Forskning

Offline accuracy has been the preferred performance measure in myoelectric pattern recognition (MPR) for the prediction of motion volition. In this study, different metrics relating the fundamental binary prediction outcomes were analyzed. Our results indicate that global accuracy is biased by 1) the unbalanced number of possible true positive and negative outcomes, and 2) the almost perfect specificity and negative predicted value, which were consistently found across algorithms, topologies, and movements (individual and simultaneous). Therefore, class-specific accuracy is advisable instead. Additionally, we propose the use of precision (positive predictive value) and sensitivity (recall) as a complement to accuracy to better describe the discrimination capabilities of MPR algorithms, as these consider the effect of false predictions. However, all the studied offline metrics failed to predict real-time decoding, and therefore real-time testing continue to be necessary to truly evaluate the clinical usability of MPR.

For the first time, a patient with transhumeral amputation was implanted with a neuromusculoskeletal prosthesis attached directly to the bone, nerves, and muscles in the residual limb. Over the course of one year, the patient demonstrated more dexterous control of the hand by delicately holding an egg without breaking it and operating the prosthesis while touching his toes and reaching his arm overhead, tasks which were more difficult with his previous conventional socket prosthesis. Direct electircal stimulation of the nerve furthermore provided the patient with a sense of touch felt on his missing hand. The neuromusculoskeletal prosthesis gives patients more freedom of movement and invuitive control over the hand, and may represent the next revolution in the field of neuroprosthetics.

This chapter provides an overview on the use of Virtual Reality (VR) in rehabilitation with respect to recent neuroscience and physical therapy reviews of individuals with motor impairments. A wide range of technologies have been employed to provide rehabilitation supported by VR. Several studies have found evidence of the benefits of VR rehabilitation technologies. However, support for their efficacy is still limited due the lack of generalizable results and the uncoordinated effort of many individual, heterogeneous studies that have been conducted. Although VR has clear potential as a rehabilitation tool to improve treatment outcomes, future trials need to take into account the individual perspective of each patient group and consolidate research methodologies across trials to allow for stronger conclusions across the heterogeneous field of neurorehabilitation.

A variety of treatments have been historically used to alleviate phantom limb pain (PLP) with varying efficacy. Recently, virtualreality (VR) has been employed as a more sophisticated mirror therapy. Despite the advantages of VR over a conventional mirror, this approach has retained the use of the contralateral limb and is therefore restricted to unilateral amputees. Moreover, this strategy disregards the actual effort made by the patient to produce phantom motions. In this work, we investigate a treatment in which the virtual limb responds directly to myoelectric activity at the stump, while the illusion of a restored limb is enhanced through augmented reality (AR). Further, phantom motions are facilitated and encouraged through gaming. The proposed set of technologies was administered to a chronic PLP patient who has shown resistance to a variety of treatments (including mirror therapy) for 48 years. Individual and simultaneous phantom movements were predicted using myoelectric patternrecognition and were then used as input for VR and AR environments, as well as for a racing game. The sustained level of pain reported by the patient was gradually reduced to complete painfree periods. The phantom posture initially reported as a strongly closed fist was gradually relaxed, interestingly resembling the neutral posture displayed by the virtual limb. The patient acquired the ability to freely move his phantomlimb, and a telescopic effect was observed where the position of the phantom hand was restored to the anatomically correct distance. More importantly, the effect of the interventions was positively and noticeably perceived by the patient and his relatives. Despite the limitation of a single case study, the successful results of the proposed system in a patient for whom other medical and non-medical treatments have been ineffective justifies and motivates further investigation in a wider study.

The prediction of simultaneous limb motions, e.g. moving two fingers at the same time, is a highly desirable feature for the control of artificial limbs. We investigate different control strategies for both individual and simultaneous movements using muscle signals acquired from able-bodied participants. Our proposed controller based on a neural network outperformed the state-of the-art and allowed the simultaneous control of three different hand movements.

A challenge when analysing electric signals from the muscles using artificial intelligence algorithms to control prosthetic limbs is to find the best algorithm. To find the best algorithm, we tested different algorithms provided by the engineering software Matlab. We found that two of the algorithms provided by Matlab outperformed other algorithms of the same type.

Electric signals from the muscles can be analysed using artificial intelligence to control artificial limbs, but researchers use different development platforms to develop these techniques which slows down progress and makes it harder to compare results. We developed a shared (open source) platform called BioPatRec to foster collaboration and demonstrated its capabilities by analysing signals from 17 able-bodied participants using various techniques. BioPatRec can be used to record signals, process them, analyse them with artificial intelligence and control virtual or mechanical limbs. BioPatrec is freely available and used in three different continents with the hope to accelerate the development of better algorithms to improve the lives of those with limb loss.

Cuff electrodes have been widely used chronically in different clinical applications. This neural interface has been dominantly used for nerve stimulation while interfering noise is the major issue when employed for recording purposes. Advancements have been made in rejecting extra-neural interference by using continuous ring contacts in tripolar topologies. Ring contacts provide an average of the neural activity, and thus reduce the information retrieved. Splitting these contacts into smaller recording areas could potentially increase the information content. In this study, we investigate the impact of such discretization on the Signal-to-Noise Ratio (SNR). The effect of contacts positioning and an additional short circuited pair of electrodes were also addressed. Different recording configurations using ring, dot, and a mixed of both contacts were studied in vitro in a frog model. An interfering signal was induced in the medium to simulate myoelectric noise. The experimental setup was design in such a way that the only difference between recordings was the configuration used. The inter-session experimental differences were taken care of by a common configuration that allowed normalization between electrode designs. It was found that splitting all contacts into small recording areas had negative effects on noise rejection. However, if this is only applied to the central contact creating a mixed tripole configuration, a considerable and statistically significant improvement was observed. Moreover, the signal to noise ratio was equal or larger than what can be achieved with the best known configuration, namely the short circuited tripole. This suggests that for recording purposes, any tripole topology would benefit from splitting the central contact into one or more discrete contacts. Our results showed that a mixed tripole configuration performs better than the configuration including only ring contacts. Therefore, splitting the central ring contact of a cuff electrode into a number of dot contacts not only provides additional information but also an improved SNR. In addition, the effect of an additional pair of short circuited electrodes and the “end effect” observed with the presented method are in line with previous findings by other authors.

In this review of implantable electrode designs, we conclude that implantable electrodes attached to the surface of muscle bellies or cuffed around the nerves are currently the most promising candidates for long-term stable and natural control of robotic prostheses. Our review describes several implantable electrodes and their capacity for allowing coordinated movement of multiple prosthetic joints. The conclusions from this review will guide the selection, design, and long-term implementation of implantable electrodes, which show promise alongside advanced control algorithms to greatly improve the control of robotic prostheses.

Finger and hand positions can be decoded by analyzing the signals acquired from muscle contractions. We selected different biologically inspired algorithms and investigated their movement decoding performance. A neural network, an algorithm inspired by biological human brain, showed the highest accuracy for decoding human hand and finger movements.