Pattern classification reveals intersubject group differences in lumbar muscle recruitment during static loading

Revealing the unique features of each individual's muscle activation signatures

There is growing evidence that each individual has unique movement patterns, or signatures. The exact origin of these movement signatures, however, remains unknown. We developed an approach that can identify individual muscle activation signatures during two locomotor tasks (walking and pedalling). A linear support vector machine was used to classify 78 participants based on their electromyographic (EMG) patterns measured on eight lower limb muscles. To provide insight into decision-making by the machine learning classification model, a layer-wise relevance propagation (LRP) approach was implemented. This enabled the model predictions to be decomposed into relevance scores for each individual input value. In other words, it provided information regarding which features of the time-varying EMG profiles were unique to each individual. Through extensive testing, we have shown that the LRP results, and by extent the activation signatures, are highly consistent between conditions and across days. In addition, they are minimally influenced by the dataset used to train the model. Additionally, we proposed a method for visualizing each individual's muscle activation signature, which has several potential clinical and scientific applications. This is the first study to provide conclusive evidence of the existence of individual muscle activation signatures.

A Review on the Use of Artificial Intelligence in Spinal Diseases

Artificial neural networks (ANNs) have been used in a wide variety of real-world applications and it emerges as a promising field across various branches of medicine. This review aims to identify the role of ANNs in spinal diseases. Literature were searched from electronic databases of Scopus and Medline from 1993 to 2020 with English publications reported on the application of ANNs in spinal diseases. The search strategy was set as the combinations of the following keywords: “artificial neural networks,” “spine,” “back pain,” “prognosis,” “grading,” “classification,” “prediction,” “segmentation,” “biomechanics,” “deep learning,” and “imaging.” The main findings of the included studies were summarized, with an emphasis on the recent advances in spinal diseases and its application in the diagnostic and prognostic procedures. According to the search strategy, a set of 3,653 articles were retrieved from Medline and Scopus databases. After careful evaluation of the abstracts, the full texts of 89 eligible papers were further examined, of which 79 articles satisfied the inclusion criteria of this review. Our review indicates several applications of ANNs in the management of spinal diseases including (1) diagnosis and assessment of spinal disease progression in the patients with low back pain, perioperative complications, and readmission rate following spine surgery; (2) enhancement of the clinically relevant information extracted from radiographic images to predict Pfirrmann grades, Modic changes, and spinal stenosis grades on magnetic resonance images automatically; (3) prediction of outcomes in lumbar spinal stenosis, lumbar disc herniation and patient-reported outcomes in lumbar fusion surgery, and preoperative planning and intraoperative assistance; and (4) its application in the biomechanical assessment of spinal diseases. The evidence suggests that ANNs can be successfully used for optimizing the diagnosis, prognosis and outcome prediction in spinal diseases. Therefore, incorporation of ANNs into spine clinical practice may improve clinical decision making.

Neuromechanical principles underlying movement modularity and their implications for rehabilitation

Neuromechanical principles define the properties and problems that shape neural solutions for movement. Although the theoretical and experimental evidence is debated, we present arguments for consistent structures in motor patterns, i.e., motor modules, that are neuromechanical solutions for movement particular to an individual and shaped by evolutionary, developmental, and learning processes. As a consequence, motor modules may be useful in assessing sensorimotor deficits specific to an individual and define targets for the rational development of novel rehabilitation therapies that enhance neural plasticity and sculpt motor recovery. We propose that motor module organization is disrupted and may be improved by therapy in spinal cord injury, stroke, and Parkinson's disease. Recent studies provide insights into the yet-unknown underlying neural mechanisms of motor modules, motor impairment, and motor learning and may lead to better understanding of the causal nature of modularity and its underlying neural substrates.

Artificial neural networks in neurosurgery

Artificial neural networks (ANNs) effectively analyze non-linear data sets. The aimed was A review of the relevant published articles that focused on the application of ANNs as a tool for assisting clinical decision-making in neurosurgery. A literature review of all full publications in English biomedical journals (1993-2013) was undertaken. The strategy included a combination of key words 'artificial neural networks', 'prognostic', 'brain', 'tumor tracking', 'head', 'tumor', 'spine', 'classification' and 'back pain' in the title and abstract of the manuscripts using the PubMed search engine. The major findings are summarized, with a focus on the application of ANNs for diagnostic and prognostic purposes. Finally, the future of ANNs in neurosurgery is explored. A total of 1093 citations were identified and screened. In all, 57 citations were found to be relevant. Of these, 50 articles were eligible for inclusion in this review. The synthesis of the data showed several applications of ANN in neurosurgery, including: (1) diagnosis and assessment of disease progression in low back pain, brain tumours and primary epilepsy; (2) enhancing clinically relevant information extraction from radiographic images, intracranial pressure processing, low back pain and real-time tumour tracking; (3) outcome prediction in epilepsy, brain metastases, lumbar spinal stenosis, lumbar disc herniation, childhood hydrocephalus, trauma mortality, and the occurrence of symptomatic cerebral vasospasm in patients with aneurysmal subarachnoid haemorrhage; (4) the use in the biomechanical assessments of spinal disease. ANNs can be effectively employed for diagnosis, prognosis and outcome prediction in neurosurgery.

Motor neuronal activity varies least among individuals when it matters most for behavior

How does motor neuronal variability affect behavior? To explore this question, we quantified activity of multiple individual identified motor neurons mediating biting and swallowing in intact, behaving Aplysia californica by recording from the protractor muscle and the three nerves containing the majority of motor neurons controlling the feeding musculature. We measured multiple motor components: duration of the activity of identified motor neurons as well as their relative timing. At the same time, we measured behavioral efficacy: amplitude of grasping movement during biting and amplitude of net inward food movement during swallowing. We observed that the total duration of the behaviors varied: Within animals, biting duration shortened from the first to the second and third bites; between animals, biting and swallowing durations varied. To study other sources of variation, motor components were divided by behavior duration (i.e., normalized). Even after normalization, distributions of motor component durations could distinguish animals as unique individuals. However, the degree to which a motor component varied among individuals depended on the role of that motor component in a behavior. Motor neuronal activity that was essential for the expression of biting or swallowing was similar among animals, whereas motor neuronal activity that was not essential for that behavior varied more from individual to individual. These results suggest that motor neuronal activity that matters most for the expression of a particular behavior may vary least from individual to individual. Shaping individual variability to ensure behavioral efficacy may be a general principle for the operation of motor systems.

Muscle tension estimation in the presence of neuromuscular impairment

Static optimization approaches to estimating muscle tensions rely on the assumption that the muscle activity pattern is in some sense optimal. However, in the case of individuals with a neuromuscular impairment, this assumption is likely not to hold true. We present an approach to muscle tension estimation that does not rely on any optimality assumptions. First, the nature of the impairment is estimated by reformulating the relationship between the muscle tensions and the external forces produced in terms of the deviation from the expected activation in the unimpaired case. This formulation allows the information from several force production tasks to be treated as a single coupled system. In a second step, the identified impairments are used to obtain a novel cost function for the muscle tension estimation task. In a simulation study of the index finger, the proposed method resulted in muscle tension errors with a mean norm of 23.3 ± 26.8% (percentage of the true solution norm), compared to 52.6 ± 24.8% when solving the estimation task using a cost function consisting of the sum of squared muscle stresses. Performance was also examined as a function of the amount of error in the kinematic and muscle Jacobians and found to remain superior to the performance of the squared muscle stress cost function throughout the range examined.

Model-based estimation of muscle forces exerted during movements

Estimation of individual muscle forces during human movement can provide insight into neural control and tissue loading and can thus contribute to improved diagnosis and management of both neurological and orthopaedic conditions. Direct measurement of muscle forces is generally not feasible in a clinical setting, and non-invasive methods based on musculoskeletal modeling should therefore be considered. The current state of the art in clinical movement analysis is that resultant joint torques can be reliably estimated from motion data and external forces (inverse dynamic analysis). Static optimization methods to transform joint torques into estimates of individual muscle forces using musculoskeletal models, have been known for several decades. To date however, none of these methods have been successfully translated into clinical practice. The main obstacles are the lack of studies reporting successful validation of muscle force estimates, and the lack of user-friendly and efficient computer software. Recent advances in forward dynamics methods have opened up new opportunities. Forward dynamic optimization can be performed such that solutions are less dependent on measured kinematics and ground reaction forces, and are consistent with additional knowledge, such as the force-length-velocity-activation relationships of the muscles, and with observed electromyography signals during movement. We conclude that clinical applications of current research should be encouraged, supported by further development of computational tools and research into new algorithms for muscle force estimation and their validation.

Applications of artificial neural nets in clinical biomechanics

The purpose of this article is to provide an overview of current applications of artificial neural networks in the area of clinical biomechanics. The body of literature on artificial neural networks grew intractably vast during the last 15 years. Conventional statistical models may present certain limitations that can be overcome by neural networks. Artificial neural networks in general are introduced, some limitations, and some proven benefits are discussed.

Principal components analysis as an evaluation and classification tool for lower torso sEMG data

The use of univariate statistical techniques on multivariate electromyography data can fail to uncover important relationships between variables. Principal components analysis (PCA) is a multivariate statistical technique that can be used as a data exploration tool, both by classifying participants and simplifying data structures. Past research using this technique has focused on discriminating between "patients" and "normals". This investigation explored the use of PCA on electromyography data from healthy participants, with the objective of elucidating any between-participant differences in the multivariate patterns of muscle coactivation. Results indicated that, even between healthy participants, quantitative and qualitative differences in muscle coactivation patterns exist and that, in the context of the lower torso, a large portion (>70%) of the empirically determined muscle activation could be synthesized in a theoretical three-parameter control model.

Lower torso muscle activation patterns for high-magnitude static exertions: gender differences and the effects of twisting

STUDY DESIGN

Surface electromyographic signals were collected from 14 lower torso muscles while participants resisted high-magnitude static trunk moments applied in a variety of directions.

OBJECTIVES

To obtain a description of muscle activations in response to large moment magnitudes and axial twisting, including levels of agonistic and antagonistic muscle cocontraction. To assess differences in lower torso muscle activation patterns associated with gender and trial repetition.

SUMMARY OF BACKGROUND DATA

Back pain is associated with mechanical loads in the back. Biomechanical modeling of these loads is facilitated by knowledge of typical muscle activation patterns. Previous efforts in obtaining such data have often limited their scope to low-magnitude exertions or relatively simple scenarios.

METHODS

Eight male and eight female participants, matched by height and mass, performed static exertions in an apparatus that immobilized their lower body while the activation levels of seven bilateral torso muscles were measured using surface electromyography. Activation patterns were analyzed to assess differences resulting from a variety of factors.

RESULTS

No significant differences in activation patterns were found between genders or repetitions, but moment magnitude and direction elicited substantial differential responses. Good repeatability was found between trial repetitions, as indicated by intraclass correlation coefficients (>0.65). Significant synergistic muscle coactivation, large intersubject variability (mean coefficient of variation 82.2%), and consistent levels of antagonism ranging from 10% to 30% maximum voluntary exertions were observed.

CONCLUSIONS

Individuals of different genders, but similar anthropometry, have comparable muscular reactions to complex torso loads, suggesting similar motor control strategies. Future spine models should consider that the variability in muscle recruitment patterns is larger between subjects than within subjects. High-magnitude exertions, especially those with moment loads in more than one plane, require most muscles to be active (>5%) and moderate levels of antagonism.

About weight factors in the non-linear objective functions used for solving indeterminate problems in biomechanics

A lot of non-linear objective criteria are applied for solving the indeterminate problems formulated for different biomechanical models--most of them can be covered by the expression [formula in text]. It might be noted, however, that most of the suggested criteria are not applicable if considerable antagonistic co-contractions exist. This could be an effect of treating the agonistic muscles and their respective antagonists in one and the same manner in the objective function. Using a completely inverse approach (the muscle forces are supposed to be known quantities) and a simple 1DOF model (actuated by three agonistic muscles and one corresponding antagonist) it has been shown which values of the weight factors c(i) may predict different levels of muscle forces from the two antagonistic groups. Three hypothetical border variants for magnitudes of the muscle forces are considered (flexor muscles are only active, extensor muscles are only active, considerable co-contraction of flexors and extensors exists). The main conclusions are: the signs of c(i) at agonistic muscles have to be opposite to the c(i) signs at their antagonists; the signs of the weight factors depend on the direction of the net external joint moment; the closer c(i) to zero, the bigger force will be predicted in the ith muscle.

Method and performance: two elements of work technique

In the present study work technique was viewed in two basic elements: the method of carrying out a work task and the individual performance of the work task. The aim was to investigate how eight selected kinematic, kinetic, electromyographic and psychophysical variables can characterize the two elements of work technique. Twelve female subjects lifted a box using two methods, back and leg lifts, and two different simulated performances, fast and slow lifts. Motions, ground reaction forces, muscle activity in the lower back and perceived exertion were measured. A dynamic biomechanical model was applied. The trunk angular displacement and velocity clearly separated the lift methods. The trunk angular velocities and accelerations, the L5/S1 moments and the EMG variables were closely related to the performances. The work technique varied between the subjects to a greater extent than the individual variability over repetitions of a lift task. A larger inter-individual variability for kinematic variables was mostly shown in leg lifts compared with back lifts. The EMG patterns displayed differences in muscle activation that were not revealed by the kinematic or kinetic patterns. The results imply that separate variables should be used for descriptions of work methods and task performances; for method descriptions ranges of motion seem to be appropriate, for performance descriptions displacement time derivatives and load variables seem to be more useful. Moreover, the inter-individual differences suggest that work technique should be evaluated on an individual level.