Computation of Gait Parameters in Post Stroke and Parkinson's Disease: A Comparative Study Using RGB-D Sensors and Optoelectronic Systems

Deep Learning for hand tracking in Parkinson's Disease video-based assessment: Current and future perspectives

BACKGROUND

Parkinson's Disease (PD) demands early diagnosis and frequent assessment of symptoms. In particular, analysing hand movements is pivotal to understand disease progression. Advancements in hand tracking using Deep Learning (DL) allow for the automatic and objective disease evaluation from video recordings of standardised motor tasks, which are the foundation of neurological examinations. In view of this scenario, this narrative review aims to describe the state of the art and the future perspective of DL frameworks for hand tracking in video-based PD assessment.

METHODS

A rigorous search of PubMed, Web of Science, IEEE Explorer, and Scopus until October 2023 using primary keywords such as parkinson, hand tracking, and deep learning was performed to select eligible by focusing on video-based PD assessment through DL-driven hand tracking frameworks RESULTS:: After accurate screening, 23 publications met the selection criteria. These studies used various solutions, from well-established pose estimation frameworks, like OpenPose and MediaPipe, to custom deep architectures designed to accurately track hand and finger movements and extract relevant disease features. Estimated hand tracking data were then used to differentiate PD patients from healthy individuals, characterise symptoms such as tremors and bradykinesia, or regress the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) by automatically assessing clinical tasks such as finger tapping, hand movements, and pronation-supination.

CONCLUSIONS

DL-driven hand tracking holds promise for PD assessment, offering precise, objective measurements for early diagnosis and monitoring, especially in a telemedicine scenario. However, to ensure clinical acceptance, standardisation and validation are crucial. Future research should prioritise large open datasets, rigorous validation on patients, and the investigation of new frontiers such as tracking hand-hand and hand-object interactions for daily-life tasks assessment.

Development of a Low-Cost Markerless Optical Motion Capture System for Gait Analysis and Anthropometric Parameter Quantification

Technological advancements have expanded the range of methods for capturing human body motion, including solutions involving inertial sensors (IMUs) and optical alternatives. However, the rising complexity and costs associated with commercial solutions have prompted the exploration of more cost-effective alternatives. This paper presents a markerless optical motion capture system using a RealSense depth camera and intelligent computer vision algorithms. It facilitates precise posture assessment, the real-time calculation of joint angles, and acquisition of subject-specific anthropometric data for gait analysis. The proposed system stands out for its simplicity and affordability in comparison to complex commercial solutions. The gathered data are stored in comma-separated value (CSV) files, simplifying subsequent analysis and data mining. Preliminary tests, conducted in controlled laboratory environments and employing a commercial MEMS-IMU system as a reference, revealed a maximum relative error of 7.6% in anthropometric measurements, with a maximum absolute error of 4.67 cm at average height. Stride length measurements showed a maximum relative error of 11.2%. Static joint angle tests had a maximum average error of 10.2%, while dynamic joint angle tests showed a maximum average error of 9.06%. The proposed optical system offers sufficient accuracy for potential application in areas such as rehabilitation, sports analysis, and entertainment.

Dynamic Stability, Symmetry, and Smoothness of Gait in People with Neurological Health Conditions

Neurological disorders such as stroke, Parkinson's disease (PD), and severe traumatic brain injury (sTBI) are leading global causes of disability and mortality. This study aimed to assess the ability to walk of patients with sTBI, stroke, and PD, identifying the differences in dynamic postural stability, symmetry, and smoothness during various dynamic motor tasks. Sixty people with neurological disorders and 20 healthy participants were recruited. Inertial measurement unit (IMU) sensors were employed to measure spatiotemporal parameters and gait quality indices during different motor tasks. The Mini-BESTest, Berg Balance Scale, and Dynamic Gait Index Scoring were also used to evaluate balance and gait. People with stroke exhibited the most compromised biomechanical patterns, with lower walking speed, increased stride duration, and decreased stride frequency. They also showed higher upper body instability and greater variability in gait stability indices, as well as less gait symmetry and smoothness. PD and sTBI patients displayed significantly different temporal parameters and differences in stability parameters only at the pelvis level and in the smoothness index during both linear and curved paths. This study provides a biomechanical characterization of dynamic stability, symmetry, and smoothness in people with stroke, sTBI, and PD using an IMU-based ecological assessment.

Exergames as a rehabilitation tool to enhance the upper limbs functionality and performance in chronic stroke survivors: a preliminary study

Introduction

Post-stroke hemiplegia commonly occurs in stroke survivors, negatively impacting the quality of life. Despite the benefits of initial specific post-acute treatments at the hospitals, motor functions, and physical mobility need to be constantly stimulated to avoid regression and subsequent hospitalizations for further rehabilitation treatments.

Method

This preliminary study proposes using gamified tasks in a virtual environment to stimulate and maintain upper limb mobility through a single RGB-D camera-based vision system (using Microsoft Azure Kinect DK). This solution is suitable for easy deployment and use in home environments. A cohort of 10 post-stroke subjects attended a 2-week gaming protocol consisting of Lateral Weightlifting (LWL) and Frontal Weightlifting (FWL) gamified tasks and gait as the instrumental evaluation task.

Results and discussion

Despite its short duration, there were statistically significant results (p < 0.05) between the baseline (T0) and the end of the protocol (TF) for Berg Balance Scale and Time Up-and-Go (9.8 and -12.3%, respectively). LWL and FWL showed significant results for unilateral executions: rate in FWL had an overall improvement of 38.5% (p < 0.001) and 34.9% (p < 0.01) for the paretic and non-paretic arm, respectively; similarly, rate in LWL improved by 19.9% (p < 0.05) for the paretic arm and 29.9% (p < 0.01) for non-paretic arm. Instead, bilateral executions had significant results for rate and speed: considering FWL, there was an improvement in rate with p < 0.01 (31.7% for paretic arm and 37.4% for non-paretic arm), whereas speed improved by 31.2% (p < 0.05) and 41.7% (p < 0.001) for the paretic and non-paretic arm, respectively; likewise, LWL showed improvement in rate with p < 0.001 (29.0% for paretic arm and 27.8% for non-paretic arm) and in speed with 23.6% (p < 0.05) and 23.5% (p < 0.01) for the paretic and non-paretic arms, respectively. No significant results were recorded for gait task, although an overall good improvement was detected for arm swing asymmetry (-22.6%). Hence, this study suggests the potential benefits of continuous stimulation of upper limb function through gamified exercises and performance monitoring over medium-long periods in the home environment, thus facilitating the patient's general mobility in daily activities.

Integrating Abnormal Gait Detection with Activities of Daily Living Monitoring in Ambient Assisted Living: A 3D Vision Approach

Gait analysis plays a crucial role in detecting and monitoring various neurological and musculoskeletal disorders early. This paper presents a comprehensive study of the automatic detection of abnormal gait using 3D vision, with a focus on non-invasive and practical data acquisition methods suitable for everyday environments. We explore various configurations, including multi-camera setups placed at different distances and angles, as well as performing daily activities in different directions. An integral component of our study involves combining gait analysis with the monitoring of activities of daily living (ADLs), given the paramount relevance of this integration in the context of Ambient Assisted Living. To achieve this, we investigate cutting-edge Deep Neural Network approaches, such as the Temporal Convolutional Network, Gated Recurrent Unit, and Long Short-Term Memory Autoencoder. Additionally, we scrutinize different data representation formats, including Euclidean-based representations, angular adjacency matrices, and rotation matrices. Our system's performance evaluation leverages both publicly available datasets and data we collected ourselves while accounting for individual variations and environmental factors. The results underscore the effectiveness of our proposed configurations in accurately classifying abnormal gait, thus shedding light on the optimal setup for non-invasive and efficient data collection.

Agreement between Optoelectronic System and Wearable Sensors for the Evaluation of Gait Spatiotemporal Parameters in Progressive Supranuclear Palsy

The use of wearable sensors for calculating gait parameters has become increasingly popular as an alternative to optoelectronic systems, currently recognized as the gold standard. The objective of the study was to evaluate the agreement between the wearable Opal system and the optoelectronic BTS SMART DX system for assessing spatiotemporal gait parameters. Fifteen subjects with progressive supranuclear palsy walked at their self-selected speed on a straight path, and six spatiotemporal parameters were compared between the two measurement systems. The agreement was carried out through paired data test, Passing Bablok regression, and Bland-Altman Analysis. The results showed a perfect agreement for speed, a very close agreement for cadence and cycle duration, while, in the other cases, Opal system either under- or over-estimated the measurement of the BTS system. Some suggestions about these misalignments are proposed in the paper, considering that Opal system is widely used in the clinical context.

Cervical Range of Motion Assessment through Inertial Technology: A Validity and Reliability Study

Inertial technology has spread widely for its comfortable use and adaptability to various motor tasks. The main objective of this study was to assess the validity of inertial measurements of the cervical spine range of motion (CROM) when compared to that of the optoelectronic system in a group of healthy individuals. A further aim of this study was to determine the optimal placement of the inertial sensor in terms of reliability of the measure, comparing measurements obtained from the same device placed at the second cervical vertebra (C2), the forehead (F) and the external occipital protuberance (EOP). Twenty healthy subjects were recruited and asked to perform flexion-extension, lateral bending, and axial rotation movements of the head. Outcome measurements of interest were CROM and mean angular velocities for each cervical movement. Results showed that inertial measurements have good reliability (0.75 < ICC < 0.9). Excellent reliability (ICC > 0.9) was found in both flexion and right lateral bending angles. All parameters extracted with EOP placement showed ICC > 0.62, while ICC < 0.5 was found in lateral bending mean angular velocities both for F and C2 placements. Therefore, the optimal sensor's positioning emerged to be EOP. These results suggest that inertial technology could be useful and reliable for the evaluation of the CROM.

A Digital Architecture for the Real-Time Tracking of Wearing off Phenomenon in Parkinson's Disease

Levodopa administration is currently the most common treatment to alleviate Parkinson's Disease (PD) symptoms. Nevertheless, prolonged use of Levodopa leads to a wearing-off (WO) phenomenon, causing symptoms to reappear. To build a personalized treatment plan aiming to manage PD and its symptoms effectively, there is a need for a technological system able to continuously and objectively assess the WO phenomenon during daily life. In this context, this paper proposes a WO tracker able to exploit neuromuscular data acquired by a dedicated wireless sensor network to discriminate between a Levodopa benefit phase and the reappearance of symptoms. The proposed architecture has been implemented on a heterogeneous computing platform, that statistically analyzes neural and muscular features to identify the best set of features to train the classifier model. Eight models among shallow and deep learning approaches are analyzed in terms of performance, timing and complexity metrics to identify the best inference engine. Experimental results on five subjects experiencing WO, showed that, in the best case, the proposed WO tracker can achieve an accuracy of ~84%, providing the inference in less than 41 ms. It is possible by employing a simple fully-connected neural network with 1 hidden layer and 32 units.

Usability of the REHOME Solution for the Telerehabilitation in Neurological Diseases: Preliminary Results on Motor and Cognitive Platforms

The progressive aging of the population and the consequent growth of individuals with neurological diseases and related chronic disabilities, will lead to a general increase in the costs and resources needed to ensure treatment and care services. In this scenario, telemedicine and e-health solutions, including remote monitoring and rehabilitation, are attracting increasing interest as tools to ensure the sustainability of the healthcare system or, at least, to support the burden for health care facilities. Technological advances in recent decades have fostered the development of dedicated and innovative Information and Communication Technology (ICT) based solutions, with the aim of complementing traditional care and treatment services through telemedicine applications that support new patient and disease management strategies. This is the background for the REHOME project, whose technological solution, presented in this paper, integrates innovative methodologies and devices for remote monitoring and rehabilitation of cognitive, motor, and sleep disorders associated with neurological diseases. One of the primary goals of the project is to meet the needs of patients and clinicians, by ensuring continuity of treatment from healthcare facilities to the patient's home. To this end, it is important to ensure the usability of the solution by elderly and pathological individuals. Preliminary results of usability and user experience questionnaires on 70 subjects recruited in three experimental trials are presented here.

Assessment Tasks and Virtual Exergames for Remote Monitoring of Parkinson's Disease: An Integrated Approach Based on Azure Kinect

Motor impairments are among the most relevant, evident, and disabling symptoms of Parkinson’s disease that adversely affect quality of life, resulting in limited autonomy, independence, and safety. Recent studies have demonstrated the benefits of physiotherapy and rehabilitation programs specifically targeted to the needs of Parkinsonian patients in supporting drug treatments and improving motor control and coordination. However, due to the expected increase in patients in the coming years, traditional rehabilitation pathways in healthcare facilities could become unsustainable. Consequently, new strategies are needed, in which technologies play a key role in enabling more frequent, comprehensive, and out-of-hospital follow-up. The paper proposes a vision-based solution using the new Azure Kinect DK sensor to implement an integrated approach for remote assessment, monitoring, and rehabilitation of Parkinsonian patients, exploiting non-invasive 3D tracking of body movements to objectively and automatically characterize both standard evaluative motor tasks and virtual exergames. An experimental test involving 20 parkinsonian subjects and 15 healthy controls was organized. Preliminary results show the system’s ability to quantify specific and statistically significant (p < 0.05) features of motor performance, easily monitor changes as the disease progresses over time, and at the same time permit the use of exergames in virtual reality both for training and as a support for motor condition assessment (for example, detecting an average reduction in arm swing asymmetry of about 14% after arm training). The main innovation relies precisely on the integration of evaluative and rehabilitative aspects, which could be used as a closed loop to design new protocols for remote management of patients tailored to their actual conditions.

Computer Vision and Machine Learning-Based Gait Pattern Recognition for Flat Fall Prediction

BACKGROUND

Gait recognition has been applied in the prediction of the probability of elderly flat ground fall, functional evaluation during rehabilitation, and the training of patients with lower extremity motor dysfunction. Gait distinguishing between seemingly similar kinematic patterns associated with different pathological entities is a challenge for the clinician. How to realize automatic identification and judgment of abnormal gait is a significant challenge in clinical practice. The long-term goal of our study is to develop a gait recognition computer vision system using artificial intelligence (AI) and machine learning (ML) computing. This study aims to find an optimal ML algorithm using computer vision techniques and measure variables from lower limbs to classify gait patterns in healthy people. The purpose of this study is to determine the feasibility of computer vision and machine learning (ML) computing in discriminating different gait patterns associated with flat-ground falls.

METHODS

We used the Kinect^® Motion system to capture the spatiotemporal gait data from seven healthy subjects in three walking trials, including normal gait, pelvic-obliquity-gait, and knee-hyperextension-gait walking. Four different classification methods including convolutional neural network (CNN), support vector machine (SVM), K-nearest neighbors (KNN), and long short-term memory (LSTM) neural networks were used to automatically classify three gait patterns. Overall, 750 sets of data were collected, and the dataset was divided into 80% for algorithm training and 20% for evaluation.

RESULTS

The SVM and KNN had a higher accuracy than CNN and LSTM. The SVM (94.9 ± 3.36%) had the highest accuracy in the classification of gait patterns, followed by KNN (94.0 ± 4.22%). The accuracy of CNN was 87.6 ± 7.50% and that of LSTM 83.6 ± 5.35%.

CONCLUSIONS

This study revealed that the proposed AI machine learning (ML) techniques can be used to design gait biometric systems and machine vision for gait pattern recognition. Potentially, this method can be used to remotely evaluate elderly patients and help clinicians make decisions regarding disposition, follow-up, and treatment.

Characterization of Infants' General Movements Using a Commercial RGB-Depth Sensor and a Deep Neural Network Tracking Processing Tool: An Exploratory Study

Cerebral palsy, the most common childhood neuromotor disorder, is often diagnosed through visual assessment of general movements (GM) in infancy. This skill requires extensive training and is thus difficult to implement on a large scale. Automated analysis of GM performed using low-cost instrumentation in the home may be used to estimate quantitative metrics predictive of movement disorders. This study explored if infants' GM may be successfully evaluated in a familiar environment by processing the 3D trajectories of points of interest (PoI) obtained from recordings of a single commercial RGB-D sensor. The RGB videos were processed using an open-source markerless motion tracking method which allowed the estimation of the 2D trajectories of the selected PoI and a purposely developed method which allowed the reconstruction of their 3D trajectories making use of the data recorded with the depth sensor. Eight infants' GM were recorded in the home at 3, 4, and 5 months of age. Eight GM metrics proposed in the literature in addition to a novel metric were estimated from the PoI trajectories at each timepoint. A pediatric neurologist and physiatrist provided an overall clinical evaluation from infants' video. Subsequently, a comparison between metrics and clinical evaluation was performed. The results demonstrated that GM metrics may be meaningfully estimated and potentially used for early identification of movement disorders.

Evaluation of Arm Swing Features and Asymmetry during Gait in Parkinson's Disease Using the Azure Kinect Sensor

Arm swinging is a typical feature of human walking: Continuous and rhythmic movement of the upper limbs is important to ensure postural stability and walking efficiency. However, several factors can interfere with arm swings, making walking more risky and unstable: These include aging, neurological diseases, hemiplegia, and other comorbidities that affect motor control and coordination. Objective assessment of arm swings during walking could play a role in preventing adverse consequences, allowing appropriate treatments and rehabilitation protocols to be activated for recovery and improvement. This paper presents a system for gait analysis based on Microsoft Azure Kinect DK sensor and its body-tracking algorithm: It allows noninvasive full-body tracking, thus enabling simultaneous analysis of different aspects of walking, including arm swing characteristics. Sixteen subjects with Parkinson's disease and 13 healthy controls were recruited with the aim of evaluating differences in arm swing features and correlating them with traditional gait parameters. Preliminary results show significant differences between the two groups and a strong correlation between the parameters. The study thus highlights the ability of the proposed system to quantify arm swing features, thus offering a simple tool to provide a more comprehensive gait assessment.

Kinect-Based Assessment of Lower Limbs during Gait in Post-Stroke Hemiplegic Patients: A Narrative Review

The aim of this review was to present an overview of the state of the art in the use of the Microsoft Kinect camera to assess gait in post-stroke individuals through an analysis of the available literature. In recent years, several studies have explored the potentiality, accuracy, and effectiveness of this 3D optical sensor as an easy-to-use and non-invasive clinical measurement tool for the assessment of gait parameters in several pathologies. Focusing on stroke individuals, some of the available studies aimed to directly assess and characterize their gait patterns. In contrast, other studies focused on the validation of Kinect-based measurements with respect to a gold-standard reference (i.e., optoelectronic systems). However, the nonhomogeneous characteristics of the participants, of the measures, of the methodologies, and of the purposes of the studies make it difficult to adequately compare the results. This leads to uncertainties about the strengths and weaknesses of this technology in this pathological state. The final purpose of this narrative review was to describe and summarize the main features of the available works on gait in the post-stroke population, highlighting similarities and differences in the methodological approach and primary findings, thus facilitating comparisons of the studies as much as possible.

Ground reaction force and joint moment estimation during gait using an Azure Kinect-driven musculoskeletal modeling approach

BACKGROUND

Gait analysis is burdened by time and equipment costs, interpretation, and accessibility of three-dimensional motion analysis systems. Evidence suggests growing adoption of gait testing in the shift toward evidence-based medicine. Further developments addressing these barriers will aid its efficacy in clinical practice. Previous research aiming to develop gait analysis systems for kinetics estimation using the Kinect V2 have provided promising results yet modified approaches using the latest hardware may further aid kinetics estimation accuracy RESEARCH QUESTION: Can a single Azure Kinect sensor combined with a musculoskeletal modeling approach provide kinetics estimations during gait similar to those obtained from marker-based systems with embedded force platforms?

METHODS

Ten subjects were recruited to perform three walking trials at their normal speed. Trials were recorded using an eight-camera optoelectronic system with two embedded force plates and a single Azure Kinect sensor. Marker and depth data were both used to drive a musculoskeletal model using the AnyBody Modeling System. Predicted kinetics from the Azure Kinect-driven model, including ground reaction force (GRF) and joint moments, were compared to measured values using root meansquared error (RMSE), normalized RMSE, Pearson correlation, concordance correlation, and statistical parametric mapping RESULTS: High to very high correlations were observed for anteroposterior GRF (ρ = 0.889), vertical GRF (ρ = 0.940), and sagittal hip (ρ = 0.805) and ankle (ρ = 0.876) moments. RMSEs were 1.2 ± 2.2 (%BW), 3.2 ± 5.7 (%BW), 0.7 ± 0.1.3 (%BWH), and 0.6 ± 1.0 (%BWH) SIGNIFICANCE: The proposed approach using the Azure Kinect provided higher accuracy compared to previous studies using the Kinect V2 potentially due to improved foot tracking by the Azure Kinect. Future studies should seek to optimize ground contact parameters and focus on regions of error between predicted and measured kinetics highlighted currently for further improvements in kinetic estimations.