Analysis of Machine Learning-Based Assessment for Elbow Spasticity Using Inertial Sensors.
Ontology highlight
ABSTRACT:
SUBMITTER: Kim JY
PROVIDER: S-EPMC7146614 | biostudies-literature | 2020 Mar
REPOSITORIES: biostudies-literature
Publications
Analysis of Machine Learning-Based Assessment for Elbow Spasticity Using Inertial Sensors.
Kim Jung-Yeon JY Park Geunsu G Lee Seong-A SA Nam Yunyoung Y
Sensors (Basel, Switzerland) 20200314 6
Spasticity is a frequently observed symptom in patients with neurological impairments. Spastic movements of their upper and lower limbs are periodically measured to evaluate functional outcomes of physical rehabilitation, and they are quantified by clinical outcome measures such as the modified Ashworth scale (MAS). This study proposes a method to determine the severity of elbow spasticity, by analyzing the acceleration and rotation attributes collected from the elbow of the affected side of pat ...[more]
Similar Datasets
Project description:BackgroundElbow and wrist chronic conditions are very common among musculoskeletal problems. These painful conditions affect muscle function, which ultimately leads to a decrease in the joint's Range Of Motion (ROM). Due to their portability and ease of use, goniometers are still the most widespread tool for measuring ROM. Inertial sensors are emerging as a digital, low-cost and accurate alternative. However, whereas inertial sensors are commonly used in research studies, due to the lack of information about their validity and reliability, they are not widely used in the clinical practice. The goal of this study is to assess the validity and intra-inter-rater reliability of inertial sensors for measuring active ROM of the elbow and wrist.Materials and methodsMeasures were taken simultaneously with inertial sensors (Werium™ system) and a universal goniometer. The process involved two physiotherapists ("rater A" and "rater B") and an engineer responsible for the technical issues. Twenty-nine asymptomatic subjects were assessed individually in two sessions separated by 48 h. The procedure was repeated by rater A followed by rater B with random order. Three repetitions of each active movement (elbow flexion, pronation, and supination; and wrist flexion, extension, radial deviation and ulnar deviation) were executed starting from the neutral position until the ROM end-feel; that is, until ROM reached its maximum due to be stopped by the anatomy. The coefficient of determination (r 2) and the Intraclass Correlation Coefficient (ICC) were calculated to assess the intra-rater and inter-rater reliability. The Standard Error of the Measurement and the Minimum Detectable Change and a Bland-Altman plots were also calculated.ResultsSimilar ROM values when measured with both instruments were obtained for the elbow (maximum difference of 3° for all the movements) and wrist (maximum difference of 1° for all the movements). These values were within the normal range when compared to literature studies. The concurrent validity analysis for all the movements yielded ICC values ≥0.78 for the elbow and ≥0.95 for the wrist. Concerning reliability, the ICC values denoted a high reliability of inertial sensors for all the different movements. In the case of the elbow, intra-rater and inter-rater reliability ICC values range from 0.83 to 0.96 and from 0.94 to 0.97, respectively. Intra-rater analysis of the wrist yielded ICC values between 0.81 and 0.93, while the ICC values for the inter-rater analysis range from 0.93 to 0.99.ConclusionsInertial sensors are a valid and reliable tool for measuring elbow and wrist active ROM. Particularly noteworthy is their high inter-rater reliability, often questioned in measurement tools. The lowest reliability is observed in elbow prono-supination, probably due to skin artifacts. Based on these results and their advantages, inertial sensors can be considered a valid assessment tool for wrist and elbow ROM.
| S-EPMC7427560 | biostudies-literature
Project description:Parkinson's disease (PD) is a neurodegenerative disease inducing dystrophy of the motor system. Automatic movement analysis systems have potential in improving patient care by enabling personalized and more accurate adjust of treatment. These systems utilize machine learning to classify the movement properties based on the features derived from the signals. Smartphones can provide an inexpensive measurement platform with their built-in sensors for movement assessment. This study compared three feature selection and nine classification methods for identifying PD patients from control subjects based on accelerometer and gyroscope signals measured with a smartphone during a 20-step walking test. Minimum Redundancy Maximum Relevance (mRMR) and sequential feature selection with both forward (SFS) and backward (SBS) propagation directions were used in this study. The number of selected features was narrowed down from 201 to 4-15 features by applying SFS and mRMR methods. From the methods compared in this study, the highest accuracy for individual steps was achieved with SFS (7 features) and Naive Bayes classifier (accuracy 75.3%), and the second highest accuracy with SFS (4 features) and k Nearest neighbours (accuracy 75.1%). Leave-one-subject-out cross-validation was used in the analysis. For the overall classification of each subject, which was based on the majority vote of the classified steps, k Nearest Neighbors provided the most accurate result with an accuracy of 84.5% and an error rate of 15.5%. This study shows the differences in feature selection methods and classifiers and provides generalizations for optimizing methodologies for smartphone-based monitoring of PD patients. The results are promising for further developing the analysis system for longer measurements carried out in free-living conditions.
| S-EPMC7377496 | biostudies-literature
Project description:Introduction: Children's walking patterns evolve with age, exhibiting less repetitiveness at a young age and more variability than adults. Three-dimensional gait analysis (3DGA) is crucial for understanding and treating lower limb movement disorders in children, traditionally performed using Optical Motion Capture (OMC). Inertial Measurement Units (IMUs) offer a cost-effective alternative to OMC, although challenges like drift errors persist. Machine learning (ML) models can mitigate these issues in adults, prompting an investigation into their applicability to a heterogeneous pediatric population. This study aimed at 1) quantifying personalized and generalized ML models' performance for predicting gait time series in typically developed (TD) children using IMUs data, 2) Comparing random forest (RF) and convolutional neural networks (CNN) models' performance, 3) Finding the optimal number of IMUs required for accurate predictions. Methodology: Seventeen TD children, aged 6 to 15, participated in data collection involving OMC, force plates, and IMU sensors. Joint kinematics and kinetics (targets) were computed from OMC and force plates' data using OpenSim. Tsfresh, a Python package, extracted features from raw IMU data. Each target's ten most important features were input in the development of personalized and generalized RF and CNN models. This procedure was initially conducted with 7 IMUs placed on all lower limb segments and then performed using only two IMUs on the feet. Results: Findings suggested that the RF and CNN models demonstrated comparable performance. RF predicted joint kinematics with a 9.5% and 19.9% NRMSE for personalized and generalized models, respectively, and joint kinetics with an NRMSE of 10.7% for personalized and 15.2% for generalized models in TD children. Personalized models provided accurate estimations from IMU data in children, while generalized models lacked accuracy due to the limited dataset. Furthermore, reducing the number of IMUs from 7 to 2 did not affect the results, and the performance remained consistent. Discussion: This study proposed a promising personalized approach for gait time series prediction in children, involving an RF model and two IMUs on the feet.
| S-EPMC10987962 | biostudies-literature
Project description:BackgroundPhysiotherapy is a critical element in the successful conservative management of low back pain (LBP). A gold standard for quantitatively measuring physiotherapy participation is crucial to understanding physiotherapy adherence in managing recovery from LBP.ObjectiveThis study aimed to develop and evaluate a system with wearable inertial sensors to objectively detect the performance of unsupervised exercises for LBP comprising movement in multiple planes and sitting postures.MethodsA quantitative classification design was used within a machine learning framework to detect exercise performance and posture in a cohort of healthy participants. A set of 8 inertial sensors were placed on the participants, and data were acquired as they performed 7 McKenzie low back exercises and 3 sitting posture positions. Engineered time series features were extracted from the data and used to train 9 models by using a 6-fold cross-validation approach, from which the best 2 models were selected for further study. In addition, a convolutional neural network was trained directly on the time series data. A feature importance analysis was performed to identify sensor locations and channels that contributed the most to the models. Finally, a subset of sensor locations and channels was included in a hyperparameter grid search to identify the optimal sensor configuration and best performing algorithms for exercise and posture classification. The final models were evaluated using the F1 score in a 10-fold cross-validation approach.ResultsIn total, 19 healthy adults with no history of LBP each completed at least one full session of exercises and postures. Random forest and XGBoost (extreme gradient boosting) models performed the best out of the initial set of 9 engineered feature models. The optimal hardware configuration was identified as a 3-sensor setup-lower back, left thigh, and right ankle sensors with acceleration, gyroscope, and magnetometer channels. The XGBoost model achieved the highest exercise (F1 score: mean 0.94, SD 0.03) and posture (F1 score: mean 0.90, SD 0.11) classification scores. The convolutional neural network achieved similar results with the same sensor locations, using only the accelerometer and gyroscope channels for exercise classification (F1 score: mean 0.94, SD 0.02) and the accelerometer channel alone for posture classification (F1 score: mean 0.88, SD 0.07).ConclusionsThis study demonstrates the potential of a 3-sensor lower body wearable solution (eg, smart pants) that can identify exercises in multiple planes and proper sitting postures, which is suitable for the treatment of LBP. This technology has the potential to improve the effectiveness of LBP rehabilitation by facilitating quantitative feedback, early problem diagnosis, and possible remote monitoring.
| S-EPMC9449825 | biostudies-literature
Project description:The monitoring of head posture is crucial for interactive learning, in order to build feedback with learners' attention, especially in the explosion of digital teaching that occurred during the current COVID-19 pandemic. However, conventional monitoring based on computer vision remains a great challenge in the multi-freedom estimation of head posture, owing to low-angle annotation and limited training accuracy. Here, we report a fully integrated attachable inertial device (AID) that comfortably monitors in situ head posture at the neck, and provides a machine learning-based assessment of attention. The device consists of a stretchable inertial sensing unit and a fully integrated circuit-based system, as well as mechanically compliant encapsulation. Due to the mechanical flexibility, the device can be seamlessly attach to a human neck's epidermis without frequent user interactions, and wirelessly supports six-axial inertial measurements, thereby obtaining multidimensional tracking of individual posture. These head postures (40 types) are then divided into 10 rotation actions which correspond to diverse situations that usually occur in daily activities of teaching. Benefiting from a 2D convolutional neural network (CNN)-based machine learning model, their classification and prediction of head postures can be used to analyze and infer attention behavior. The results show that the proposed 2D CNN-based machine learning method can effectively distinguish the head motion posture, with a high accuracy of 98.00%, and three actual postures were successfully verified and evaluated in a predefined attention model. The inertial monitoring and attention evaluation based on attachable devices and machine learning will have potential in terms of learning feedback and planning for learners.
| S-EPMC9788255 | biostudies-literature
Project description:Real-world gait analysis can aid in clinical assessments and influence related interventions, free from the restrictions of a laboratory setting. Using individual accelerometers, we aimed to use a simple machine learning method to quantify the performance of the discrimination between three self-selected cyclical locomotion types using accelerometers placed at frequently referenced attachment locations. Thirty-five participants walked along a 10 m walkway at three different speeds. Triaxial accelerometers were attached to the sacrum, thighs and shanks. Slabs of magnitude, three-second-long accelerometer data were transformed into two-dimensional Fourier spectra. Principal component analysis was undertaken for data reduction and feature selection, followed by discriminant function analysis for classification. Accuracy was quantified by calculating scalar accounting for the distances between the three centroids and the scatter of each category's cloud. The algorithm could successfully discriminate between gait modalities with 91% accuracy at the sacrum, 90% at the shanks and 87% at the thighs. Modalities were discriminated with high accuracy in all three sensor locations, where the most accurate location was the sacrum. Future research will focus on optimising the data processing of information from sensor locations that are advantageous for practical reasons, e.g., shank for prosthetic and orthotic devices.
| S-EPMC10675053 | biostudies-literature
Project description:The use of walking aids is prevalent among older people and people with mobility impairment. Rollators are designed to support outdoor mobility and require the user to negotiate curbs and slopes in the urban environment. Despite the prevalence of rollators, analysis of their use outside of controlled environments has received relatively little attention. This Letter reports on an initial study to characterise rollator movement. An inertial measurement unit (IMU) was used to measure the motion of the rollator and analytical approaches were developed to extract features characterising the rollator movement, properties of the surface and push events. The analytics were tested in two situations: first, a healthy participant used a rollator in a laboratory using a motion capture system to obtain ground truth. Second, the IMU was used to measure the movement of a rollator being used by a user with multiple sclerosis on a flat surface, cross-slope, up and down slopes and up and down a step. The results showed that surface inclination and distance travelled measured by the IMU have close approximation to the results from ground truth; therefore, demonstrating the potential for IMU-derived metrics to characterise rollator movement and user's pushing style in the outdoor environment.
| S-EPMC5168841 | biostudies-other
Project description:Full-body motion capture typically requires sensors/markers to be placed on each rigid body segment, which results in long setup times and is obtrusive. The number of sensors/markers can be reduced using deep learning or offline methods. However, this requires large training datasets and/or sufficient computational resources. Therefore, we investigate the following research question: "What is the performance of a shallow approach, compared to a deep learning one, for estimating time coherent full-body poses using only five inertial sensors?". We propose to incorporate past/future inertial sensor information into a stacked input vector, which is fed to a shallow neural network for estimating full-body poses. Shallow and deep learning approaches are compared using the same input vector configurations. Additionally, the inclusion of acceleration input is evaluated. The results show that a shallow learning approach can estimate full-body poses with a similar accuracy (~6 cm) to that of a deep learning approach (~7 cm). However, the jerk errors are smaller using the deep learning approach, which can be the effect of explicit recurrent modelling. Furthermore, it is shown that the delay using a shallow learning approach (72 ms) is smaller than that of a deep learning approach (117 ms).
| S-EPMC6749312 | biostudies-literature
Project description:In this paper, we develop an algorithm to automatically validate and segment a gait cycle in real time into three gait events, namely midstance, toe-off, and heel-strike, using inertial sensors. We first use the physical models of sensor data obtained from a foot-mounted inertial system to differentiate stationary and moving segments of the sensor data. Next, we develop an optimization routine called sparsity-assisted wavelet denoising (SAWD), which simultaneously combines linear time invariant filters, orthogonal multiresolution representations such as wavelets, and sparsity-based methods, to generate a sparse template of the moving segments of the gyroscope measurements in the sagittal plane for valid gait cycles. Thereafter, to validate any moving segment as a gait cycle, we compute the root-mean-square error between the generated sparse template and the sparse representation of the moving segment of the gyroscope data in the sagittal plane obtained using SAWD. Finally, we find the local minima for the stationary and moving segments of a valid gait cycle to detect the gait events. We compare our proposed method with existing methods, for a fixed threshold, using real data obtained from three groups, namely controls, participants with Parkinson disease, and geriatric participants. Our proposed method demonstrates an average F1 score of 87.78% across all groups for a fixed sampling rate, and an average F1 score of 92.44% across all Parkinson disease participants for a variable sampling rate.
| S-EPMC7305840 | biostudies-literature
Project description:BackgroundDepression levels in adolescents have trended upward over the past several years. According to a 2020 survey by the National Survey on Drug Use and Health, 4.1 million US adolescents have experienced at least one major depressive episode. This number constitutes approximately 16% of adolescents aged 12 to 17 years. However, only 32.3% of adolescents received some form of specialized or nonspecialized treatment. Identifying worsening symptoms earlier using mobile and wearable sensors may lead to earlier intervention. Most studies on predicting depression using sensor-based data are geared toward the adult population. Very few studies look into predicting depression in adolescents.ObjectiveThe aim of our work was to study passively sensed data from adolescents with depression and investigate the predictive capabilities of 2 machine learning approaches to predict depression scores and change in depression levels in adolescents. This work also provided an in-depth analysis of sensor features that serve as key indicators of change in depressive symptoms and the effect of variation of data samples on model accuracy levels.MethodsThis study included 55 adolescents with symptoms of depression aged 12 to 17 years. Each participant was passively monitored through smartphone sensors and Fitbit wearable devices for 24 weeks. Passive sensors collected call, conversation, location, and heart rate information daily. Following data preprocessing, 67% (37/55) of the participants in the aggregated data set were analyzed. Weekly Patient Health Questionnaire-9 surveys answered by participants served as the ground truth. We applied regression-based approaches to predict the Patient Health Questionnaire-9 depression score and change in depression severity. These approaches were consolidated using universal and personalized modeling strategies. The universal strategies consisted of Leave One Participant Out and Leave Week X Out. The personalized strategy models were based on Accumulated Weeks and Leave One Week One User Instance Out. Linear and nonlinear machine learning algorithms were trained to model the data.ResultsWe observed that personalized approaches performed better on adolescent depression prediction compared with universal approaches. The best models were able to predict depression score and weekly change in depression level with root mean squared errors of 2.83 and 3.21, respectively, following the Accumulated Weeks personalized modeling strategy. Our feature importance investigation showed that the contribution of screen-, call-, and location-based features influenced optimal models and were predictive of adolescent depression.ConclusionsThis study provides insight into the feasibility of using passively sensed data for predicting adolescent depression. We demonstrated prediction capabilities in terms of depression score and change in depression level. The prediction results revealed that personalized models performed better on adolescents than universal approaches. Feature importance provided a better understanding of depression and sensor data. Our findings can help in the development of advanced adolescent depression predictions.
| S-EPMC9270714 | biostudies-literature