Search

The aim of this study was to determine which supervised machine learning (ML) algorithm can most accurately classify people with Parkinson's disease (pwPD) from speed-matched healthy subjects (HS) based on a selected minimum set of IMU-derived gait features. Twenty-two gait features were extrapolated from the trunk acceleration patterns of 81 pwPD and 80 HS, including spatiotemporal, pelvic kinematics, and acceleration-derived gait stability indexes. After a three-level feature selection procedure, seven gait features were considered for implementing five ML algorithms: support vector machine (SVM), artificial neural network, decision trees (DT), random forest (RF), and K-nearest neighbors. Accuracy, precision, recall, and F1 score were calculated. SVM, DT, and RF showed the best classification performances, with prediction accuracy higher than 80% on the test set. The conceptual model of approaching ML that we proposed could reduce the risk of overrepresenting multicollinear gait features in the model, reducing the risk of overfitting in the test performances while fostering the explainability of the results.

The interpretability of gait analysis studies in people with rare diseases, such as those with primary hereditary cerebellar ataxia (pwCA), is frequently limited by the small sample sizes and unbalanced datasets. The purpose of this study was to assess the effectiveness of data balancing and generative artificial intelligence (AI) algorithms in generating synthetic data reflecting the actual gait abnormalities of pwCA. Gait data of 30 pwCA (age: 51.6 ± 12.2 years; 13 females, 17 males) and 100 healthy subjects (age: 57.1 ± 10.4; 60 females, 40 males) were collected at the lumbar level with an inertial measurement unit. Subsampling, oversampling, synthetic minority oversampling, generative adversarial networks, and conditional tabular generative adversarial networks (ctGAN) were applied to generate datasets to be input to a random forest classifier. Consistency and explainability metrics were also calculated to assess the coherence of the generated dataset with known gait abnormalities of pwCA. ctGAN significantly improved the classification performance compared with the original dataset and traditional data augmentation methods. ctGAN are effective methods for balancing tabular datasets from populations with rare diseases, owing to their ability to improve diagnostic models with consistent explainability. [ABSTRACT FROM AUTHOR]

Introduction: The progressive modular rebalancing (PMR) system is a comprehensive rehabilitation approach derived from proprioceptive neuromuscular facilitation principles. PMR training encourages focus on trunk and proximal muscle function through direct perception, strength, and stretching exercises and emphasizes bi-articular muscle function in the improvement of gait performance. Sensory cueing, such as visual cues (VC), is one of the more established techniques for gait rehabilitation in PD. In this study, we propose PMR combined with VC for improving gait performance, balance, and trunk control during gait in patients with PD. Our assumption herein was that the effect of VC may add to improved motor performance induced by the PMR treatment. The primary aim of this study was to evaluate whether the PMR system plus VC was a more effective treatment option than standard physiotherapy in improving gait function in patients with PD. The secondary aim of the study was to evaluate the effect of this treatment on motor function severity. Design: Two-center, randomized, controlled, observer-blind, crossover study with a 4-month washout period. Participants: Forty individuals with idiopathic PD in Hoehn and Yahr stages 1–4. Intervention: Eight-week rehabilitation programs consisting of PMR plus VC (treatment A) and conventional physiotherapy (treatment B). Primary outcome measures: Spatiotemporal gait parameters, joint kinematics, and trunk kinematics. Secondary outcome measures: UPDRS-III scale scores. Results: The rehabilitation program was well-tolerated by individuals with PD and most participants showed improvements in gait variables and UPDRS-III scores with both treatments. However, patients who received PMR with VC showed better results in gait function with regard to gait performance (increased step length, gait speed, and joint kinematics), gait balance (increased step width and double support duration), and trunk control (increased trunk motion) than those receiving conventional physiotherapy. While crossover results revealed some differences in primary outcomes, only 37.5% of patients crossed over between the groups. As a result, our findings should be interpreted cautiously. Conclusions: The PMR plus VC program could be used to improve gait function and severity motor of motor deficit in individuals with PD. Clinical Trial Registration : www.ClinicalTrials.gov, identifier NCT03346265. [ABSTRACT FROM AUTHOR]

Background: Gait disorders represent one of the most disabling features of Parkinson's disease, which may benefit from rehabilitation. No consistent evidence exists about which gait biomechanical factors can be modified by rehabilitation and which clinical characteristic can predict rehabilitation-induced improvements. Objectives: The aims of the study were as follows: (i) to recognize the gait parameters modifiable by a short-term rehabilitation program; (ii) to evaluate the gait parameters that can normalize after rehabilitation; and (iii) to identify clinical variables predicting improvements in gait function after rehabilitation. Methods: Thirty-six patients affected by idiopathic Parkinson's disease in Hoehn-Yahr stage 1–3 and 22 healthy controls were included in the study. Both clinical and instrumental (gait analysis) evaluations were performed before and after a 10-weeks rehabilitation treatment. Time-distance parameters, lower limb joint, and trunk kinematics were measured. Results: At baseline evaluation with matched speed, almost all gait parameters were significantly different between patients and healthy controls. After the 10-weeks rehabilitation, most gait parameters improved, and spatial asymmetry and trunk rotation normalized. Multiple linear regression of gender combined with Unified Parkinson's Disease Rating Scale-III predicted both ΔSpeed and ΔStep length of both sides; gender combined with Unified Parkinson's Disease Rating Scale-II predicted ΔCadence; age combined with Hoehn-Yahr score and disease duration predicted Δtrunk rotation range of motion. Conclusions: Impaired gait parameters are susceptible to improvement by rehabilitation, and younger men with Parkinson's disease who are less severely affected and at early disease stage are more susceptible to improvements in gait function after a 10-weeks rehabilitation program. [ABSTRACT FROM AUTHOR]

Background. Patients suffering from cerebellar ataxia have extremely variable gait kinematic features. We investigated whether and how wearable inertial sensors can describe the gait kinematic features among ataxic patients. Methods. We enrolled 17 patients and 16 matched control subjects. We acquired data by means of an inertial sensor attached to an ergonomic belt around pelvis, which was connected to a portable computer via Bluetooth. Recordings of all the patients were obtained during overground walking. From the accelerometric data, we obtained the harmonic ratio (HR), i.e., a measure of the acceleration patterns, smoothness and rhythm, and the step length coefficient of variation (CV), which evaluates the variability of the gait cycle. Results. Compared to controls, patients had a lower HR, meaning a less harmonic and rhythmic acceleration pattern of the trunk, and a higher step length CV, indicating a more variable step length. Both HR and step length CV showed a high effect size in distinguishing patients and controls (p < 0.001 and p = 0.011, respectively). A positive correlation was found between the step length CV and both the number of falls (R = 0.672; p = 0.003) and the clinical severity (ICARS: R = 0.494; p = 0.044; SARA: R = 0.680; p = 0.003). Conclusion. These findings demonstrate that the use of inertial sensors is effective in evaluating gait and balance impairment among ataxic patients. [ABSTRACT FROM AUTHOR]

Total hip replacement with minimally invasive direct anterior approach using the "Smith Petersen" interval is an alternative technique to conventional surgery aimed at preserving the integrity of the muscles around the hip joint. This study aimed to observe hip biomechanics, gait variables, hip muscle activation and locomotor performance during three locomotor tasks (forward, lateral, and backward walking), in subjects who undergo total hip arthroplasty with direct anterior approach. Fourteen patients with primary osteoarthritis who underwent direct anterior approach were included in the study. The optoelectronic 3-D motion analysis system integrated with an electromyography surface device was used to acquire the biomechanics of patients before surgery and at 3 and 6 months post-surgery. Spatio-temporal, dynamic, and hip muscle electromyographic parameters were analyzed and compared whit those of healthy controls. Almost all gait parameters improved after surgery. The majority of gait variables neared to the control group at 6 months, while the hip joint range of motion did not. The abnormally increased activation of the muscles around the hip joint was reduced at 6 months post-surgery during all three locomotor tasks. Conversely, the altered gait phase-related electromyographic pattern did not change after the surgery. Our results indicate that hip and gait function during several locomotor tasks improved after surgery, while simultaneously either preserve or restore the muscle activation around the hip joint. A full biomechanical evaluation of the hip function during locomotion may aid physicians and surgeons in optimizing the management of patients before and after hip replacement surgery. • Patients after hip replacement obtain a series of gait function improvements. • The majority of gait variables normalized in patients at 6 months post-surgery. • The surgery reduce the hyperactivation of the hip muscles around the hip joint. [ABSTRACT FROM AUTHOR]