Video-Based Pose Estimation for Gait Analysis in Stroke Survivors during Clinical Assessments: A Proof-of-Concept Study

Recent advancements in deep learning have produced significant progress in markerless human pose estimation, making it possible to estimate human kinematics from single camera videos without the need for reflective markers and specialized labs equipped with motion capture systems. Such algorithms have the potential to enable the quantification of clinical metrics from videos recorded with a handheld camera. Here we used DeepLabCut, an open-source framework for markerless pose estimation, to fine-tune a deep network to track 5 body keypoints (hip, knee, ankle, heel, and toe) in 82 below-waist videos of 8 patients with stroke performing overground walking during clinical assessments. We trained the pose estimation model by labeling the keypoints in 2 frames per video and then trained a convolutional neural network to estimate 5 clinically relevant gait parameters (cadence, double support time, swing time, stance time, and walking speed) from the trajectory of these keypoints. These results were then compared to those obtained from a clinical system for gait analysis (GAITRite®, CIR Systems). Absolute accuracy (mean error) and precision (standard deviation of error) for swing, stance, and double support time were within 0.04 ± 0.11 s; Pearson’s correlation with the reference system was moderate for swing times (<i>r</i> = 0.4–0.66), but stronger for stance and double support time (<i>r</i> = 0.93–0.95). Cadence mean error was −0.25 steps/min ± 3.9 steps/min (<i>r</i> = 0.97), while walking speed mean error was −0.02 ± 0.11 m/s (<i>r</i> = 0.92). These preliminary results suggest that single camera videos and pose estimation models based on deep networks could be used to quantify clinically relevant gait metrics in individuals poststroke, even while using assistive devices in uncontrolled environments. Such development opens the door to applications for gait analysis both inside and outside of clinical settings, without the need of sophisticated equipment.

THE EFFECTS OF TRAINING ON DIFFERENT SURFACES, ON BALANCE AND GAIT PERFORMANCE IN STROKE HEMIPLEGIA

ABSTRACT Although many studies have focused on balance exercises for elderly or stroke patients, no comprehensive studies have investigated the use of training on different surfaces (TDS) with analysis of gait performance in elderly male stroke patients. The active properties of balance and subjective reporting of functional gait ability were used to identify the effects of TDS. Static balance (SB), dynamic balance (DB) and gait analysis was measured in 30 elderly stroke patients. The patients were divided into the TDS group (n=15) and a control group (CG, n=15). Fifteen elderly stroke patients underwent TDS five times a week for 12 weeks. The data was analyzed using repeated measures analysis of variance. Significant differences were observed between the two groups (TDS and Control): SB (p < 0.0001), DB (OSI: p < 0.0001, APSI: p < 0.001, MLSI: p < 0.004) and gait analysis (right: temporal step time: p < 0.0001, temporal cycle time: p < 0.001, temporal double support time: p < 0.0001; left: temporal step time: p < 0.0001, temporal cycle time: p < 0.0001, temporal double support time: p < 0.0001). TDS in elderly male stroke patients suggests that the characteristics of gait performance in these patients may be improved by increasing static balance, dynamic balance and gait velocity. It is hoped that the results of this trial will provide new information on the effects of TDS on balance stability and gait ability in stroke patients, through changes in stability of the lower extremities. Level III, Case-control Study.

Gait and Axial Spondyloarthritis: Comparative Gait Analysis Study Using Foot-Worn Inertial Sensors

Background Axial spondyloarthritis (axSpA) can lead to spinal mobility restrictions associated with restricted lower limb ranges of motion, thoracic kyphosis, spinopelvic ankylosis, or decrease in muscle strength. It is well known that these factors can have consequences on spatiotemporal gait parameters during walking. However, no study has assessed spatiotemporal gait parameters in patients with axSpA. Divergent results have been obtained in the studies assessing spatiotemporal gait parameters in ankylosing spondylitis, a subgroup of axSpA, which could be partly explained by self-reported pain intensity scores at time of assessment. Inertial measurement units (IMUs) are increasingly popular and may facilitate gait assessment in clinical practice. Objective This study compared spatiotemporal gait parameters assessed with foot-worn IMUs in patients with axSpA and matched healthy individuals without and with pain intensity score as a covariate. Methods A total of 30 patients with axSpA and 30 age- and sex-matched healthy controls performed a 10-m walk test at comfortable speed. Various spatiotemporal gait parameters were computed from foot-worn inertial sensors including gait speed in ms–1 (mean walking velocity), cadence in steps/minute (number of steps in a minute), stride length in m (distance between 2 consecutive footprints of the same foot on the ground), swing time in percentage (portion of the cycle during which the foot is in the air), stance time in percentage (portion of the cycle during which part of the foot touches the ground), and double support time in percentage (portion of the cycle where both feet touch the ground). Results Age, height, and weight were not significantly different between groups. Self-reported pain intensity was significantly higher in patients with axSpA than healthy controls (P<.001). Independent sample t tests indicated that patients with axSpA presented lower gait speed (P<.001) and cadence (P=.004), shorter stride length (P<.001) and swing time (P<.001), and longer double support time (P<.001) and stance time (P<.001) than healthy controls. When using pain intensity as a covariate, spatiotemporal gait parameters were still significant with patients with axSpA exhibiting lower gait speed (P<.001), shorter stride length (P=.001) and swing time (P<.001), and longer double support time (P<.001) and stance time (P<.001) than matched healthy controls. Interestingly, there were no longer statistically significant between-group differences observed for the cadence (P=.17). Conclusions Gait was significantly altered in patients with axSpA with reduced speed, cadence, stride length, and swing time and increased double support and stance time. Taken together, these changes in spatiotemporal gait parameters could be interpreted as the adoption of a so-called cautious gait pattern in patients with axSpA. Among factors that may influence gait in patients with axSpA, patient self-reported pain intensity could play a role. Finally, IMUs allowed computation of spatiotemporal gait parameters and are usable to assess gait in patients with axSpA in clinical routine. Trial Registration ClinicalTrials.gov NCT03761212; https://clinicaltrials.gov/ct2/show/NCT03761212 International Registered Report Identifier (IRRID) RR2-10.1007/s00296-019-04396-4

Assessment of gait in patients with fibromyalgia during motor and cognitive dual task walking: a cross-sectional study

Background The aim of the study was to assess gait pattern of patients diagnosed with fibromyalgia (FM) while performing demanding motor and/or cognitive dual tasks while walking. Further, idea was to explore possible correlations of dual task gait pattern alterations to patients’ functional status and presence or absence of clinical symptoms associated with FM. Methods Twenty-four female FM patients and 24 healthy female subjects performed a basic walking task, a dual motor, a dual mental (cognitive) and a combined, dual motor and cognitive task simultaneously. Quantitative spatial (stride length) and temporal (cycle time, swing time and double support time) gait parameters were measured using GAITRite walkway system and their variability was assessed. Patients underwent clinical examination including assessment of functional status, pain and fatigue level, psychiatric and cognitive manifestations. Results The motor, cognitive and combined dual tasks affect gait performance in FM patients. Difference in tasks between FM and healthy subjects was found as double support time prolongation. Comparison of tasks showing that cycle time in FM was longer than controls and stride length was shorter in patients for all conditions, while no changes were found in any of the gait parameters variability. Further, mental/cognitive dual tasks had a larger effect than motor tasks. Correlations were also found between depression and functional status of the patients and the gait parameters. Conclusions Gait is affected in FM patients while dual task walking. No changes in stride-to-stride variability point that patients preserve stability in complex walking situations. Analysis of gait may provide additional information for the FM identification based on presence of clinical features and cognitive status. Correlation of dual task gait alterations with occurrence of clinical symptoms and influence of cognitive changes on gait pattern could additionally define FM subgroups.

Music-based therapy in rehabilitation of people with multiple sclerosis: a systematic review of clinical trials

Background: Multiple sclerosis (MS) is a major cause of chronic neurological disability in young adults. An increasing number of controlled studies have assessed the potential rehabilitative effects of new drug-free treatments, complementary to the standard care, including music-based therapy (MBT). Objective: To analyze the evidence for the effectiveness of MBT within the therapeutic approaches to individuals diagnosed with MS. Methods: A systematic review of clinical trials was performed with searches in the following databases: BIOSIS, CINAHL, Cochrane, EBSCO, ERIC, Google Scholar, IBECS, LILACS, LISA (ProQuest), Medline, PEDro, PsycINFO (APA), Psychological & Behavioral, PubMed, SciELO, Scopus, SPORTDiscus and Web of Science. Clinical trials comparing MBT versus conventional therapy/no intervention were included. Results: From the 282 studies identified, 10 trials were selected. Among these, the total sample consisted of 429 individuals: 253 were allocated to the experimental group (MBT) and 176 to the control group (conventional therapies or no intervention). All the studies presented high methodological quality. Modalities of MBT were clustered into four groups: (1) Rhythmic auditory; (2) Playing musical instruments; (3) Dance strategy; and (4) Neurological music therapy. Overall, the studies consistently showed that MBT was better than conventional therapy or no intervention, with regard to gait parameters (double support time and walking speed), fatigue level, fatigability, coordination, dexterity, balance, walking endurance, lower extremity functional strength, emotional status and pain. Regarding mental fatigability and memory, the data were conflicting and the evidence was unclear. Conclusion: MBT is a safe and effective approach for clinical rehabilitation of MS patients that leads to positive results regarding both motor and non-motor functions.

Physiological and Cognitive Determinants of Dual-Task Costs for Gait Parameters: The Yishun Study

Background: Studies indicate that physiological and cognitive aging are causally related and functionally interdependent. However, the relative contribution of physiological factors and cognition to dual-task costs (DTC) of gait parameters has not been well studied. In this cross-sectional study, we examined the trajectory of DTC of gait parameters across the adult age spectrum for both sexes and identified the contributions of physical and cognitive performance to DTC of gait. Methods: A total of 492 community-dwelling adults, aged 21–90 years, were randomly recruited into the study. Participants were divided into 7 age groups, with 10-year age range for each group. Demographic data, height, body mass, education level, and information on comorbidities were recorded. Cognition was measured using the Repeatable Battery for the Assessment of Neuropsychological Status. Physical performance included visual contrast sensitivity, postural sway, hand reaction time, handgrip strength, knee extensor strength, and single-task and dual-task gait assessments. Stepwise multivariable regression was used to examine the association between physical and cognitive performance with DTC of gait parameters. Results: Women were found to have significantly higher DTC of gait speed (p = 0.01), cadence (p < 0.01), and double support time (p < 0.01) than men. However, significant aging effect on DTC of gait speed (p = 0.01), step length (p = 0.01), and double support time (p = 0.01) was observed in men but not in women. Immediate memory was the primary determinant for the DTC of gait speed (β = −0.25, p < 0.01), step length (β = −0.22, p < 0.01), and cadence (β = −0.15, p = 0.03) in men. Besides immediate memory, postural sway (β = −0.13, p = 0.03) and hand reaction (β = 0.14, p = 0.02) were also significantly associated with DTC of step length and cadence, respectively, in women. Conclusion: There were sex differences in the amplitude and trajectories of DTC of gait parameters. The DTC increased with age in men but not in women. Immediate memory was the primary determinant of DTC of gait parameters in men while immediate memory, postural sway, and reaction time were associated with DTC of gait in women. Future studies should investigate the clinical implications of the sex differences in the DTC with fall risks.

Analysis of Gait for Disease Stage in Patients with Parkinson’s Disease

Understanding the motor patterns underlying the movement of individuals with Parkinson’s disease (PD) is fundamental to the effective targeting of non-pharmacological therapies. This study aimed to analyze the gait pattern in relation to the evolutionary stages I–II and III–IV according to the Hoehn and Yahr (H&Y) scale in individuals affected by PD. The study was conducted with the participation of 37 PD patients with a mean age of 70.09 ± 9.53 years, and of whom 48.64% were women. The inclusion criteria were (1) to be diagnosed with PD; (2) to be in an evolutionary stage of the disease between I and IV: and (3) to be able to walk independently and without any assistance. Kinematic and spatial-temporal parameters of the gait were analyzed. The results showed differences in speed of movement, cadence, stride length, support duration, swing duration, step width, walking cycle duration, and double support time between the stages analyzed. These results confirmed the differences in PD gait pattern between stages I–II and III–IV. Different behaviors of the same variable were recorded depending on whether the right or left side was affected by PD.

Age-related changes in postural control in older women: transitional tasks in step initiation

Background: Aging, being a natural process, involves many functional and structural changes within the body. Identifying the age-related postural changes will provide insight into the role of aging on postural control during locomotion. The aim of this study was to identify age-related postural changes during a transitional task under different conditions.Methods: Sixty healthy females divided into three age groups: A (50-60 y/o), B (60-70 y/o), and C (70-80 y/o). The transitional task was measured by two force platforms. The procedure consisted of three phases: quiet standing, transfer onto a second platform, and quiet standing on the second platform. Four different conditions were applied: unperturbed transfer, obstacle crossing, step-up, and step-down. Double-support time, transit time, and stability time before and after the step task were analyzed.Results: The transit time was longer by 30% for subjects over 70 y/o. The double-support time was longer by 11% among adults 60-70 y/o, while in people over 70 y/o it was longer by almost 50% compared to the 50-60 y/o subjects. The stability time before the transitional task was longer by 17% among adults over 60 y/o compared to middle-age subjects. The stability times before and after the transitional task were longer for adults in the 50-60 y/o category. Conclusion: The proposed procedure is adequate for assessing age-related changes in postural control while undergoing a transitional task. An analysis of the double-support time and stability time before and after the step task enabled the detection of early signs of balance changes in middle-age adults. Independent of age, the transitional task parameters changed with the increasing difficulty of the tasks.

Age-related changes in postural control in older women: transitional tasks in step initiation

Background Aging, being a natural process, involves many functional and structural changes within the body. Identifying the age-related postural changes will provide insight into the role of aging on postural control during locomotion. The aim of this study was to identify age-related postural changes during a transitional task under different conditions. Methods Sixty healthy females divided into three age groups: A (50-60 y/o), B (60-70 y/o), and C (70-80 y/o). The transitional task was measured by two force platforms. The procedure consisted of three phases: quiet standing, transfer onto a second platform, and quiet standing on the second platform. Four different conditions were applied: unperturbed transfer, obstacle crossing, step-up, and step-down. Double-support time, transit time, and stability time before and after the step task were analyzed. Results The transit time was longer by 30% for subjects over 70 y/o. The double-support time was longer by 11% among adults 60-70 y/o, while in people over 70 y/o it was longer by almost 50% compared to the 50-60 y/o subjects. The stability time before the transitional task was longer by 17% among adults over 60 y/o compared to middle-age subjects. The stability times before and after the transitional task were longer for adults in the 50-60 y/o category. Conclusion The proposed procedure is adequate for assessing age-related changes in postural control while undergoing a transitional task. An analysis of the double-support time and stability time before and after the step task enabled the detection of early signs of balance changes in middle-age adults. Independent of age, the transitional task parameters changed with the increasing difficulty of the tasks.

Analysis for Disease Stages of Gait in Patients with Parkinson´s Disease

Understanding the motor patterns underlying the movement of people with Parkinson's disease (PD) is fundamental to the effective targeting of non-pharmacological therapies. This study aims to analyze the gait pattern in relation to the evolutionary stage between I-II and III-IV according to the Hoehn and Yahr scale (H&amp;amp;Y) in people affected by PD. The study was conducted with the participation of 37 PD patients, with a mean age of 70.09&plusmn;9.53 years, and of whom 48.64% were women. The inclusion criteria were: 1. To be diagnosed with PD; 2. To be in an evolutionary stage of the disease of between I and IV and; 3. To be able to walk independently and without any assistance. Kinematic and spatial-temporal parameters of the gait were analyzed. The results show differences in speed of movement, cadence, stride length, support duration, swing duration, step width, walking cycle duration and double support time between the stages analyzed. These results confirm the differences in PD gait pattern between stages I-II and III-IV. Different behaviors of the same variable were recorded depending on whether the right or left sides were affected by PD.