Centre National de Rééducation Fonctionnelle et de Réadaptation – Rehazenter, Laboratoire d'Analyse du Mouvement et de la Posture(LAMP), Luxembourg, Luxembourg
Dr. Frédéric Dierick
Centre National de Rééducation Fonctionnelle et de Réadaptation – Rehazenter, Laboratoire d'Analyse du Mouvement et de la Posture(LAMP), Luxembourg, Luxembourg
Assessing the risk of fall in elderly people is a difficult challenge for clinicians. Since falls represent one of the first causes of death in such people, numerous clinical tests have been created and validated over the past 30 years to ascertain the risk of falls. More recently, the developments of low-cost motion capture sensors have facilitated observations of gait differences between fallers and nonfallers. The aim of this study is twofold. First, to design a method combining clinical tests and motion capture sensors in order to optimize the prediction of the risk of fall. Second to assess the ability of artificial intelligence to predict risk of fall from sensor raw data only. Seventy-three nursing home residents over the age of 65 underwent the Timed Up and Go (TUG) and six-minute walking tests equipped with a home-designed wearable Inertial Measurement Unit during two sets of measurements at a six-month interval. Observed falls during that interval enabled us to divide residents into two categories: fallers and nonfallers. We show that the TUG test results coupled to gait variability indicators, measured during a six-minute walking test, improve (from 68% to 76%) the accuracy of risk of fall’s prediction at six months. In addition, we show that an artificial intelligence algorithm trained on the sensor raw data of 57 participants reveals an accuracy of 75% on the remaining 16 participants.
Little is known of the performance characteristics of the shotokan karate mae-geri kick. The aim of this study was to compare the execution time, the lower limb kinetics and kinematics, and their respective repeatability in the mae-geri kick of karate athletes of two different standards. Seventeen adult black belt karate competitors (9 national and 8 international athletes) performed six kicks with their dominant lower limb on a striking surface, combining maximum force impact and velocity. Execution time of movement and lower limb kinematics were recorded with a high-speed camera. Maximum force at impact and the forces exerted on the ground were measured using three force plates. The duration of the kick was significantly shorter for international than for national standard athletes. However, no significant difference in the maximum impact force of the kick was observed between the two groups. In addition, significant kinematic differences were observed between the groups, with two angles of motion and one velocity peak occurring sooner in the kick movement for the international athletes, specifically for the knee joint. International athletes also performed the kick with a significantly higher repeatability for duration and kinematics, specifically during the pre-loading phase that precedes the attack phase. We conclude that theduration of the kick and repeatability of lower limb kinematics could be useful in selecting top-level karate athletes and monitoring their training status.
Nowadays, a classification system for unilateral stiff-knee gait (SKG) kinematic severity in hemiparetic adult patients after stroke does not exist. However, such classification would be useful to the clinicians. We proposed the use of the k-means method in order to define unilateral SKG severity clusters in hemiparetic adults after stroke. A retrospective k-means cluster analysis was applied to five selected knee kinematic parameters collected during gait in 96 hemiparetic adults and 19 healthy adults from our clinical gait analysis database. A total of five discrete knee kinematic clusters were determined. Three clusters of SKG were identified, based on which a three-level severity classification was defined: unbend-knee gait, braked-knee gait, and frozen-limb gait. Preliminary construct validity of the classification was obtained. All selected knee kinematic parameters defining the five clusters and the majority of usual kinematic parameters of the lower limbs showed statistically significant differences between the different clusters. We recommend diagnosing SKG for values strictly below 40° of knee flexion during the swing phase. Clinicians and researchers are now able to specify the level of kinematic severity of SKG in order to optimize treatment choices and future clinical trial eligibility criteria.
The Timed Up and Go test (TUG) is commonly used to estimate the fall risk in the elderly. Several ways to improve the predictive accuracy of TUG (cameras, multiple sensors, other clinical tests) have already been proposed. Here, we added a single wearable inertial measurement unit (IMU) to capture the residents’ body center-of-mass kinematics in view of improving TUG’s predictive accuracy. The aim is to find out which kinematic variables and residents’ characteristics are relevant for distinguishing faller from non-faller patients. Data were collected in 73 nursing home residents with the IMU placed on the lower back. Acceleration and angular velocity time series were analyzed during different subtasks of the TUG. Multiple logistic regressions showed that total time required, maximum angular velocity at the first half-turn, gender, and use of a walking aid were the parameters leading to the best predictive abilities of fall risk. The predictive accuracy of the proposed new test, called i + TUG, reached a value of 74.0%, with a specificity of 95.9% and a sensitivity of 29.2%. By adding a single wearable IMU to TUG, an accurate and highly specific test is therefore obtained. This method is quick, easy to perform and inexpensive. We recommend to integrate it into daily clinical practice in nursing homes.
Contrary to common belief of clinicians that hemorrhagic stroke survivors have better functional prognoses than ischemic, recent studies show that ischemic survivors could experience similar or even better functional improvements. However, the influence of stroke subtype on gait and posture outcomes following an intervention blending conventional physiotherapy with robotic-assisted gait therapy is missing. This study compared gait and posture outcome measures between ambulatory hemorrhagic patients and ischemic patients, who received a similar 4 weeks’ intervention blending a conventional bottom-up physiotherapy approach and an exoskeleton top-down robotic-assisted gait training (RAGT) approach with Lokomat. Forty adult hemiparetic stroke inpatient subjects were recruited: 20 hemorrhagic and 20 ischemic, matched by age, gender, side of hemisphere lesion, stroke severity, and locomotor impairments. Functional Ambulation Category, Postural Assessment Scale for Stroke, Tinetti Performance Oriented Mobility Assessment, 6 Minutes Walk Test, Timed Up and Go and 10-Meter Walk Test were performed before and after a 4-week long intervention. Functional gains were calculated for all tests. Hemorrhagic and ischemic subjects showed significant improvements in Functional Ambulation Category (P<0.001 and P = 0.008, respectively), Postural Assessment Scale for Stroke (P<0.001 and P = 0.003), 6 Minutes Walk Test (P = 0.003 and P = 0.015) and 10-Meter Walk Test (P = 0.001 and P = 0.024). Ischemic patients also showed significant improvements in Timed Up and Go. Significantly greater mean Functional Ambulation Category and Tinetti Performance Oriented Mobility Assessment gains were observed for hemorrhagic compared to ischemic, with large (dz = 0.81) and medium (dz = 0.66) effect sizes, respectively. Overall, both groups exhibited quasi similar functional improvements and benefits from the same type, length and frequency of blended conventional physiotherapy and RAGT protocol. The use of intensive treatment plans blending top-down physiotherapy and bottom-up robotic approaches is promising for post-stroke rehabilitation.
Nowadays, the better assessment of low back pain (LBP) is an important challenge, as it is the leading musculoskeletal condition worldwide in terms of years of disability. The objective of this study was to evaluate the relevance of various machine learning (ML) algorithms and Sample Entropy (SampEn), which assesses the complexity of motion variability in identifying the condition of low back pain. Twenty chronic low-back pain (CLBP) patients and 20 healthy non-LBP participants performed 1-min repetitive bending (flexion) and return (extension) trunk movements. Analysis was performed using the time series recorded by three inertial sensors attached to the participants. It was found that SampEn was significantly lower in CLBP patients, indicating a loss of movement complexity due to LBP. Gaussian Naive Bayes ML proved to be the best of the various tested algorithms, achieving 79% accuracy in identifying CLBP patients. Angular velocity of flexion movement was the most discriminative feature in the ML analysis. This study demonstrated that: supervised ML and a complexity assessment of trunk movement variability are useful in the identification of CLBP condition, and that simple kinematic indicators are sensitive to this condition. Therefore, ML could be progressively adopted by clinicians in the assessment of CLBP patients.