Gait analysis comparison between manual marking, 2D pose estimation algorithms, and 3D marker-based system.

Introduction: Recent advances in Artificial Intelligence (AI) and Computer Vision (CV) have led to automated pose estimation algorithms using simple 2D videos. This has created the potential to perform kinematic measurements without the need for specialized, and often expensive, equipment. Even though there's a growing body of literature on the development and validation of such algorithms for practical use, they haven't been adopted by health professionals. As a result, manual video annotation tools remain pretty common. Part of the reason is that the pose estimation modules can be erratic, producing errors that are difficult to rectify. Because of that, health professionals prefer the use of tried and true methods despite the time and cost savings pose estimation can offer. Methods: In this work, the gait cycle of a sample of the elderly population on a split-belt treadmill is examined. The Openpose (OP) and Mediapipe (MP) AI pose estimation algorithms are compared to joint kinematics from a marker-based 3D motion capture system (Vicon), as well as from a video annotation tool designed for biomechanics (Kinovea). Bland-Altman (B-A) graphs and Statistical Parametric Mapping (SPM) are used to identify regions of statistically significant difference. Results: Results showed that pose estimation can achieve motion tracking comparable to marker-based systems but struggle to identify joints that exhibit small, but crucial motion. Discussion: Joints such as the ankle, can suffer from misidentification of their anatomical landmarks. Manual tools don't have that problem, but the user will introduce a static offset across the measurements. It is proposed that an AI-powered video annotation tool that allows the user to correct errors would bring the benefits of pose estimation to professionals at a low cost.

A Comparative Analysis of Symmetry Indices for Spatiotemporal Gait Features in Early Parkinson's Disease.

This study compared the five most commonly used equations for calculating gait symmetry in discrete variables among Parkinson's disease patients. Twelve patients (five women and seven men) performed ten consecutive gait trials on a 10 m walkway. Gait data were collected using eight optoelectronic cameras (100 fr/s). The analysis focused on various spatiotemporal parameters, including cadence, step time, stride time, single support, double support, walking speed, step length, stride length, step width, and foot angle. Five symmetry indices were calculated for each trial rather than averaging the ten recorded trials. The variability in and reliability of each symmetry equation were assessed using the coefficient of variation (CV) and intraclass correlation coefficient (ICC), respectively. Additionally, Bland-Altman plots were produced to visualize the agreement between each pair of methods for each spatiotemporal parameter. The results revealed that the symmetry ratio method exhibited lower variability and higher reliability compared with the other four indices across all spatiotemporal gait parameters. However, it was found that the reliability of a single trial was generally poor, regardless of the symmetry calculation formula used. Therefore, we recommend basing measurements of gait asymmetry in Parkinson's disease on multiple trials.

Monocyte to HDL and Neutrophil to HDL Ratios as Potential Ischemic Stroke Prognostic Biomarkers.

Ischemic stroke (IS) exhibits significant heterogeneity in terms of etiology and pathophysiology. Several recent studies highlight the significance of inflammation in the onset and progression of IS. White blood cell subtypes, such as neutrophils and monocytes, participate in the inflammatory response in various ways. On the other hand, high-density lipoproteins (HDL) exhibit substantial anti-inflammatory and antioxidant actions. Consequently, novel inflammatory blood biomarkers have emerged, such as neutrophil to HDL ratio (NHR) and monocyte to HDL ratio (MHR). Literature research of two databases (MEDLINE and Scopus) was conducted to identify all relevant studies published between 1 January 2012 and 30 November 2022 dealing with NHR and MHR as biomarkers for IS prognosis. Only full-text articles published in the English language were included. Thirteen articles have been traced and are included in the present review. Our findings highlight the utility of NHR and MHR as novel stroke prognostic biomarkers, the widespread application, and the calculation of which, along with their inexpensive cost, make their clinical application extremely promising.

Elucidating the Role of Baseline Leukoaraiosis on Forecasting Clinical Outcome of Acute Ischemic Stroke Patients Undergoing Reperfusion Therapy.

Stroke stands as a major cause of death and disability with increasing prevalence. The absence of clinical improvement after either intravenous thrombolysis (IVT) or mechanical thrombectomy (MT) represents a frequent concern in the setting of acute ischemic stroke (AIS). In an attempt to optimize overall stroke management, it is clinically valuable to provide important insight into functional outcomes after reperfusion therapy among patients presenting with AIS. The aim of the present review is to explore the predictive value of leukoaraiosis (LA) in terms of clinical response to revascularization poststroke. A literature research of two databases (MEDLINE and Scopus) was conducted in order to trace all relevant studies published between 1 January 2012 and 1 November 2022 that focused on the potential utility of LA severity regarding reperfusion status and clinical outcome after revascularization. A total of 37 articles have been traced and included in this review. LA burden assessment is indicative of functional outcome post-intervention and may be associated with hemorrhagic events' incidence among stroke individuals. Nevertheless, LA may not solely guide decision-making about treatment strategy poststroke. Overall, the evaluation of LA upon admission seems to have interesting prognostic potential and may substantially enhance individualized stroke care.

An Explainable Machine Learning Pipeline for Stroke Prediction on Imbalanced Data.

Stroke is an acute neurological dysfunction attributed to a focal injury of the central nervous system due to reduced blood flow to the brain. Nowadays, stroke is a global threat associated with premature death and huge economic consequences. Hence, there is an urgency to model the effect of several risk factors on stroke occurrence, and artificial intelligence (AI) seems to be the appropriate tool. In the present study, we aimed to (i) develop reliable machine learning (ML) prediction models for stroke disease; (ii) cope with a typical severe class imbalance problem, which is posed due to the stroke patients' class being significantly smaller than the healthy class; and (iii) interpret the model output for understanding the decision-making mechanism. The effectiveness of the proposed ML approach was investigated in a comparative analysis with six well-known classifiers with respect to metrics that are related to both generalization capability and prediction accuracy. The best overall false-negative rate was achieved by the Multi-Layer Perceptron (MLP) classifier (18.60%). Shapley Additive Explanations (SHAP) were employed to investigate the impact of the risk factors on the prediction output. The proposed AI method could lead to the creation of advanced and effective risk stratification strategies for each stroke patient, which would allow for timely diagnosis and the right treatments.

Stroke and Emerging Blood Biomarkers: A Clinical Prospective.

Stroke constitutes the primary source of adult functional disability, exhibiting a paramount socioeconomic burden. Thus, it is of great importance that the prediction of stroke outcome be both prompt and accurate. Although modern neuroimaging and neurophysiological techniques are accessible, easily available blood biomarkers reflecting underlying stroke-related pathophysiological processes, including glial and/or neuronal death, neuroendocrine responses, inflammation, increased oxidative stress, blood-brain barrier disruption, endothelial dysfunction, and hemostasis, are required in order to facilitate stroke prognosis. A literature search of two databases (MEDLINE and Science Direct) was conducted in order to trace all relevant studies published between 1 January 2010 and 31 December 2021 that focused on the clinical utility of brain natriuretic peptide, glial fibrillary acidic protein, the red cell distribution width, the neutrophil-to-lymphocyte ratio, matrix metalloproteinase-9, and aquaporin-4 as prognostic tools in stroke survivors. Only full-text articles published in English were included. Twenty-eight articles were identified and are included in this review. All studied blood-derived biomarkers proved to be valuable prognostic tools poststroke, the clinical implementation of which may accurately predict the survivors' functional outcomes, thus significantly enhancing the rehabilitation efficiency of stroke patients. Along with already utilized clinical, neurophysiological, and neuroimaging biomarkers, a blood-derived multi-biomarker panel is proposed as a reasonable approach to enhance the predictive power of stroke prognostic models.

Development of Muscle-Tendon Adaptation in Preadolescent Gymnasts and Untrained Peers: A 12-Month Longitudinal Study.

PURPOSE: The current study investigated the effects of long-term athletic training on the development of the triceps surae muscle-tendon unit in preadolescence. METHODS: Eleven preadolescent untrained children and a group of 21 artistic gymnastics athletes of similar age (9 ± 1.7 yr) and maturity (Tanner stages I and II) participated in the study. The measurements were conducted every 3 months for 1 yr, and training volume and duration of the athletes were documented. Plantar flexor muscle strength, Achilles tendon stiffness, maximum tendon strain, and gastrocnemius medialis morphometrics were measured by integrating kinematics, ultrasonography, and dynamometry. A linear mixed-effects model was used to analyze the investigated parameters. RESULTS: We found greater muscle strength (P < 0.001) in athletes compared with nonathletes but no differences in Achilles tendon stiffness (P = 0.252), indicating a training-induced imbalanced adaptation of muscle strength and tendon stiffness in preadolescent athletes. Although pennation angle (P = 0.490), thickness (P = 0.917), and fascicle length (P = 0.667) did not differ between groups, we found higher fluctuations in pennation angle and muscle strength over 1 yr in athletes. The imbalanced adaptation of muscle strength and tendon stiffness together with greater fluctuations of muscle strength resulted in greater tendon strain fluctuations over 1 yr (P = 0.017) and a higher frequency of athletes with high-level tendon strain (≥9%) compared with nonathletes. CONCLUSIONS: The findings indicate an increased mechanical demand for the tendon in preadolescent athletes that could have implications for the risk of tendon overuse injury. Therefore, we recommend the implementation of individual training approaches to preserve a balanced adaptation within the triceps surae muscle-tendon unit in preadolescent athletes.

Effects of long-term athletic training on muscle morphology and tendon stiffness in preadolescence: association with jump performance.

PURPOSE: Evidence on training-induced muscle hypertrophy during preadolescence is limited and inconsistent. Possible associations of muscle strength and tendon stiffness with jumping performance are also not investigated. We investigated the thickness and pennation angle of the gastrocnemius medialis muscle (GM), as indicators for potential muscle hypertrophy in preadolescent athletes. Further, we examined the association of triceps surae muscle-tendon properties with jumping performance. METHODS: Eleven untrained children (9 years) and 21 similar-aged artistic gymnastic athletes participated in the study. Muscle thickness and pennation angle of the GM were measured at rest and muscle strength of the plantar flexors and Achilles tendon stiffness during maximum isometric contractions. Jumping height in squat (SJ) and countermovement jumps (CMJ) was examined using a force plate. We evaluated the influence of normalised muscle strength and tendon stiffness on jumping performance with a linear regression model. RESULTS: Muscle thickness and pennation angle did not differ significantly between athletes and non-athletes. In athletes, muscle strength was greater by 25% and jumping heights by 36% (SJ) and 43% (CMJ), but Achilles tendon stiffness did not differ between the two groups. The significant predictor for both jump heights was tendon stiffness in athletes and normalised muscle strength for the CMJ height in non-athletes. CONCLUSION: Long-term artistic gymnastics training during preadolescence seems to be associated with increased muscle strength and jumping performance but not with training-induced muscle hypertrophy or altered tendon stiffness in the plantar flexors. Athletes benefit more from tendon stiffness and non-athletes more from muscle strength for increased jumping performance.

Triceps Surae Muscle-Tendon Unit Properties in Preadolescent Children: A Comparison of Artistic Gymnastic Athletes and Non-athletes.

Knowledge regarding the effects of athletic training on the properties of muscle and tendon in preadolescent children is scarce. The current study compared Achilles tendon stiffness, plantar flexor muscle strength and vertical jumping performance of preadolescent athletes and non-athletes to provide insight into the potential effects of systematic athletic training. Twenty-one preadolescent artistic gymnastic athletes (9.2 ± 1.6 years, 15 girls) and 11 similar-aged non-athlete controls (9.0 ± 1.7 years, 6 girls) participated in the study. The training intensity and volume of the athletes was documented for the last 6 months before the measurements. Subsequently, vertical ground reaction forces were measured with a force plate to assess jumping performance during squat (SJ) and countermovement jumps (CMJ) in both groups. Muscle strength of the plantar flexor muscles and Achilles tendon stiffness were examined using ultrasound, electromyography, and dynamometry. The athletes trained 6 days per week with a total of 20 h of training per week. Athletes generated significantly greater plantar flexion moments normalized to body mass compared to non-athletes (1.75 ± 0.32 Nm/kg vs. 1.31 ± 0.33 Nm/kg; p = 0.001) and achieved a significantly greater jump height in both types of jumps (21.2 ± 3.62 cm vs. 14.9 ± 2.32 cm; p < 0.001 in SJ and 23.4 ± 4.1 cm vs. 16.4 ± 4.1 cm; p < 0.001 in CMJ). Achilles tendon stiffness did not show any statistically significant differences (p = 0.413) between athletes (116.3 ± 32.5 N/mm) and non-athletes (106.4 ± 32.8 N/mm). Athletes were more likely to reach strain magnitudes close to or higher than 8.5% strain compared to non-athletes (frequency: 24% vs. 9%) indicating an increased mechanical demand for the tendon. Although normalized muscle strength and jumping performance were greater in athletes, gymnastic-specific training in preadolescence did not cause a significant adaptation of Achilles tendon stiffness. The potential contribution of the high mechanical demand for the tendon to the increasing risk of tendon overuse call for the implementation of specific exercises in the athletic training of preadolescent athletes that increase tendon stiffness and support a balanced adaptation within the muscle-tendon unit.

Reproducibility of gait kinematics and kinetics in chronic stroke patients.

BACKGROUND: The search for reliable techniques to assess gait in stroke patients is crucial for the design and follow-up of rehabilitation programs. OBJECTIVE: To assess the reproducibility of kinematic and kinetic gait parameters in chronic stroke patients using a three-dimensional gait analysis system. METHODS: Ten chronic stroke patients were assessed while walking along a 20 m walkway at their natural speed, using a gait analysis system of six infrared cameras and two force plates. Each patient performed 10 gait trials on 2 separate days. Inter-measurement agreement was assessed with the Coefficient of Multiple Correlation, while Root Mean Square Differences were used to quantify the variability of the trials. RESULTS: The majority of kinetics and kinematics showed excellent reproducibility in all patients. Joints' power seemed to be more reliable compared with joints' angle and moment. Most parameters presented greater variability in non-paretic than the paretic leg, while they were less variable in the sagittal compared with the non-sagittal planes. Less than 10 trials were sufficient to obtain excellent reproducibility for most kinematic and kinetic parameters. CONCLUSIONS: The reproducibility of movement assessment through three-dimensional gait analysis appears excellent in chronic stroke patients.

Reproducibility of gastrocnemius medialis muscle architecture during treadmill running.

The purpose of this study was to assess the reproducibility of fascicle length (FL) and pennation angle (PA) of gastrocnemius medialis (GM) muscle during running in vivo. Twelve male recreational long distance runners (mean±SD; age: 24±3 years, mass: 76±7kg) ran on a treadmill at a speed of 3.0m/s, wearing their own running shoes, for two different 10min sessions that were at least 2 days apart. For each test day 10 acceptable trials were recorded. Ankle and knee joint angle data were recorded by a Vicon 624 system with three cameras operating at 120Hz. B-mode ultrasonography was used to examine fascicle length and pennation angle of gastrocnemius medialis muscle. The ultrasound probe was firmly secured on the muscle belly using a lightweight foam fixation. The results indicated that fascicle length and pennation angle demonstrated high reproducibility values during treadmill running both for within and between test days. The root mean square scores between the repeated waveforms of pennation angle and fascicle length were small (∼2° and ∼3.5mm, respectively). However, ∼14 trials for pennation angle and ∼9 trials for fascicle length may be required in order to record accurate data from muscle architecture parameters. In conclusion, ultrasound measurements may be highly reproducible during dynamic movements such as treadmill running, provided that a proper fixation is used in order to assure the constant location and orientation of the ultrasound probe throughout the movement.

Reproducibility of fascicle length and pennation angle of gastrocnemius medialis in human gait in vivo.

The purpose of the current study was to examine the reproducibility of fascicle length and pennation angle of gastrocnemius medialis while human walking. To the best of our knowledge, this is the first study of the reproducibility of fascicle length and pennation angle of gastrocnemius medialis in vivo during human gait. Twelve males performed 10 gait trials on a treadmill, in 2 separate days. B-mode ultrasonography, with the ultrasound probe firmly adjusted in the transverse and frontal planes using a special cast, was used to measure the fascicle length and the pennation angle of the gastrocnemius medialis (GM). A Vicon 624 system with three cameras operating at 120 Hz was also used to record the ankle and knee joint angles. The results showed that measurements of fascicle length and pennation angle showed high reproducibility during the gait cycle, both within the same day and between different days. Moreover, the root mean square differences between the repeated waveforms of both variables were very small, compared with their ranges (fascicle length: RMS= approximately 3mm, range: 38-63 mm; pennation angle: RMS= approximately 1.5 degrees, range: 22-32 degrees). However, their reproducibility was lower compared to the joint angles. It was found that representative data have to be derived by a wide number of gait trials (fascicle length approximately six trials, pennation angle more than 10 trials), to assure the reliability of the fascicle length and pennation angle in human gait.

Repeatability of electromyographic waveforms during the naeryo chagi in taekwondo.

The purpose of the research was to study the repeatability of electromyographic (EMG) waveforms of major lower limb muscles during the naeryo chagi (axe kick) in taekwondo. Six male and female athletes, aged between 20 and 24 years served as volunteers. All participants were black belt holders and performed the naeryo chagi with their right leg. The electromyographic activity of rectus femoris, biceps femoris, gastrocnemius lateralis and tibialis anterior was recorded during the kick through four preamplified surface electrodes. The participants preformed 10 successive kicks to a fixed target with 1 min inter-trial interval. The electromyograms were recorded during each kick at a sampling frequency of 1000Hz. After the processing of the raw EMG data, myoelectrical activity was normalized on the time and amplitude domain. The coefficient of variation (CV), intra-class correlation coefficient (ICC) and coefficient of multiple correlation (CMC) were computed to test the repeatability of the electromyographic waveforms in each participant. The electromyographic activity during the naeryo chagi demonstrated poor repeatability. More specifically, all CVs were greater than 80%, all CMCs were lower than 0.75 and the majority of the average measure ICCs as well as all single measure ICCs were lower than 0.55. It seemed that only ensemble averages of EMG waveforms obtained from more than ten kicks may be considered as representatives of the muscle function in naeryo chagi and conclusions that have been drawn from a single trial should be reconsidered. Key pointsThe paper is the only known paper focused on the EMG repeatability of a taekwondo kick (naeryo chagi).The paper is among the few papers of repeatability dealing with the whole EMG waveforms and not with discrete EMG parameters.Repeatability was tested using all the available statistical indices.The results suggested that conclusions drawn from a single trial in EMG studies of taekwondo kicks and probably in other sports should be treated carefully.