Assessing workload in using electromyography (EMG)-based prostheses.

Using prosthetic devices requires a substantial cognitive workload. This study investigated classification models for assessing cognitive workload in electromyography (EMG)-based prosthetic devices with various types of input features including eye-tracking measures, task performance, and cognitive performance model (CPM) outcomes. Features selection algorithm, hyperparameter tuning with grid search, and k-fold cross-validation were applied to select the most important features and find the optimal models. Classification accuracy, the area under the receiver operation characteristic curve (AUC), precision, recall, and F1 scores were calculated to compare the models' performance. The findings suggested that task performance measures, pupillometry data, and CPM outcomes, combined with the naïve bayes (NB) and random forest (RF) algorithms, are most promising for classifying cognitive workload. The proposed algorithms can help manufacturers/clinicians predict the cognitive workload of future EMG-based prosthetic devices in early design phases.Practitioner summary: This study investigated the use of machine learning algorithms for classifying the cognitive workload of prosthetic devices. The findings suggested that the models could predict workload with high accuracy and low computational cost and could be used in assessing the usability of prosthetic devices in the early phases of the design process.Abbreviations: 3d: 3 dimensional; ADL: Activities for daily living; ANN: Artificial neural network; AUC: Area under the receiver operation characteristic curve; CC: Continuous control; CPM: Cognitive performance model; CPM-GOMS: Cognitive-Perceptual-Motor GOMS; CRT: Clothespin relocation test; CV: Cross validation; CW: Cognitive workload; DC: Direct control; DOF: Degrees of freedom; ECRL: Extensor carpi radialis longus; ED: Extensor digitorum; EEG: Electroencephalogram; EMG: Electromyography; FCR: Flexor carpi radialis; FD: Flexor digitorum; GOMS: Goals, Operations, Methods, and Selection Rules; LDA: Linear discriminant analysis; MAV: Mean absolute value; MCP: Metacarpophalangeal; ML: Machine learning; NASA-TLX: NASA task load index; NB: Naïve Bayes; PCPS: Percent change in pupil size; PPT: Purdue Pegboard Test; PR: Pattern recognition; PROS-TLX: Prosthesis task load index; RF: Random forest; RFE: Recursive feature selection; SHAP: Southampton hand assessment protocol; SFS: Sequential feature selection; SVC: Support vector classifier.

Angle-programmed tendril-like trajectories enable a multifunctional gripper with ultradelicacy, ultrastrength, and ultraprecision.

Achieving multicapability in a single soft gripper for handling ultrasoft, ultrathin, and ultraheavy objects is challenging due to the tradeoff between compliance, strength, and precision. Here, combining experiments, theory, and simulation, we report utilizing angle-programmed tendril-like grasping trajectories for an ultragentle yet ultrastrong and ultraprecise gripper. The single gripper can delicately grasp fragile liquids with minimal contact pressure (0.05 kPa), lift objects 16,000 times its own weight, and precisely grasp ultrathin, flexible objects like 4-µm-thick sheets and 2-µm-diameter microfibers on flat surfaces, all with a high success rate. Its scalable and material-independent design allows for biodegradable noninvasive grippers made from natural leaves. Explicitly controlled trajectories facilitate its integration with robotic arms and prostheses for challenging tasks, including picking grapes, opening zippers, folding clothes, and turning pages. This work showcases soft grippers excelling in extreme scenarios with potential applications in agriculture, food processing, prosthesis, biomedicine, minimally invasive surgeries, and deep-sea exploration.

Offline Evaluation Matters: Investigation of the Influence of Offline Performance of EMG-Based Neural-Machine Interfaces on User Adaptation, Cognitive Load, and Physical Efforts in a Real-Time Application.

There has been controversy about the value of offline evaluation of EMG-based neural-machine interfaces (NMIs) for their real-time application. Often, conclusions have been drawn after studying the correlation of the offline EMG decoding accuracy/error with the NMI user's real-time task performance without further considering other important human performance metrics such as adaptation rate, cognitive load, and physical effort. To fill this gap, this study aimed to investigate the relationship between the offline decoding accuracy of EMG-based NMIs and user adaptation, cognitive load, and physical effort in real-time NMI use. Twelve non-disabled subjects participated in this study. For each subject, we established three EMG decoders that yielded different offline accuracy (low, moderate, and high) in predicting continuous hand and wrist motions. The subject then used each EMG decoder to perform a virtual hand posture matching task in real time with and without a secondary task as the evaluation trials. Results showed that the high-level offline performance decoders yield the fastest adaptation rate and highest posture matching completion rate with the least muscle effort in users during online testing. A secondary task increased the cognitive load and reduced real-time virtual task competition rate for all the decoders; however, the decoder with high offline accuracy still produced the highest task completion rate. These results imply that the offline performance of EMG-based NMIs provide important insight to users' abilities to utilize them and should play an important role in research and development of novel NMI algorithms.

Harnessing Machine Learning and Physiological Knowledge for a Novel EMG-Based Neural-Machine Interface.

OBJECTIVE: In this study, we aimed to develop a novel electromyography (EMG)-based neural machine interface (NMI), called the Neural Network-Musculoskeletal hybrid Model (N2M2), to decode continuous joint angles. Our approach combines the concepts of machine learning and musculoskeletal modeling. METHODS: We compared our novel design with a musculoskeletal model (MM) and 2 continuous EMG decoders based on artificial neural networks (ANNs): multilayer perceptrons (MLPs) and nonlinear autoregressive neural networks with exogenous inputs (NARX networks). EMG and joint kinematics data were collected from 10 non-disabled and 1 transradial amputee subject. The offline performance tested across 3 different conditions (i.e., varied arm postures, shifted electrode locations, and noise-contaminated EMG signals) and online performance for a virtual postural matching task was quantified. Finally, we implemented the N2M2 to operate a prosthetic hand and tested functional task performance. RESULTS: The N2M2 made more accurate predictions than the MLP in all postures and electrode locations (p < 0.003). For estimated MCP joint angles, the N2M2 was less sensitive to noisy EMG signals than the MM or NARX network with respect to error (p < 0.032) as well as the NARX network with respect to correlation (p = 0.007). Additionally, the N2M2 had better online task performance than the NARX network (p ≤ 0.030). CONCLUSION: Overall, we have found that combining the concepts of machine learning and musculoskeletal modeling has resulted in a more robust joint kinematics decoder than either concept individually. SIGNIFICANCE: The outcome of this study may result in a novel, highly reliable controller for powered prosthetic hands.

Offline Evaluation Matters: Investigation of the Influence of Offline Performance on Real-time Operation of Electromyography-based Neural-Machine Interfaces.

There has been a debate on the most appropriate way to evaluate electromyography (EMG)-based neural-machine interfaces (NMIs). Accordingly, this study examined whether a relationship between offline kinematic predictive accuracy (R2) and user real-time task performance while using the interface could be identified. A virtual posture-matching task was developed to evaluate motion capture-based control and myoelectric control with artificial neural networks (ANNs) trained to low (R2 ≈ 0.4), moderate (R2 ≈ 0.6), and high (R2 ≈ 0.8) offline performance levels. Twelve able-bodied subjects trained with each offline performance level decoder before evaluating final real-time posture matching performance. Moderate to strong relationships were detected between offline performance and all real-time task performance metrics: task completion percentage (r=0.66, p<0.001), normalized task completion time (r = -0.51, p = 0.001), path efficiency (r = 0.74, p < 0.001), and target overshoots (r = -0.79, p < 0.001). Significant improvements in each real-time task evaluation metric were also observed between the different offline performance levels. Additionally, subjects rated myoelectric controllers with higher offline performance more favorably. The results of this study support the use and validity of offline analyses for optimization of NMIs in myoelectric control research and development.

Comparing Reinforcement Learning Agents and Supervised Learning Neural Networks for EMG-Based Decoding of Continuous Movements.

Recent work on electromyography (EMG)-based decoding of continuous joint kinematics has included model-based approaches, such as musculoskeletal modeling, as well as model-free approaches such as supervised learning neural networks (SLNN). This study aimed to present a new kinematics decoding framework based on reinforcement learning (RL), which combines machine learning and model-based approaches together. We compared the performance and robustness of our new method with those of the SLNN approach. EMG and kinematic data were collected from 5 able-bodied subjects while they performed flexion and extension of the metacarpophalangeal (MCP) and wrist joints simultaneously at both a slow and fast tempo. The data were used to train an RL agent and a SLNN for each of the 2 tempos. All the trained agents and SLNNs were tested with both fast and slow kinematic data. Pearson's correlation coefficient (r) and normalized root mean square error (NRMSE) between measured and estimated joint angles were used to determine performance. Our results suggest that the RL-based kinematics decoder is more robust to changes in movement speeds between training and testing data and has better performance than the SLNN.

Hepatocellular Carcinoma Without Cirrhosis Presenting With Hypercalcemia: Case Report and Literature Review.

BACKGROUND: Hepatocellular carcinoma (HCC) in non-cirrhotic livers is an uncommon finding and can present insidiously in patients. Another uncommon finding in HCC, and one of poor prognosis, is the presence of paraneoplastic diseases such as hypercalcemia. We report a case of a 66-year-old previous healthy Filipina woman who after routine laboratory evaluation was discovered to have hypercalcemia as the first sign of an advanced HCC without underlying cirrhosis. Because of the patient's relative lack of symptoms, healthy liver function, lack of classical HCC risk factors, and unexpected hypercalcemia, the diagnosis of a paraneoplastic syndrome caused by a noncirrhotic HCC was unanticipated. METHODS: Case Analysis with Pubmed literature review. RESULTS: It is unknown how often hypercalcemia is found in association with HCC in a non-cirrhotic liver. However, paraneoplastic manifestations of HCC, particularly hypercalcemia, can be correlated with poor prognosis. For this patient, initial management included attempts to lower calcium levels via zoledronate, which wasn't completely effective. Tumor resection was then attempted however the patient expired due to complications from advanced tumor size. CONCLUSIONS: Hypercalcemia of malignancy can be found in association with non-cirrhotic HCC and should be considered on the differential diagnosis during clinical work-up.

Bactericidal and cytotoxic effects of chloramine-T on wound pathogens and human fibroblasts in vitro.

OBJECTIVES: To evaluate cytotoxicity and bactericidal effects of chloramine-T. METHODS: In vitro study of various concentrations and exposure times to preparations containing human fibroblasts or 1.5 x 10 colony forming units per milliliter (CFU/mL) of 3 gram-positive bacteria-Staphylococcus aureus, methicillin-resistant S aureus, and vancomycin-resistant Enterococcus faecalis-and 2 gram-negative bacteria-Escherichia coli and Pseudomonas aeruginosa-with and without fetal bovine serum present. MAIN OUTCOME MEASURES: Percentage reduction of bacterial growth and percentage of viable fibroblasts 48 hours after exposure. RESULTS: All gram-positive growth was reduced by 95% to 100%, regardless of dose, with or without serum. E coli (gram-negative; with/without serum) was reduced 94% to 100% at antiseptic concentrations of 300 and 400 ppm. At 200 ppm, E coli growth was fully inhibited without serum present and by 50% with serum. P aeruginosa (gram-negative) was not significantly affected under any conditions. At 100 and 200 ppm, cell viability remained greater than 90% under all experimental conditions. A 300-ppm, 3-minute exposure to chloramine-T resulted in cell viability of up to 70%, with longer exposures producing lower viabilities. Serum did not affect cell viability in any condition. CONCLUSIONS: In vitro, chloramine-T at 200 ppm for 5 to 20 minutes was effective against 3 virulent gram-positive bacteria without fibroblast damage. At 300 ppm and 3 and 5 minutes, 30% of fibroblasts were damaged and 95% to 100 % of E coli were inhibited, respectively.

Effect of computer keyboard slope on wrist position and forearm electromyography of typists without musculoskeletal disorders.

BACKGROUND AND PURPOSE: Positioning a computer keyboard with a downward slope reduces wrist extension needed to use the keyboard and has been shown to decrease pressure in the carpal tunnel. However, whether a downward slope of the keyboard reduces electromyographic (EMG) activity of the forearm muscles, in particular the wrist extensors, is not known. SUBJECTS AND METHODS: Sixteen experienced typists participated in this study and typed on a conventional keyboard that was placed on slopes at angles of 7.5, 0, -7.5, and -15 degrees. Electromyographic activity of the extensor carpi ulnaris (ECU), flexor carpi ulnaris (FCU), and flexor carpi radialis (FCR) muscles was measured with surface electrodes, while the extension and ulnar deviation angles of the right and left wrists were measured with electrogoniometers. RESULTS: Wrist extension angle decreased from approximately 12 degrees of extension while typing on a keyboard with a 7.5-degree slope to 3 degrees of flexion with the keyboard at a slope of -15 degrees. Although the differences were in the range of 1% to 3% of maximum voluntary contraction (MVC), amplitude probability distribution function (APDF) of root-mean-square EMG data points from the ECU, FCU, and FCR muscles varied across keyboard slopes. DISCUSSION AND CONCLUSION: Wrist extension decreased as the keyboard slope decreased. Furthermore, a slight decrease in percentage of MVC of the ECU muscle was noted as the keyboard slope decreased. Based on biomechanical modeling and published work on carpal tunnel pressure, both of these findings appear to be positive with respect to comfort and fatigue, but the exact consequences of these findings on the reduction or prevention of injuries have yet to be determined. The results may aid physical therapists and ergonomists in their evaluations of computer keyboard workstations and in making recommendations for interventions with regard to keyboard slope angle.

A randomized controlled clinical trial to evaluate the effects of noncontact normothermic wound therapy on chronic full-thickness pressure ulcers.

OBJECTIVE: To determine the effect of noncontact normothermic wound therapy (NNWT) versus standard wound care on chronic full-thickness pressure ulcers. DESIGN: Prospective, randomized, controlled trial. SETTING: Veterans administration medical center and 7 long-term-care facilities. PATIENTS: 40 inpatients with 43 Stage III and IV pressure ulcers. INTERVENTIONS: A sterile noncontact wound dressing was applied to 21 wounds for 24 hours per day, 7 days per week. Each day after the wound was irrigated and the noncontact dressing was changed, a heating element in the dressing was activated for 3 1-hour periods for 12 weeks or until wound closure. Twenty-two control wounds were treated with standard, moisture-retentive dressings 24 hours per day, 7 days per week for 12 weeks or until wound closure. MAIN OUTCOME MEASURE: Measurement of wound surface area. MAIN RESULTS: Healing rate for the NNWT group was significantly greater than for the control group (0.52 cm2 per week and 0.23 cm2 per week, respectively; P<.02). A clinically significant increase was seen among the NNWT group in the incidence of closure among wounds that completed the entire 12-week protocol compared with controls (11 of 14 or 79% and 8 of 16 or 50%, respectively; not significant). The mean slope of the individual regression analyses for the NNWT group was significantly different from the mean slope for the control group (-0.07 and -0.033, respectively; P<.05). Large wounds in the NNWT group demonstrated a significantly greater healing rate than large wounds in the control group (P <.05). CONCLUSION: Wounds treated with NNWT healed significantly faster than wounds in the control group. The healing rate was greatest for larger wounds treated with NNWT.