Search

Abstract Early detection of Parkinson’s disease (PD) and accurate assessment of disease progression are critical for optimizing treatment and rehabilitation. However, there is no consensus on how to effectively detect early-stage PD and classify motor symptom severity using gait analysis. This study evaluated the accuracy of machine learning models in classifying early and moderate-stages of PD based on spatiotemporal gait features at different walking speeds. A total of 178 participants were recruited, including 103 individuals with PD (61 early-stage, 42 moderate-stage) and 75 healthy controls. Participants performed a walking test on a 24-m walkway at three speeds: preferred walking speed (PWS), 20% faster (HWS), and 20% slower (LWS). Key features—walking speed at PWS, stride length at HWS, and the coefficient of variation (CV) of the stride length at LWS—achieved a classification accuracy of 78.1% using the random forest algorithm. For early PD detection, the stride length at HWS and CV of the stride length at LWS provided an accuracy of 67.3% with Naïve Bayes. Walking at PWS was the most critical feature for distinguishing early from moderate PD, with an accuracy of 69.8%. These findings suggest that assessing gait over consecutive steps under different speed conditions may improve the early detection and severity assessment of individuals with PD.

Abstract We proposed a deep learning method using a convolutional neural network on time-series (TS) images to detect and differentiate affected body parts in people with Parkinson’s disease (PD) and freezing of gait (FOG) during 360° turning tasks. The 360° turning task was performed by 90 participants (60 people with PD [30 freezers and 30 nonfreezers] and 30 age-matched older adults (controls) at their preferred speed. The position and acceleration underwent preprocessing. The analysis was expanded from temporal to visual data using TS imaging methods. According to the PD vs. controls classification, the right lower third of the lateral shank (RTIB) on the least affected side (LAS) and the right calcaneus (RHEE) on the LAS were the most relevant body segments in the position and acceleration TS images. The RHEE marker exhibited the highest accuracy in the acceleration TS images. The identified markers for the classification of freezers vs. nonfreezers vs. controls were the left lateral humeral epicondyle (LELB) on the more affected side and the left posterior superior iliac spine (LPSI). The LPSI marker in the acceleration TS images displayed the highest accuracy. This approach could be a useful supplementary tool for determining PD severity and FOG.

Abstract The heterogeneity of Parkinson’s disease (PD) presents considerable challenges for accurate diagnosis, particularly during early-stage disease, when the symptoms may be extremely subtle. This study aimed to assess the accuracy of a convolutional neural network (CNN) technique based on the 6-min walk test (6MWT) measured using wearable sensors to distinguish patients with early-stage PD (n = 78) from healthy controls (n = 50). The participants wore six sensors, and performed the 6MWT. The time-series data were converted into new images. The results revealed that the gyroscopic vertical component of the lumbar spine displayed the highest classification accuracy of 83.5%, followed by those of the thoracic spine (83.1%) and right thigh (79.5%) segment. These findings suggest that the 6MWT and CNN models may facilitate earlier diagnosis and monitoring of PD symptoms, enabling clinicians to provide timely treatment during the critical transition from normal to pathologic gait patterns.

BackgroundThe aging process is associated with a cognitive and physical declines that affects neuromotor control, memory, executive functions, and motor abilities. Previous studies have made efforts to find biomarkers, utilizing complex factors such as gait as indicators of cognitive and physical health in older adults. However, while gait involves various complex factors, such as attention and the integration of sensory input, cognitive-related motor planning and execution, and the musculoskeletal system, research on biomarkers that simultaneously considers multiple factors is scarce. This study aimed to extract gait features through stepwise regression, based on three speeds, and evaluate the accuracy of machine-learning (ML) models based on the selected features to solve classification problems caused by declines in cognitive function (Cog) and physical function (PF), and in Cog and muscle strength (MS).MethodsCognitive assessments, five times sit-to-stand, and handgrip strength were performed to evaluate the Cog, PF, and MS of 198 women aged 65 years or older. For gait assessment, all participants walked along a 19-meter straight path at three speeds [preferred walking speed (PWS), slower walking speed (SWS), and faster walking speed (FWS)]. The extracted gait features based on the three speeds were selected using stepwise regression.ResultsThe ML model accuracies were revealed as follows: 91.2% for the random forest model when using all gait features and 91.9% when using the three features (walking speed and coefficient of variation of the left double support phase at FWS and the right double support phase at SWS) selected for the Cog+PF+ and Cog–PF– classification. In addition, support vector machine showed a Cog+MS+ and Cog–MS– classification problem with 93.6% accuracy when using all gait features and two selected features (left step time at PWS and gait asymmetry at SWS).ConclusionOur study provides insights into the gait characteristics of older women with decreased Cog, PF, and MS, based on the three walking speeds and ML analysis using selected gait features, and may help improve objective classification and evaluation according to declines in Cog, PF, and MS among older women.

Abstract Background Freezing of gait (FOG) is a sensitive problem, which is caused by motor control deficits and requires greater attention during postural transitions such as turning in people with Parkinson’s disease (PD). However, the turning characteristics have not yet been extensively investigated to distinguish between people with PD with and without FOG (freezers and non-freezers) based on full-body kinematic analysis during the turning task. The objectives of this study were to identify the machine learning model that best classifies people with PD and freezers and reveal the associations between clinical characteristics and turning features based on feature selection through stepwise regression. Methods The study recruited 77 people with PD (31 freezers and 46 non-freezers) and 34 age-matched older adults. The 360° turning task was performed at the preferred speed for the inner step of the more affected limb. All experiments on the people with PD were performed in the “Off” state of medication. The full-body kinematic features during the turning task were extracted using the three-dimensional motion capture system. These features were selected via stepwise regression. Results In feature selection through stepwise regression, five and six features were identified to distinguish between people with PD and controls and between freezers and non-freezers (PD and FOG classification problem), respectively. The machine learning model accuracies revealed that the random forest (RF) model had 98.1% accuracy when using all turning features and 98.0% accuracy when using the five features selected for PD classification. In addition, RF and logistic regression showed accuracies of 79.4% when using all turning features and 72.9% when using the six selected features for FOG classification. Conclusion We suggest that our study leads to understanding of the turning characteristics of people with PD and freezers during the 360° turning task for the inner step of the more affected limb and may help improve the objective classification and clinical assessment by disease progression using turning features.

Abstract This study aimed to identify the optimal features of gait parameters to predict the fall risk level in older adults. The study included 746 older adults (age: 63–89 years). Gait tests (20 m walkway) included speed modification (slower, preferred, and faster-walking) while wearing the inertial measurement unit sensors embedded in the shoe-type data loggers on both outsoles. A metric was defined to classify the fall risks, determined based on a set of questions determining the history of falls and fear of falls. The extreme gradient boosting (XGBoost) model was built from gait features to predict the factor affecting the risk of falls. Moreover, the definition of the fall levels was classified into high- and low-risk groups. At all speeds, three gait features were identified with the XGBoost (stride length, walking speed, and stance phase) that accurately classified the fall risk levels. The model accuracy in classifying fall risk levels ranged between 67–70% with 43–53% sensitivity and 77–84% specificity. Thus, we identified the optimal gait features for accurate fall risk level classification in older adults. The XGBoost model could inspire future works on fall prevention and the fall-risk assessment potential through the gait analysis of older adults.

Background The functional movement screen (FMS)TM is a screening tool used to evaluate fundamental motor function. A score of 14 for the composite total FMS score (TFMS) is generally used as the cut-off point (≤14/21). In addition, gait analysis is used to evaluate fundamental motor function in humans. Thus, evaluating the fundamental motor function using the FMSTM test and gait analysis at various speeds can provide further understanding of any decline in gait stability. In this study, we aimed to investigate the association between gait ability and fundamental movement patterns in young adults according to the cut-off point. Methods A total of 439 participants (male: 203, female: 236) successfully completed the FMS test and a 1 min treadmill test; the participants were classified into two groups: low TFMS (≤14) and high TFMS (>14). Results The low TFMS group exhibited slower and shortened walking patterns and worsen gait variability than the high TFMS group. The coefficient of variance (CV) for the double support phase at a faster speed (male) and the stride length at a slower speed (female) were classifiers between the two groups. In addition, the low TFMS group demonstrated insufficient gait adaptation at the preferred and faster speeds based on the CV of the double support phase and gait asymmetry. Lower TFMS is associated with a decline in gait ability. Therefore, participants with a lower TFMS and poor gait ability may require intervention programs to prevent risk of future injury and to enhance motor function.

Objective The purpose of this study was to determine the effect of fatigue level and sex on the range of motions of the lower extremities and impulses during the jump-landing phase after performing bilateral fatiguing tasks.Methods In total, 41 healthy young adults volunteered for this study. Participants’ jump-landing trajectories were monitored using nine cameras, and ground reaction forces were measured using a force plate. Participants performed five maximal bilateral countermovement jumps as prefatiguing tasks. The fatiguing tasks consisted of maximal effort contractions of the knee extensor at 60°/s on a dynamometer until task failure, defined as the inability to reach 50% of the peak knee extension torque for three consecutive times. The post-task maximal bilateral jumps were immediately captured after the participants failed the fatiguing task. Participants were asked to perform this cycle again, performing the fatiguing contraction task until failure to reach 30% of the peak knee extension torque.Results and conclusion It was found that the knee joint was more extended in the post-30% fatiguing task, which was due to the reduction of the flexion angle of the hip and knee joints in response to fatigue level. The impulses for both sexes were reduced at the severe fatigue level. Fatigability altered jump-landing kinematics, jump heights and impulses in response to fatigue level. The post-30% fatiguing task elicited more fatigue than the post-50% fatiguing task.

Background Several studies have reported the association between gait and global cognitive function; however, there is no study explaining the age-specific gait characteristics of older women and association between those characteristics and global cognitive function by age-specific differences and gait speed modification. The aim of this study was to examine age-specific differences in gait characteristics and global cognitive function in older women as well as identify gait domains strongly associated with global cognitive function in older women based on gait speed modification. Methods One hundred sixty-four female participants aged 65–85 years were examined. Participants were assessed for global cognitive function through the mini-mental state examination. They also performed three trials of the overground walking test along a straight 20 m walkway. Inertial measurement unit sensors with shoe-type data loggers on both the left and right outsoles were used to measure gait characteristics. Results The pace at all speeds and the variability and phase at faster speeds were altered in women aged >75 years (all pace domain parameters, p < 0.05); variability and phase highly depended on age (all p < 0.05). Variability at slower speeds (β = −0.568 and p = 0.006) and the phase at the preferred (β = −0.471 and p = 0.005) and faster speeds (β = −0.494 and p = 0.005) were associated with global cognitive function in women aged >75 years. Discussion The variability and phase domains at faster speeds were considered to identify gait changes that accompany aging. In addition, the decreases in global cognitive function are associated with increased variability and phase domains caused by changes in gait speed in older women. Conclusion Our results are considered useful for understanding age-related gait characteristics with global cognitive function in old women.

Abstract Background When examining participants with pathologies, a shoe-type inertial measurement unit (IMU) system with sensors mounted on both the left and right outsoles may be more useful for analysis and provide better stability for the sensor positions than previous methods using a single IMU sensor or attached to the lower back and a foot. However, there have been few validity analyses of shoe-type IMU systems versus reference systems for patients with Parkinson’s disease (PD) walking continuously with a steady-state gait in a single direction. Therefore, the purpose of this study is to assess the validity of the shoe-type IMU system versus a 3D motion capture system for patients with PD during 1 min of continuous walking on a treadmill. Methods Seventeen participants with PD successfully walked on a treadmill for 1 min. The shoe-type IMU system and a motion capture system comprising nine infrared cameras were used to collect the treadmill walking data with participants moving at their own preferred speeds. All participants took anti-parkinsonian medication at least 3 h before the treadmill walk. An intraclass correlation coefficient analysis and the associated 95% confidence intervals were used to evaluate the validity of the resultant linear acceleration and spatiotemporal parameters for the IMU and motion capture systems. Results The resultant linear accelerations, cadence, left step length, right step length, left step time, and right step time showed excellent agreement between the shoe-type IMU and motion capture systems. Conclusions The shoe-type IMU system provides reliable data and can be an alternative measurement tool for objective gait analysis of patients with PD in a clinical environment.

Senior citizens have increased plasma glucose and a higher risk of diabetes-related complications than young people. However, it is difficult to diagnose and manage elderly diabetics because there is no clear symptom according to current diagnostic criteria. They also dislike the invasive blood sample test. This study aimed to classify a difference in gait and physical fitness characteristics between senior citizens with and without diabetes for a non-invasive method and propose a machine-learning-based personal home-training system for training abnormal gait motions by oneself. We used a dataset for classification with 200 over 65-year-old elders who walked a flat and straight 15 m route in 3 different walking speed conditions using an inertial measurement unit and physical fitness test. Then, questionnaires for participants were included to identify life patterns. Through results, it was found that there were abnormalities in gait and physical fitness characteristics related to balance ability and walking speed. Using a single RGB camera, the developed training system for improving abnormalities enabled us to correct the exercise posture and speed in real-time. It was discussed that there are risks and errors in the training system based on human pose estimation for future works.

This study investigated the turning characteristics of the more-affected limbs in Parkinson’s disease (PD) patients in comparison with that of a control group, and in PD patients with freezing of gait (FOG; freezers) in comparison with those without FOG (non-freezers) for 360° and 540° turning tasks at the maximum speed. A total of 12 freezers, 12 non-freezers, and 12 controls participated in this study. The PD patients showed significantly longer total durations, shorter inner and outer step lengths, and greater anterior–posterior (AP) root mean square (RMS) center of mass (COM) distances compared to those for the controls. The freezers showed significantly greater AP and medial-lateral (ML) RMS COM distances compared to those of non-freezers. The turning task toward the inner step of the more-affected side (IMA) in PD patients showed significantly greater step width, total steps, and AP and ML RMS COM distances than that toward the outer step of the more-affected side (OMA). The corresponding results for freezers revealed significantly higher total steps and shorter inner step length during the 540° turn toward the IMA than that toward the OMA. Therefore, PD patients and freezers exhibited greater turning difficulty in performing challenging turning tasks such as turning with an increased angle and speed and toward the more-affected side.

This study investigated the gait characteristics of healthy young adults using shoe-type inertial measurement units (IMU) during treadmill walking. A total of 1478 participants were tested. Principal component analyses (PCA) were conducted to determine which principal components (PCs) best defined the characteristics of healthy young adults. A non-hierarchical cluster analysis was conducted to evaluate the essential gait ability, according to the results of the PC1 score. One-way repeated analysis of variance with the Bonferroni correction was used to compare gait performances in the cluster groups. PCA outcomes indicated 76.9% variance for PC1–PC6, where PC1 (gait variability (GV): 18.5%), PC2 (pace: 17.8%), PC3 (rhythm and phase: 13.9%), and PC4 (bilateral coordination: 11.2%) were the gait-related factors. All of the pace, rhythm, GV, and variables for bilateral coordination classified the gait ability in the cluster groups. We suggest that the treadmill walking task may be reliable to evaluate the gait performances, which may provide insight into understanding the decline of gait ability. The presented results are considered meaningful for understanding the gait patterns of healthy adults and may prove useful as reference outcomes for future gait analyses.

Evaluating gait stability at slower or faster speeds and self-preferred speeds based on continuous steps may assist in determining the severity of motor symptoms in Parkinson’s disease (PD) patients. This study aimed to investigate the gait ability at imposed speed conditions in PD patients during overground walking. Overall, 74 PD patients and 52 age-matched healthy controls were recruited. Levodopa was administered to patients in the PD group, and all participants completed imposed slower, preferred, and faster speed walking tests along a straight 15-m walkway wearing shoe-type inertial measurement units. Reliability of the slower and faster conditions between the estimated and measured speeds indicated excellent agreement for PD patients and controls. PD patients demonstrated higher gait asymmetry (GA) and coefficient of variance (CV) for stride length and stance phase than the controls at slower speeds and higher CVs for phases for single support, double support, and stance. CV of the double support phase could distinguish between PD patients and controls at faster speeds. The GA and CVs of stride length and phase-related variables were associated with motor symptoms in PD patients. Speed conditions should be considered during gait analysis. Gait variability could evaluate the severity of motor symptoms in PD patients.