on simple assessment measures such as task scores (e.g., number of objects moved across a barrier) or duration-based measures (e.g., overall task completion time). These assessment measures, however, fail to capture valuable details about: the quality of device arm movements; whether these movements match users' intentions; the timing of specific wrist and hand control functions; and users' opinions regarding overall device reliability and controller training requirements. In this work, we present a comprehensive and novel suite of myoelectric prosthesis control evaluation metrics that better facilitates analysis of device movement details-spanning measures of task performance, control characteristics, and user experience. As a case example of their use and research viability, we applied these metrics in real-time control experimentation. Here, eight participants without upper limb impairment compared device control offered by a deep learning-based controller (recurrent convolutional neural network-based classification with transfer learning, or RCNN-TL) to that of a commonly used controller (linear discriminant analysis, or LDA). The participants wore a simulated prosthesis and performed complex functional tasks across multiple limb positions. Analysis resulting from our suite of metrics identified 16 instances of a user-facing problem known as the "limb position effect". We determined that RCNN-TL performed the same as or significantly better than LDA in four such problem instances. We also confirmed that transfer learning can minimize user training burden. Overall, this study contributes a multifaceted new suite of control evaluation metrics, along with a guide to their application, for use in research and testing of myoelectric controllers today, and potentially for use in broader rehabilitation technologies of the future.

Clinical and genetic characteristics of myotonia congenita in Chinese population.

Myotonia congenita (MC) is a rare hereditary muscle disease caused by variants in the CLCN1 gene. Currently, the correlation of phenotype-genotype is still uncertain between dominant-type Thomsen (TMC) and recessive-type Becker (BMC). The clinical data and auxiliary examinations of MC patients in our clinic were retrospectively collected. Electromyography was performed in 11 patients and available family members. Whole exome sequencing was conducted in all patients. The clinical and laboratory data of Chinese MC patients reported from June 2004 to December 2022 were reviewed. A total of 11 MC patients were included in the study, with a mean onset age of 12.64 ± 2.73 years. The main symptom was muscle stiffness of limbs. Warm-up phenomenon and percussion myotonia were found in all patients. Electromyogram revealed significant myotonic charges in all patients and two asymptomatic carriers, while muscle MRI and biopsy showed normal or nonspecific changes. Fourteen genetic variants including 6 novel variants were found in CLCN1. Ninety-eight Chinese patients were re-analyzed and re-summarized in this study. There were no significant differences in the demographic data, clinical characteristics, and laboratory findings between 52 TMC and 46 BMC patients. Among the 145 variants in CLCN1, some variants, including the most common variant c.892 G>A, could cause TMC in some families and BMC in others. This study expanded the clinical and genetic spectrum of Chinese patients with MC. It was difficult to distinguish between TMC and BMC only based on the clinical, laboratory, and genetic characteristics.

Optimizing shoulder elevation assist rate in exoskeletal rehabilitation based on muscular activity indices: a clinical feasibility study.

BACKGROUND: Restoring shoulder function is critical for upper-extremity rehabilitation following a stroke. The complex musculoskeletal anatomy of the shoulder presents a challenge for safely assisting elevation movements through robotic interventions. The level of shoulder elevation assistance in rehabilitation is often based on clinical judgment. There is no standardized method for deriving an optimal level of assistance, underscoring the importance of addressing abnormal movements during shoulder elevation, such as abnormal synergies and compensatory actions. This study aimed to investigate the effectiveness and safety of a newly developed shoulder elevation exoskeleton robot by applying a novel optimization technique derived from the muscle synergy index. METHODS: Twelve chronic stroke participants underwent an intervention consisting of 100 robot-assisted shoulder elevation exercises (10 × 10 times, approximately 40 min) for 10 days (4-5 times/week). The optimal robot assist rate was derived by detecting the change points using the co-contraction index, calculated from electromyogram (EMG) data obtained from the anterior deltoid and biceps brachii muscles during shoulder elevation at the initial evaluation. The primary outcomes were the Fugl-Meyer assessment-upper extremity (FMA-UE) shoulder/elbow/forearm score, kinematic outcomes (maximum angle of voluntary shoulder flexion and elbow flexion ratio during shoulder elevation), and shoulder pain outcomes (pain-free passive shoulder flexion range of motion [ROM] and visual analogue scale for pain severity during shoulder flexion). The effectiveness and safety of robotic therapy were examined using the Wilcoxon signed-rank sum test. RESULTS: All 12 patients completed the procedure without any adverse events. Two participants were excluded from the analysis because the EMG of the biceps brachii was not obtained. Ten participants (five men and five women; mean age: 57.0 [5.5] years; mean FMA-UE total score: 18.7 [10.5] points) showed significant improvement in the FMA-UE shoulder/elbow/forearm score, kinematic outcomes, and pain-free passive shoulder flexion ROM (P < 0.05). The shoulder pain outcomes remained unchanged or improved in all patients. CONCLUSIONS: The study presents a method for deriving the optimal robotic assist rate. Rehabilitation using a shoulder robot based on this derived optimal assist rate showed the possibility of safely improving the upper-extremity function in patients with severe stroke in the chronic phase.

Exploration of a machine learning approach for diagnosing sarcopenia among Chinese community-dwelling older adults using sEMG-based data.

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.

Orbicularis oculi muscle activity during computer reading under different degrees of artificially-induced aniseikonia.

Background: Aniseikonia is a binocular vision disorder that has been associated with asthenopic symptoms. However, asthenopia has been evaluated with subjective tests that make difficult to determine the level of aniseikonia. This study aims to objectively evaluate the impact of induced aniseikonia at different levels on visual fatigue by measuring the orbicularis oculi muscle activity in the dominant and non-dominant eyes while performing a reading task. Methods: Twenty-four collegiate students (24.00 ± 3.86 years) participated in this study. Participants read a passage for 7 minutes under four degrees of aniseikonia (0%, 3%, 5% and 10%) at 50 cm. Orbicularis oculi muscle activity of the dominant and non-dominant eye was recorded by surface electromyography. In addition, visual discomfort was assessed after each task by completing a questionnaire. Results: Orbicularis oculi muscle activity increased under induced aniseikonia (i.e., greater values for the 10% condition in comparison to 0%, and 3% conditions (p = 0.034 and p = 0.023, respectively)). No statistically significant differences were observed in orbicularis oculi muscle activity for the time on task and between the dominant and non-dominant eyes. Additionally, higher levels of subjective visual discomfort were observed for lower degrees of induced aniseikonia. Conclusion: Induced aniseikonia increases visual fatigue at high aniseikonia degrees as measured by the orbicularis oculi muscle activity, and at low degrees as measured with subjective questionnaires. These findings may be of relevance to better understand the visual symptomatology of aniseikonia.