Edge Artificial Intelligence (AI) for real-time automatic quantification of filariasis in mobile microscopy.

Filariasis, a neglected tropical disease caused by roundworms, is a significant public health concern in many tropical countries. Microscopic examination of blood samples can detect and differentiate parasite species, but it is time consuming and requires expert microscopists, a resource that is not always available. In this context, artificial intelligence (AI) can assist in the diagnosis of this disease by automatically detecting and differentiating microfilariae. In line with the target product profile for lymphatic filariasis as defined by the World Health Organization, we developed an edge AI system running on a smartphone whose camera is aligned with the ocular of an optical microscope that detects and differentiates filarias species in real time without the internet connection. Our object detection algorithm that uses the Single-Shot Detection (SSD) MobileNet V2 detection model was developed with 115 cases, 85 cases with 1903 fields of view and 3342 labels for model training, and 30 cases with 484 fields of view and 873 labels for model validation before clinical validation, is able to detect microfilariae at 10x magnification and distinguishes four species of them at 40x magnification: Loa loa, Mansonella perstans, Wuchereria bancrofti, and Brugia malayi. We validated our augmented microscopy system in the clinical environment by replicating the diagnostic workflow encompassed examinations at 10x and 40x with the assistance of the AI models analyzing 18 samples with the AI running on a middle range smartphone. It achieved an overall precision of 94.14%, recall of 91.90% and F1 score of 93.01% for the screening algorithm and 95.46%, 97.81% and 96.62% for the species differentiation algorithm respectively. This innovative solution has the potential to support filariasis diagnosis and monitoring, particularly in resource-limited settings where access to expert technicians and laboratory equipment is scarce.

Human Motor Noise Assessed by Electromagnetic Sensors and Its Relationship with the Degrees of Freedom Involved in Movement Control.

Motor variability is a prominent feature of the human movement that, nowadays, can be easily measured through different sensors and analyzed using different types of variables, and it seems to be related to functional and adaptative motor behavior. It has been stated that motor variability is related to the system's flexibility needed to choose the right degrees of freedom (DoFs) to adapt to constant environmental changes. However, the potential relationship between motor variability and DoFs is unknown. The aim of this study was to analyze how motor variability, both the amount and structure, changes depending on the mechanical DoFs involved in the movement control. For this purpose, movement variability was assessed by a tracking sensor in five tasks with different DoFs, and the amount, using standard deviation, and the structure of variability, through fuzzy entropy and detrended fluctuation analysis, were also assessed. The results showed a higher amount of variability and a less predictable and more auto-correlated variability structure in the long-term when more mechanical DoFs are implied. The studies that analyze motor variability should consider the type of movement and the DoFs involved in the analyzed task since, as the findings have shown, both factors have a noticeable influence on the amount and the structure of motor variability.

One-Leg Stance Postural Sway Is Not Benefited by Bicycle Motocross Practice in Elite Riders.

Balance has been positioned as an important performance skill in sport. Differences in postural control have been found between levels of expertise. However, this statement remains unanswered in some cyclic sports. This work aimed to describe the one-leg balance performance of a sample of elite BMX riders-racing and freestyle-compared to a control group formed by recreational athletes. The center of pressure (COP) of nineteen international BMX riders (freestyle, n = 7; racing, n = 12) and twenty physically active adults was analyzed in a 30-s one-leg stance test on both legs. COP dispersion and velocity variables were analyzed. Non-linear dynamics of postural sway were evaluated through Fuzzy Entropy and Detrended Fluctuation Analysis. BMX athletes did not show differences between legs in any of the variables. The control group did show differences between the dominant and non-dominant leg in the magnitude of variability of the COP in the mediolateral axis. Group comparison revealed non-significant differences. International BMX athletes did not show better balance parameters than the control group in a one-leg stance balance task. The adaptations derived from BMX practice do not have a significant impact in one-leg stance balance performance.

Variations induced by the use of unstable surface do not facilitate motor adaptation to a throwing skill.

Induced variability by the use of unstable surfaces has been proposed to enhance proprioceptive control to deal with perturbations in the support base better. However, there is a lack of evidence about its benefits facilitating motor adaptions in upper body skills. In this experiment, practice on an unstable surface was applied to analyze the adaptations in an upper limb precision throwing skill. After a pretest, twenty-one participants were randomly allocated into two groups: one group practiced the throwing task on a stable surface and the other group practiced the same task on an unstable support base. Differences in throwing performance between pre- and post-practice were analyzed in accuracy, hand movement kinematics and variability of the throw in both surface conditions. Fuzzy entropy of the horizontal force was calculated to assess the complexity dynamics of postural sway. Participants improved their performance on the stable and the unstable surface. Induced variability using an unstable surface reduced participants' variability and the complexity of postural sway, but it did not facilitate a superior adaptation of the throwing task. The results suggest that the variations induced by unstable surfaces would fall far from the family of specific motor solutions and would not facilitate additional motor performance of the throwing task.

Kinematics and performance of team-handball throwing: effects of age and skill level.

To assess the influence of age and skill level on handball throwing kinematics and performance, 126 participants were distributed into groups according to their skill level (elite or recreational) and age group (U12, U16 or +18). Each participant performed three sets of 10 throws, aiming to hit a target (40 × 40 cm) located in the right corner of the goal. During testing, kinematic data were recorded and throwing performance (accuracy and velocity) was measured. Results showed greater throwing velocity in the elite compared to recreational groups, whereas no differences were found for throwing accuracy. The elite U16 and +18 groups displayed higher segment velocities (hand, arm and pelvis) than the recreational groups. The participation of proximal segments was higher in older groups, showing the more skilled players (U16 and +18) greater pelvis velocities (1.62-1.75 vs 1.02-1.22 m/s). The increased velocity of the distal joints (hand peak velocity: 13.56 ± 1.65 vs 10.67 ± 1.98 m/s) are responsible for the difference in throwing velocity between the elite and recreational U12 groups. Several correlations were found between joint kinematics and throwing velocity. Coaches could use these results during training, to optimise specific throwing training.

The effect of enhanced variability after performance stabilization through constant practice.

There is a controversy about the benefits of variable practice on motor learning. This study aimed to analyze the effect of variable practice after the learner stabilized their performance. Thirty-two healthy adults performed a computer-simulated discrete accuracy task in which they had to release a virtual ball to try to hit a target. After a pre-test, the participants were distributed into three training groups: constant practice, variable practice and a group that started practicing in constant conditions, and when their performance stabilized, changed to variable practice. The participants performed 44 sets of 10 repetitions of the task. A post-test and two retention tests were carried out. Variable practice did not show a significant improvement compared to constant practice. Variable practice did not show higher benefits even when performance was stabilized through constant practice, but its effects seem to be modulated by the initial variability of the learners.

The use of non-linear tools to analyze the variability of force production as an index of fatigue: A systematic review.

Background: Fatigue is a process that results in a decreased ability to produce force, and which could eventually affect performance and increase the risk of injury. Force variability analysis has been proposed to describe the level of fatigue with the purpose of detecting the development of fatigue. Variability is credited to play a functional and adaptive role through which the components of a system self-organize to solve a motor problem. Non-linear tools have been applied to analyze the variability of physiological signals, revealing that the structure of motor fluctuations provides relevant information about the functional role of variability. It has been suggested that the presence of lower complexity in the variability structure could reveal a less functional and adaptative state (e.g., ageing or illness). In the last years, an increased number of studies have applied these techniques to force variability analysis in relation to fatigue. Objective: To provide an overview of the current knowledge on the use of non-linear tools on force variability as a fatigue index. Methods: Following PRISMA guidelines, a systematic search of SPORTDiscus, Scopus, Web of Science and PubMed was carried out. Studies included were: a) original studies that analyzed the effect of fatigue on humans during an action focused on force production; b) published studies with their title and abstract in English; c) studies that applied non-linear tools on a signal directly related to force production. Results: Twenty-five studies were included in this review. The relationship between fatigue and the complexity of force variability, the type of action and relative intensity, the nature of the signal and the non-linear tools used, and the methods of data acquisition and processing were identified. Conclusion: The articles reviewed suggest that fatigue leads to a decrease in complexity mostly in isometric contractions, but this is not as clear in dynamic contractions. This fatigue-induced loss of complexity seems to be a result of changes in the nervous system at the central level, albeit triggered by peripheral mechanisms. It should be noted that non-linear tools are affected by the relative intensity of contraction, non-stationarity, and the acquisition and treatment of the signal.

Motor Synergies Measurement Reveals the Relevant Role of Variability in Reward-Based Learning.

Currently, it is not fully understood how motor variability is regulated to ease of motor learning processes during reward-based tasks. This study aimed to assess the potential relationship between different dimensions of motor variability (i.e., the motor variability structure and the motor synergies variability) and the learning rate in a reward-based task developed using a two-axis force sensor in a computer environment. Forty-four participants performed a pretest, a training period, a posttest, and three retests. They had to release a virtual ball to hit a target using a vertical handle attached to a dynamometer in a computer-simulated reward-based task. The participants' throwing performance, learning ratio, force applied, variability structure (detrended fluctuation analysis, DFA), and motor synergy variability (good and bad variability ratio, GV/BV) were calculated. Participants with higher initial GV/BV displayed greater performance improvements than those with lower GV/BV. DFA did not show any relationship with the learning ratio. These results suggest that exploring a broader range of successful motor synergy combinations to achieve the task goal can facilitate further learning during reward-based tasks. The evolution of the motor variability synergies as an index of the individuals' learning stages seems to be supported by our study.

Balance dynamics are related to age and levels of expertise. Application in young and adult tennis players.

In tennis, coaches consider balance fundamental for the acquisition of skilled motor performance. However, the potential relationship between balance and tennis expertise and performance has not been explored yet. Therefore, this study assessed the relationship between balance and tennis performance using linear and non-linear parameters through 1) the comparison of tennis players of different ages and levels of expertise, and 2) analyzing the relationship between balance and tennis serving speed and accuracy. One hundred and six recreational and expert male tennis players took part in the study (age range 10-35 years old). Temporal dynamics of postural control during a balance task on an unstable surface were analyzed through the mean velocity and the detrended fluctuation analysis (DFAV) of center of pressure (COP). Tennis serve performance was quantified by measuring accuracy and speed. Traditional variables measuring balance performance only showed differences according to age but not to sport performance. COP showed a reduction of auto-correlated variability (reflected by DFAV) with age but mainly in expert players. COP dynamics was the only balance parameter discriminating sport expertise and it was related to age. Balance dynamics exhibited by expert tennis players DFAV results support the idea that, along the years, sport experience induces balance adaptations characterized by a higher ability to perform postural adjustments. These results also reinforce the use of non-linear analysis to reveal subtle balance adaptations produced by sport practice. Finally, the lack of correlations suggests that balance, measured with scattering variables, in a non-specific task is not a main determinant of sport performance in tennis serve.

Functional Variability in Team-Handball Players during Balance Is Revealed by Non-Linear Measures and Is Related to Age and Expertise Level.

Postural control is considered a key variable in team sports, such as handball, which require abilities strongly related to balance. However, postural control and its relationship to the performance of handball skills according to the players' skill level and age has not been evaluated to date. This study analyzes the relationship between balance ability and team-handball performance according to age and expertise, applying a non-linear approach to balance assessment. Postural control from 114 male team-handball players was analyzed through the center of pressure (COP) during a balance task. Sport performance was measured by the accuracy and speed in throwing. Expert players threw faster, but not more accurately than recreational players. Balance performance was better for 18+ players (older than 18 years old) than those U12 (under 12 years old), but no differences were found according to their skill level. Players who threw with less accuracy showed slower COP velocity during the balance task and their moves were less irregular. Players who threw faster displayed more irregular and less auto-correlated COP movements. In conclusion, experienced team-handball players exhibited better balance performance, and this seems to be related to the maturation of the motor system more than to sport performance level. Nevertheless, non-linear measures of COP excursion revealed an exploratory behavior during balance in expert players, exhibiting more motion adjustments to reduce motor output error. Traditional variables measuring balance performance did not show sensitivity to this motor control process. A non-linear approach to balance assessment revealed functional variability during balance as an intrinsic characteristic of individuals' motor control according to age and skill level.

Age-Dependent Statistical Changes of Involuntary Head Motion Signatures Across Autism and Controls of the ABIDE Repository.

The DSM-5 definition of autism spectrum disorders includes sensory issues and part of the sensory information that the brain continuously receives comes from kinesthetic reafference, in the form of self-generated motions, including those that the nervous systems produce at rest. Some of the movements that we self-generate are deliberate, while some occur spontaneously, consequentially following those that we can control. Yet, some motions occur involuntarily, largely beneath our awareness. We do not know much about involuntary motions across development, but these motions typically manifest during resting state in fMRI studies. Here we ask in a large data set from the Autism Brain Imaging Exchange repository, whether the stochastic signatures of variability in the involuntary motions of the head typically shift with age. We further ask if those motions registered from individuals with autism show a significant departure from the normative data as we examine different age groups selected at random from cross-sections of the population. We find significant shifts in statistical features of typical levels of involuntary head motions for different age groups. Further, we find that in autism these changes also manifest in non-uniform ways, and that they significantly differ from their age-matched groups. The results suggest that the levels of random involuntary motor noise are elevated in autism across age groups. This calls for the use of different age-appropriate statistical models in research that involves dynamically changing signals self-generated by the nervous systems.

Aging with Autism Departs Greatly from Typical Aging.

Autism has been largely portrayed as a psychiatric and childhood disorder. However, autism is a lifelong neurological condition that evolves over time through highly heterogeneous trajectories. These trends have not been studied in relation to normative aging trajectories, so we know very little about aging with autism. One aspect that seems to develop differently is the sense of movement, inclusive of sensory kinesthetic-reafference emerging from continuously sensed self-generated motions. These include involuntary micro-motions eluding observation, yet routinely obtainable in fMRI studies to rid images of motor artifacts. Open-access repositories offer thousands of imaging records, covering 5-65 years of age for both neurotypical and autistic individuals to ascertain the trajectories of involuntary motions. Here we introduce new computational techniques that automatically stratify different age groups in autism according to probability distance in different representational spaces. Further, we show that autistic cross-sectional population trajectories in probability space fundamentally differ from those of neurotypical controls and that after 40 years of age, there is an inflection point in autism, signaling a monotonically increasing difference away from age-matched normative involuntary motion signatures. Our work offers new age-appropriate stochastic analyses amenable to redefine basic research and provide dynamic diagnoses as the person's nervous systems age.

Do intentionality constraints shape the relationship between motor variability and performance?

The aim of this experiment was to assess if the previously supported relationship between the structure of motor variability and performance changes when the task or organismic constraints encourage individuals to adjust their movement to achieve a goal. Forty-two healthy volunteers (aged 26.05 ± 5.02 years) performed three sets of cyclic pointing movements, 600 cycles each. Every set was performed under different conditions: 1) without a target; 2) with a target; 3) with a target and a financial reward. The amount of performance variability was analysed using the standard deviation of the medial-lateral (ML) and anterior-posterior (AP) axes and the bivariate variable error. The structure of the variability was assessed by Detrended Fluctuation Analysis (DFA) of the following time series: the coordinate values of the endpoint in ML, AP axes and resultant distance (RD), the hand orientation and the movement time. The performance of the task constrained with a target, or a target and reward, required higher implication to adjust an individual's movements to achieve the task goal, showing a decrease in dispersions and lower autocorrelation. Under the condition without a target, variability dispersion was positively related to autocorrelation of the movement values from ML axis and RD time series, and negatively related to the values from the hand orientation time series. There was a loss of the relationship between variability structure and performance when the task was constrained by the target and the reward. That could indicate different strategies of the participants to achieve the objective. Considering the results and previous studies, the relationship between variability structure and performance could depend on task constraints such as feedback, difficulty or the skill level of participants and it is mediated by individual constraints such as implication or intentionality.

Movement variability emerges in gait as adaptation to task constraints in dynamic environments.

BACKGROUND: Motor variability has been related to motor control playing a functional role in human adaptive behaviours. However, the direction of the relationship between variability and motor control can be unclear. The specific relations that exist between task constraints and movement (re)organization could explain some of this controversy. RESEARCH QUESTION: This study sought to understand whether manipulation of task constraints result in changes in the magnitude or structure of motor system variability observed in a basic walking task. We also investigated the relationship between performance in achieving task goals and the structure of motor variability. METHODS: Twenty volunteers walked around a circular track with binary combinations of 3 task constraints, providing 8 conditions. The manipulated task constraints were: 1) track width; 2) surface stiffness; and 3), walking direction. Performance was analysed using standard deviation (SD) of sacral displacement and its mean velocity (MV). Fuzzy Entropy (FE) and Detrended Fluctuation Analysis (DFA) were used to assess the kinematic variability structure. RESULTS: Individuals showed lower SD and MV walking on the narrower track. These changes were also followed by higher DFA values, indicating a more auto-correlated structure of variability. The foam surface was also associated with an increase in amplitude, velocity and irregularity (FE) of movement. SIGNIFICANCE: Results of this study describe how specific task constraints, such as the width of the walking track and the surface stiffness, shape emergent movement coordination patterns as participants search for functional information from the environment to regulate performance behaviors. Changes in variability structure could reveal the search for adaptive strategies during walking. Smaller movement fluctuations and higher velocity in gait patterns are related to greater irregularity and lower autocorrelation in the kinematic variability structure, demonstrating that a specific relationship emerges between system variability and movement performance, which is driven by task constraints.

Characterization of Noise Signatures of Involuntary Head Motion in the Autism Brain Imaging Data Exchange Repository.

The variability inherently present in biophysical data is partly contributed by disparate sampling resolutions across instrumentations. This poses a potential problem for statistical inference using pooled data in open access repositories. Such repositories combine data collected from multiple research sites using variable sampling resolutions. One example is the Autism Brain Imaging Data Exchange repository containing thousands of imaging and demographic records from participants in the spectrum of autism and age-matched neurotypical controls. Further, statistical analyses of groups from different diagnoses and demographics may be challenging, owing to the disparate number of participants across different clinical subgroups. In this paper, we examine the noise signatures of head motion data extracted from resting state fMRI data harnessed under different sampling resolutions. We characterize the quality of the noise in the variability of the raw linear and angular speeds for different clinical phenotypes in relation to age-matched controls. Further, we use bootstrapping methods to ensure compatible group sizes for statistical comparison and report the ranges of physical involuntary head excursions of these groups. We conclude that different sampling rates do affect the quality of noise in the variability of head motion data and, consequently, the type of random process appropriate to characterize the time series data. Further, given a qualitative range of noise, from pink to brown noise, it is possible to characterize different clinical subtypes and distinguish them in relation to ranges of neurotypical controls. These results may be of relevance to the pre-processing stages of the pipeline of analyses of resting state fMRI data, whereby head motion enters the criteria to clean imaging data from motion artifacts.

Manual Dexterity and Intralimb Coordination Assessment to Distinguish Different Levels of Impairment in Boccia Players with Cerebral Palsy.

BACKGROUND: Boccia is a paralympic sport played by athletes with severe neurological impairments affecting all four limbs. Impaired manual dexterity (MD) and intralimb coordination (ILC) may limit individuals' ability to perform certain activities such as grasping, releasing, or manipulating objects, which are essential tasks for daily life or to participate in para sports such as boccia. However, there are currently no specific instruments available to assess hand-arm coordination in boccia players with severe cerebral palsy (CP). PURPOSE: To design new sport-specific coordination tests to assess impaired MD and ILC in boccia players; afterward, quantify to what extent their coordination is impaired compared to a control group (CG) without neurological impairments. METHODS: Seventy-three recreational boccia players with severe CP (BC1: age = 34.01 ± 16.43 years; BC2: age = 33.97 ± 14.29 years), and 19 healthy adults (age = 27.89 ± 7.08 years) completed the test battery. The Box and Block test (BBT) and Box and Ball test (BBLT) were used to assess MD and four tapping tests to assess upper ILC. RESULTS: Both MD tests were able to discriminate between sport classes. Boccia players obtained better scores in the BBLT in comparison to the BBT, showing that the BBLT had more appropriate testing features. On the other hand, only one of the ILC tests was able to discriminate between sport classes, displaying the highest practical significance (d = -1.12). Participants with CP scored significantly worse in all the coordination tests compared to the CG. CONCLUSION: Using sport-specific equipment facilitated grasp function during the MD assessment. Regarding the ILC, the type of movement (continuous vs. discrete) seems to be more relevant for classification than the movement direction (vertical vs. horizontal) or the presence of a ball.

How does the ball influence the performance of change of direction and sprint tests in para-footballers with brain impairments? Implications for evidence-based classification in CP-Football.

The aims of this study were: i) to analyze the reliability and validity of three tests that require sprinting (10 m, 25 m, 40 m), accelerations/decelerations (Stop and Go Test) and change of direction (Illinois Agility Test), with and without ball, in para-footballers with neurological impairments, and ii) to compare the performance in the tests when ball dribbling is required and to explore the practical implications for evidence-based classification in cerebral palsy (CP)-Football. Eighty-two international para-footballers (25.2 ± 6.8 years; 68.7 ± 8.3 kg; 175.3 ± 7.4 cm; 22.5 ± 2.7 kg·m-2), classified according to the International Federation of Cerebral Palsy Football (IFCPF) Classification Rules (classes FT5-FT8), participated in the study. A group of 31 players without CP was also included in the study as a control group. The para-footballers showed good reliability scores in all tests, with and without ball (ICC = 0.53-0.95, SEM = 2.5-9.8%). Nevertheless, the inclusion of the ball influenced testing reproducibility. The low or moderate relationships shown among sprint, acceleration/deceleration and change of direction tests with and without ball also evidenced that they measure different capabilities. Significant differences and large effect sizes (0.53 < ηp2 < 0.97; p < 0.05) were found when para-footballers performed the tests with and without dribbling the ball. Players with moderate neurological impairments (i.e. FT5, FT6, and FT7) had higher coefficients of variation in the trial requiring ball dribbling. For all the tests, we also obtained between-group (FT5-FT8) statistical and large practical differences (ηp2 = 0.35-0.62, large; p < 0.01). The proposed sprint, acceleration/deceleration and change of direction tests with and without ball may be applicable for classification purposes, that is, evaluation of activity limitation from neurological impairments, or decision-making between current CP-Football classes.

Stochastic Signatures of Involuntary Head Micro-movements Can Be Used to Classify Females of ABIDE into Different Subtypes of Neurodevelopmental Disorders.

Background: The approximate 5:1 male to female ratio in clinical detection of Autism Spectrum Disorder (ASD) prevents research from characterizing the female phenotype. Current open access repositories [such as those in the Autism Brain Imaging Data Exchange (ABIDE I-II)] contain large numbers of females to help begin providing a new characterization of females on the autistic spectrum. Here we introduce new methods to integrate data in a scale-free manner from continuous biophysical rhythms of the nervous systems and discrete (ordinal) observational scores. Methods: New data-types derived from image-based involuntary head motions and personalized statistical platform were combined with a data-driven approach to unveil sub-groups within the female cohort. Further, to help refine the clinical DSM-based ASD vs. Asperger's Syndrome (AS) criteria, distributional analyses of ordinal score data from Autism Diagnostic Observation Schedule (ADOS)-based criteria were used on both the female and male phenotypes. Results: Separate clusters were automatically uncovered in the female cohort corresponding to differential levels of severity. Specifically, the AS-subgroup emerged as the most severely affected with an excess level of noise and randomness in the involuntary head micro-movements. Extending the methods to characterize males of ABIDE revealed ASD-males to be more affected than AS-males. A thorough study of ADOS-2 and ADOS-G scores provided confounding results regarding the ASD vs. AS male comparison, whereby the ADOS-2 rendered the AS-phenotype worse off than the ASD-phenotype, while ADOS-G flipped the results. Females with AS scored higher on severity than ASD-females in all ADOS test versions and their scores provided evidence for significantly higher severity than males. However, the statistical landscapes underlying female and male scores appeared disparate. As such, further interpretation of the ADOS data seems problematic, rather suggesting the critical need to develop an entirely new metric to measure social behavior in females. Conclusions: According to the outcome of objective, data-driven analyses and subjective clinical observation, these results support the proposition that the female phenotype is different. Consequently the "social behavioral male ruler" will continue to mask the female autistic phenotype. It is our proposition that new observational behavioral tests ought to contain normative scales, be statistically sound and combined with objective data-driven approaches to better characterize the females across the human lifespan.

Role of vision in sighted and blind soccer players in adapting to an unstable balance task.

This study tested whether a compensatory hypothesis exists on postural control during standing unstable balance tasks comparing blind soccer players (n = 7) to sighted soccer players (n = 15) and sighted sedentary individuals (n = 6). All subjects performed a pre-test, a training of ten practice trials on a single day, and a post-test balance test. All tests were performed on an unstable surface placed on a force platform and under closed-eyes conditions, and a final test was performed with open eyes. Balance performance was assessed by resultant distance (RD) and the magnitude of mean velocity (MV) of the centre of pressure (CoP) displacement, and EMG signals from the gastrocnemius lateralis, tibialis anterior, rectus femoris, and peroneus longus were measured with surface electromyography. Principal component analysis (PCA) on EMG muscular activation was used to assess EMG pattern differences during the balance tasks. All groups improved their performance, obtaining low scores for the closed-eyes condition balance task after the training period in RD, VM, and aids received to keep balance in the novel task, and no differences were found between groups or in interaction effects. Sighted individuals and the control group showed significantly lower RD and VM scores under open-eyes conditions than blind participants. As regards neuromuscular behaviour, three principal patterns explained 84.15% of the variability in the measured data. The theoretical improvement of the other senses caused by visual deprivation does not allow blind individuals to obtain better balance than sighted individuals under closed-eyes conditions, thereby reinforcing the prominent role of vision in integrating and processing the other sensory inputs. In addition, blind individuals seem to increase their muscular co-activation as a safety strategy, but this behaviour is not different to that shown by sighted people under closed-eyes conditions.