Detecting compensatory movements of stroke survivors using pressure distribution data and machine learning algorithms

For stroke patients with hemiplegia, reaching with the paretic arm is often associated with compensatory movements due to limited active arm movement and a loss of interjoint coordination. Detecting common compensatory movement patterns, such as excessive trunk displacement and scapular elevation, is critical for improving the motor function of the paretic arm. Existing compensatory movement pattern detection methods, including sensor-based systems and camera-based systems, suffer from object obstruction and require complex setups. In this paper, a compensatory movement pattern detection system using a pressure distribution mattress is presented. This method is a novel approach to detect compensations and has observed advantages; it is simple, unobtrusive and low cost. Fifteen healthy participants with no motor impairments performed three reaching tasks (back-and-forth, side-to-side, and up-and-down reaching) in a normal pattern and in compensatory movement patterns (trunk rotation and lean-forward, and scapular elevation). Pressure distribution data of all motions were recorded and processed to generate a group of features (average sensor values, the lateral center of pressure, longitudinal center of pressure, the ratio of left-side to right-side pressure, and the ratio of front-side to back-side pressure) reflecting the information of each predefined pattern. Four machine learning methods were implemented to detect compensatory movement patterns and showed good reliability and precision. Both k-nearest neighbor (kNN) and support vector machine (SVM) classifiers have achieved an excellent classification performance (F1-score = 0.934) in detecting compensation during all reaching tasks. For the multiclass classification of compensatory movement patterns, the SVM classifier exhibited a good classification performance for trunk lean-forward (F1-score = 0.933), scapular elevation (F1-score = 0.881), and trunk rotation (F1-score = 0.854) and outperformed previous reports. The study results provide initial evidence of a pressure distribution mattress for detecting compensatory movement patterns. Future work needs to test the approach on stroke survivors to verified the feasibility and validity.

Stroke survivors often compensate for the loss of motor function in their distal joints by altered use of more proximal joints and body segments. Since this can be detrimental to the rehabilitation process in the long-term, it is imperative that such movements are indicated to the patients and their caregiver. This is a difficult task since compensation strategies are varied and multi-faceted. Recent works that have focused on supervised machine learning methods for compensation detection often require a large training dataset of motions with compensation location annotations for each time-step of the recorded motion. In contrast, this study proposed a novel approach that learned a linear classifier from energy-based features to discriminate between healthy and compensatory movements and identify the compensating joints without the need for dense and explicit annotations. Six healthy physiotherapists performed five different tasks using healthy movements and acted compensations. The resulting motion capture data was transformed into joint kinematic and dynamic trajectories. Inspired by works in bio-mechanics, energy-based features were extracted from this dataset. Support vector machine (SVM) and logistic regression (LR) algorithms were then applied for detection of compensatory movements. For compensating joint identification, an additional condition enforcing the independence of the feature calculation for each observable degree of freedom was imposed. Using leave-one-out cross validation, low values of mean brier score (<0.15), mis-classification rate (<0.2) and false discovery rate (<0.2) were obtained for both SVM and LR classifiers. These methods were found to outperform deep learning classifiers that did not use energy-based features. Additionally, online classification performance by our methods were also shown to outperform deep learning baselines. Furthermore, qualitative results obtained from the compensation joint identification experiment indicated that the method could successfully identify compensating joints. Results from this study indicated that including prior bio-mechanical information in the form of energy based features can improve classification performance even when linear classifiers are used, both for offline and online classification. Furthermore, evaluation compensation joint identification algorithm indicated that it could potentially provide a straightforward and interpretable way of identifying compensating joints, as well as the degree of compensation being performed.

As societies age, the number of individuals experiencing stroke increases, necessitating more effective rehabilitation strategies. Over half of stroke survivors suffer from upper limb impairments, making assessments of sensory-motor function crucial for both improving interventions and tracking progress. Ideally, such assessments could also be performed at home without requiring a therapist's presence. Advances in computer vision and human pose estimation allow for human movement analysis using consumer-grade cameras. This study investigates whether a single webcam, combined with human pose estimation and deep learning algorithms, can automatically detect compensatory movements in persons with stroke performing a drinking task. Twenty participants with stroke with mild to moderate upper limb impairment were recruited. Each participant performed multiple repetitions of the drinking task while being recorded by multiple cameras and an optical motion capture system (OMC) for kinematic ground truth. The videos were labeled by therapists to indicate the presence or absence of compensatory movements. Human poses were extracted from the videos using MediaPipe, and deep learning models were trained to predict these compensatory movements based on MediaPipe keypoints. Several factors affecting compensation detection accuracy were evaluated. Models trained on raw MediaPipe keypoints for inter-person compensation detection failed to generalize, achieving accuracy around 50%. Using custom features instead of raw keypoints improved the accuracy to 70%. In contrast, intraperson classification achieved high accuracy, typically exceeding 90%. Using OMC data significantly improved classification accuracy compared to using MediaPipe keypoints. Camera angle had an effect on accuracy, and convolutional neural networks outperformed long short-term memory networks. Generalizing models remain limited by (1) the measurement uncertainty of human pose estimation and (2) insufficient data representing the full spectrum of compensatory strategies (3) accurate compensation labels. The results demonstrate that deep learning approaches can differentiate between compensatory and non-compensatory movements when movement representations are sufficiently accurate. Future work should improve pose estimation and expand labeled datasets to better reflect the stroke population. While general models are limited in accuracy, personalized models using consumer cameras can support home-based rehabilitation. This digitalized assessment approach has the potential to quantify recovery progress throughout the continuum of care.

Introduction: Interactive game systems can motivate stroke survivors to engage with their rehabilitation exercises. However, it is crucial that systems are in place to detect if exercises are performed correctly as stroke survivors often perform compensatory movements which can be detrimental to recovery. Very few game systems integrate motion tracking algorithms to monitor performance and detect such movements. This paper describes the development of algorithms which monitor for compensatory movements during upper limb reaching movements in real-time and provides quantitative metrics for health professionals to monitor performance and progress over time.Methods: A real-time algorithm was developed to analyse reaching motions in real-time through a low-cost depth camera. The algorithm segments cyclical reaching motions into component parts, including compensatory movement, and provides a graphical representation of task performance. Healthy participants (n = 10) performed reaching motions facing the camera. The real-time accuracy of the algorithm was assessed by comparing offline analysis to real-time collection of data.Results: The algorithm’s ability to segment cyclical reaching motions and detect the component parts in real-time was assessed. Results show that movement types can be detected in real time with accuracy, showing a maximum error of 1.71%.Conclusions: Using the methods outlined, the real-time detection and quantification of compensatory movements is feasible for integration within home-based, repetitive task practice game systems for people with stroke.

The aim of this study is to extract impervious surfaces and show their spatial distribution, using different machine learning algorithms. For this purpose, geoprocessing and remote sensing techniques were used and three classification methods for digital images were compared, namely Support Vector Machines (SVM), Maximum Likelihood (ML) and Random Trees (RT) classifiers. The study area is one of the most prestigious and the largest housing estates in Warsaw (Poland), the Fort Bema housing complex, which is also an exemplary model for hydrological solutions. The study was prepared on the Geographic Information System platform (GIS) using aerial optical images, orthorectified and thus provided with a suitable coordinate system. The use of these data is therefore supported by the accuracy of the resulting infrared channel product with a pixel size of 0.25 m, making the results much more accurate compared to satellite imagery. The results of the SVM, ML and RT classifiers were compared using the confusion matrix, accuracy (Root Mean Square Error /RMSE/) and kappa index. This showed that the three algorithms were able to successfully discriminate between targets. Overall, the three classifiers had errors, but specifically for impervious surfaces, the highest accuracy was achieved with the SVM classifier (the highest percentage of overall accuracy), followed by ML and RT with 91.51%, 91.35% and 84.52% of the results, respectively. A comparison of the visual results and the confusion matrix shows that although visually the RT method appears to be the most detailed classification into pervious and impervious surfaces, the results were not always correct, e.g., water/shadow was detected as an impervious surface. The NDVI index was also mapped for the same spatial study area and its application in the evaluation of pervious surfaces was explained. The results obtained with the GIS platform, presented in this paper, provide a better understanding of how these advanced classifiers work, which in turn can provide insightful guidance for their selection and combination in real-world applications. The paper also provides an overview of the main works/studies dealing with impervious surface mapping, with different methods for their assessment (including the use of conventional remote sensing, NDVI, multisensory and cross-source data, ‘social sensing’ and classification methods such as SVM, ML and RT), as well as an overview of the research results.

Considering the form diversity of tree species composition in the Bagong Mountain National Forest Park of China, we mapped tree species utilizing Machine Learning Algorithms (support vector machines (SVM) and random forest (RF) classifiers) based on the OHS-2 hyperspectral satellite image by different datasets which combined spectral information and hyperspectral-derived vegetation indices (VIs) for improving tree species classification and explored the best performance of them. To verify the improvement, the results of physically-based spectral classifiers (spectral angle mapper (SAM) and maximum likelihood (ML) classifiers) were applied to compare with the results of machine learning algorithms. The results indicated an overall accuracy of 94.01%, 96.08%, 82.9% and 79.3% for SVM, RF, SAM and ML classifiers of the best performance using different datasets. Highest accuracies resulted from two machine learning algorithms classifiers; SVM and RF compared to SAM and ML classifiers. Although SVM outperformed RF when using all hyperspectral bands and VIs, the overall accuracy of the RF classifier is higher when compared to the SVM classifier using VIs combined selected features. Meanwhile, the RF classifier performed better than SVM after removing the redundancy of spectral data in training samples. Moreover, the machine learning algorithms successfully classified a small number of tree species (Cedrus deodara and Pterocarya stenoptera C. DC.) in the study area, but the physical spectroscopy-based method failed to classify these species. Such integration strategy improved the effectiveness of enhancing the accuracy of tree species classification and mapping their distribution on broad spatial and temporal scales using machine learning algorithms and hyperspectral imagery.

The Effects of Constraint-Induced Therapy on Kinematic Outcomes and Compensatory Movement Patterns: An Exploratory Study

A comparison of compensatory movements between body-powered and myoelectric prosthesis users during activities of daily living

The problem with development of the support vector machine (SVM) classifiers using modified particle swarm optimization (PSO) algorithm and their ensembles has been considered. Solving this problem would allow fulfilling the high-precision data classification, especially Big Data classification, with the acceptable time expenditures. The modified PSO algorithm conducts a simultaneous search of the type of kernel functions, the parameters of the kernel function and the value of the regularization parameter for the SVM classifier. The idea of particles' «regeneration» served as the basis for the modified PSO algorithm. In the implementation of this algorithm, some particles change the type of their kernel function to the one which corresponds to the particle with the best value of the classification accuracy. The offered PSO algorithm allows reducing the time expenditures for the developed SVM classifiers, which is very important for Big Data classification problem. In most cases such SVM classifier provides the high quality of data classification. In exceptional cases the SVM ensembles based on the decorrelation maximization algorithm for the different strategies of the decision-making on the data classification and the majority vote rule can be used. Also, the two-level SVM classifier has been offered. This classifier works as the group of the SVM classifiers at the first level and as the SVM classifier on the base of the modified PSO algorithm at the second level. The results of experimental studies confirm the efficiency of the offered approaches for Big Data classification.

Background: Neurocognitive disorder (NCD) is common after stroke, with major NCD appearing in about 10% of survivors of a first-ever stroke. We aimed to classify clinical- and imaging factors related to rapid development of major NCD 3 months after a stroke, so as to examine the optimal composition of factors for predicting rapid development of the disorder. We hypothesized that the prediction would mainly be driven by neurodegenerative as opposed to vascular brain changes.Methods: Stroke survivors from five Norwegian hospitals were included from the “Norwegian COgnitive Impairment After STroke” (Nor-COAST) study. A support vector machine (SVM) classifier was trained to distinguish between patients who developed major NCD 3 months after the stroke and those who did not. Potential predictor factors were based on previous literature and included both vascular and neurodegenerative factors from clinical and structural magnetic resonance imaging findings. Cortical thickness was obtained via FreeSurfer segmentations, and volumes of white matter hyperintensities (WMH) and stroke lesions were semi-automatically gathered using FSL BIANCA and ITK-SNAP, respectively. The predictive value of the classifier was measured, compared between classifier models and cross-validated.Results: Findings from 227 stroke survivors [age = 71.7 (11.3), males = (56.4%), stroke severity NIHSS = 3.8 (4.8)] were included. The best predictive accuracy (AUC = 0.876) was achieved by an SVM classifier with 19 features. The model with the fewest number of features that achieved statistically comparable accuracy (AUC = 0.850) was the 8-feature model. These features ranked by their weighting were; stroke lesion volume, WMH volume, left occipital and temporal cortical thickness, right cingulate cortical thickness, stroke severity (NIHSS), antiplatelet medication intake, and education.Conclusion: The rapid (<3 months) development of major NCD after stroke is possible to predict with an 87.6% accuracy and seems dependent on both neurodegenerative and vascular factors, as well as aspects of the stroke itself. In contrast to previous literature, we also found that vascular changes are more important than neurodegenerative ones. Although possible to predict with relatively high accuracy, our findings indicate that the development of rapid onset post-stroke NCD may be more complex than earlier suggested.

Stroke survivors often suffer from movement impairments that significantly affect their daily activities. The advancements in sensor technology and IoT have provided opportunities to automate the assessment and rehabilitation process for stroke survivors. This paper aims to provide a smart post-stroke severity assessment using AI-driven models. With the absence of labelled data and expert assessment, there is a research gap in providing virtual assessment, especially for unlabeled data. Inspired by the advances in consensus learning, in this paper, we propose a consensus clustering algorithm, PSA-NMF, that combines various clusterings into one united clustering, i.e., cluster consensus, to produce more stable and robust results compared to individual clustering. This paper is the first to investigate severity level using unsupervised learning and trunk displacement features in the frequency domain for post-stroke smart assessment. Two different methods of data collection from the U-limb datasets—the camera-based method (Vicon) and wearable sensor-based technology (Xsens)—were used. The trunk displacement method labelled each cluster based on the compensatory movements that stroke survivors employed for their daily activities. The proposed method uses the position and acceleration data in the frequency domain. Experimental results have demonstrated that the proposed clustering method that uses the post-stroke assessment approach increased the evaluation metrics such as accuracy and F-score. These findings can lead to a more effective and automated stroke rehabilitation process that is suitable for clinical settings, thus improving the quality of life for stroke survivors.

High temporal resolution of synthetic aperture radar (SAR) imagery (e.g., Sentinel-1 (S1) imagery) creates new possibilities for monitoring green vegetation in urban areas and generating land-cover classification (LCC) maps. This research evaluates how different pre-processing steps of SAR imagery affect classification accuracy. Machine learning (ML) methods were applied in three different study areas: random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB). Since the presence of the speckle noise in radar imagery is inevitable, different adaptive filters were examined. Using the backscattering values of the S1 imagery, the SVM classifier achieved a mean overall accuracy (OA) of 63.14%, and a Kappa coefficient (Kappa) of 0.50. Using the SVM classifier with a Lee filter with a window size of 5×5 (Lee5) for speckle reduction, mean values of 73.86% and 0.64 for OA and Kappa were achieved, respectively. An additional increase in the LCC was obtained with texture features calculated from a grey-level co-occurrence matrix (GLCM). The highest classification accuracy obtained for the extracted GLCM texture features using the SVM classifier, and Lee5 filter was 78.32% and 0.69 for the mean OA and Kappa values, respectively. This study improved LCC with an evaluation of various radiometric and texture features and confirmed the ability to apply an SVM classifier. For the supervised classification, the SVM method outperformed the RF and XGB methods, although the highest computational time was needed for the SVM, whereas XGB performed the fastest. These results suggest pre-processing steps of the SAR imagery for green infrastructure mapping in urban areas. Future research should address the use of multitemporal SAR data along with the pre-processing steps and ML algorithms described in this research.

Limb amputation can cause severe functional disability in performing activities of daily living (ADLs). Using prosthetic devices as aids for such activities requires substantial cognitive resources. Machine Learning (ML) algorithms can be used to predict cognitive workload (CW) of prosthetic device prototypes early in the design process and serve as a tool for improving device usability. The objective of this study was to explore subsets of input features that can be easily captured during early stages of the design cycle to classify CW of electromyography (EMG)-based upper-limb prostheses. An experiment was conducted with 30 participants to collect task performance and pupillometry data, and to provide a basis for generating cognitive performance model (CPM) outcomes. Three ML algorithms, including the random forest (RF), support vector machine (SVM), and naive Bayesian (NB) classifier were developed. The most important subset of features was selected based on classification accuracy and computational and experimental cost. Findings revealed that the CPM outcomes and prosthetic device configuration were the most important features for reasonably classifying CW responses under low cost. Also, the SVM classifier can be used for near-real time classification of CW. Future studies should include additional data and improve hyperparameter tuning parameters, as well as advanced CPM techniques to improve the performance of algorithms.

Several machine learning (ML) algorithms have been increasingly utilized for cardiovascular disease prediction. We aim to assess and summarize the overall predictive ability of ML algorithms in cardiovascular diseases. A comprehensive search strategy was designed and executed within the MEDLINE, Embase, and Scopus databases from database inception through March 15, 2019. The primary outcome was a composite of the predictive ability of ML algorithms of coronary artery disease, heart failure, stroke, and cardiac arrhythmias. Of 344 total studies identified, 103 cohorts, with a total of 3,377,318 individuals, met our inclusion criteria. For the prediction of coronary artery disease, boosting algorithms had a pooled area under the curve (AUC) of 0.88 (95% CI 0.84–0.91), and custom-built algorithms had a pooled AUC of 0.93 (95% CI 0.85–0.97). For the prediction of stroke, support vector machine (SVM) algorithms had a pooled AUC of 0.92 (95% CI 0.81–0.97), boosting algorithms had a pooled AUC of 0.91 (95% CI 0.81–0.96), and convolutional neural network (CNN) algorithms had a pooled AUC of 0.90 (95% CI 0.83–0.95). Although inadequate studies for each algorithm for meta-analytic methodology for both heart failure and cardiac arrhythmias because the confidence intervals overlap between different methods, showing no difference, SVM may outperform other algorithms in these areas. The predictive ability of ML algorithms in cardiovascular diseases is promising, particularly SVM and boosting algorithms. However, there is heterogeneity among ML algorithms in terms of multiple parameters. This information may assist clinicians in how to interpret data and implement optimal algorithms for their dataset.

Alternative splicing is a mechanism for generating different gene transcripts (called isoforms) from the same genomic sequence. Finding alternative splicing events experimentally is both expensive and time consuming. Computational methods, in general, and machine learning algorithms,in particular, can be used to complement experimental methods in the process of identifying alternative splicing events. In this paper, we explore the predictive power of a rich set of features that have been experimentally shown to affect alternative splicing. We use these features to build support vector machine (SVM) classifiers for distinguishing between alternatively spliced exons and constitutive exons.Our results show that simple linear SVM classifiers built from a rich set of features give results comparable to those of more sophisticated SVM classifiers that use more basic sequence features. Furthermore, we use feature selection methods to identify computationally the most informative features for the prediction problem considered.