Shoulder assessment according to the international classification of functioning by means of inertial sensor technologies: A systematic review

Upper-Limb Movement Quality before and after Surgery in Women with Breast Cancer: An Exploratory Study

(1) Background: This study aimed to describe upper-limb (UL) movement quality parameters in women after breast cancer surgery and to explore their clinical relevance in relation to post-surgical pain and disability. (2) Methods: UL movement quality was assessed in 30 women before and 3 weeks after surgery for breast cancer. Via accelerometer data captured from a sensor located at the distal end of the forearm on the operated side, various movement quality parameters (local dynamic stability, movement predictability, movement smoothness, movement symmetry, and movement variability) were investigated while women performed a cyclic, weighted reaching task. At both test moments, the Quick Disabilities of the Arm, Shoulder, and Hand (Quick DASH) questionnaire was filled out to assess UL disability and pain severity. (3) Results: No significant differences in movement quality parameters were found between the pre-surgical and post-surgical time points. No significant correlations between post-operative UL disability or pain severity and movement quality were found. (4) Conclusions: From this study sample, no apparent clinically relevant movement quality parameters could be derived for a cyclic, weighted reaching task. This suggests that the search for an easy-to-use, quantitative analysis tool for UL qualitative functioning to be used in research and clinical practice should continue.

X-Sens Inertial Sensor Technology-Based Rehabilitation on a Patient With Posterior Cruciate Ligament Avulsion Fracture and Shaft of Femur Fracture: A Case Report

The posterior cruciate ligament (PCL), one of the key ligaments in the knee, serves to prevent backward movement of the tibia relative to the femur. A simultaneous occurrence of a PCL avulsion fracture and a femur shaft fracture in a pediatric patient suggests a complex orthopedic injury resulting from significant trauma to the knee and thigh area. This study describes the rehabilitation process of a 12-year-old female involved in a road traffic accident, who suffered both a midshaft femur fracture and a PCL avulsion fracture. Following surgical procedures, the patient underwent a comprehensive physiotherapy regimen utilizing X-Sens inertial sensor technology. The rehabilitation plan comprised multiple stages targeting pain alleviation, muscle strengthening, flexibility exercises, gait retraining, and balance improvement. Various interventions including contrast baths, cryotherapy, patellar mobilization, isotonic and resistance exercises, and progressive gait training were integrated across different phases of the rehabilitation program. Over subsequent follow-up periods, the patient demonstrated significant enhancements in pain management, range of motion, muscle strength, functional capabilities, and gait metrics. This case report underscores the efficacy of a systematic physiotherapy strategy incorporating advanced technology in the successful recovery from intricate lower limb fractures, underscoring the importance of prompt intervention and multidisciplinary collaboration for optimal patient outcomes.

The effect of myofascial and physical therapy on trunk, shoulder, and elbow movement patterns in women with pain and myofascial dysfunctions after breast cancer surgery: Secondary analyses of a randomized controlled trial

INTRODUCTION

Secondary upper limb dysfunctions are common after breast cancer treatment. Myofascial treatment may be a valuable physical therapy modality for this problem.

OBJECTIVE

To investigate the effect of myofascial therapy in addition to physical therapy on shoulder, trunk, and elbow movement patterns in women with pain and myofascial dysfunctions at the upper limb after breast cancer surgery.

DESIGN

A double-blinded randomized controlled trial.

SETTING

Rehabilitation unit of a university hospital.

PARTICIPANTS

Forty-eight women with persistent pain after finishing breast cancer treatment.

INTERVENTIONS

Over 3 months, all participants received a standard physical therapy program. The experimental (n = 24) and control group (n = 24) received 12 additional sessions of myofascial therapy or placebo therapy, respectively.

MAIN OUTCOME MEASURES

Outcomes of interest were movement patterns of the humerothoracic joint, scapulothoracic joint, trunk, and elbow, measured with an optoelectronic measurement system during the performance of a forward flexion and scaption task. Statistical parametric mapping (SPM) analyses were used for assessing the effect of treatment on movement patterns between both groups (group × time interaction effect).

RESULTS

A significantly decreased protraction and anterior tilting was found after experimental treatment. No beneficial effects on movement patterns of the humerothoracic joint, trunk, or elbow were found.

CONCLUSION

Myofascial therapy in addition to a 12-week standard physical therapy program can decrease scapular protraction and anterior tilting (scapulothoracic joint) during arm movements. Given the exploratory nature of these secondary analyses, the clinical relevance of these results needs to be investigated further.

Conversion of Upper-Limb Inertial Measurement Unit Data to Joint Angles: A Systematic Review

Inertial measurement units (IMUs) have become the mainstay in human motion evaluation outside of the laboratory; however, quantification of 3-dimensional upper limb motion using IMUs remains challenging. The objective of this systematic review is twofold. Firstly, to evaluate computational methods used to convert IMU data to joint angles in the upper limb, including for the scapulothoracic, humerothoracic, glenohumeral, and elbow joints; and secondly, to quantify the accuracy of these approaches when compared to optoelectronic motion analysis. Fifty-two studies were included. Maximum joint motion measurement accuracy from IMUs was achieved using Euler angle decomposition and Kalman-based filters. This resulted in differences between IMU and optoelectronic motion analysis of 4° across all degrees of freedom of humerothoracic movement. Higher accuracy has been achieved at the elbow joint with functional joint axis calibration tasks and the use of kinematic constraints on gyroscope data, resulting in RMS errors between IMU and optoelectronic motion for flexion-extension as low as 2°. For the glenohumeral joint, 3D joint motion has been described with RMS errors of 6° and higher. In contrast, scapulothoracic joint motion tracking yielded RMS errors in excess of 10° in the protraction-retraction and anterior-posterior tilt direction. The findings of this study demonstrate high-quality 3D humerothoracic and elbow joint motion measurement capability using IMUs and underscore the challenges of skin motion artifacts in scapulothoracic and glenohumeral joint motion analysis. Future studies ought to implement functional joint axis calibrations, and IMU-based scapula locators to address skin motion artifacts at the scapula, and explore the use of artificial neural networks and data-driven approaches to directly convert IMU data to joint angles.

Assessing Upper Limb Function in Breast Cancer Survivors Using Wearable Sensors and Machine Learning in a Free-Living Environment

(1) Background: Being able to objectively assess upper limb (UL) dysfunction in breast cancer survivors (BCS) is an emerging issue. This study aims to determine the accuracy of a pre-trained lab-based machine learning model (MLM) to distinguish functional from non-functional arm movements in a home situation in BCS. (2) Methods: Participants performed four daily life activities while wearing two wrist accelerometers and being video recorded. To define UL functioning, video data were annotated and accelerometer data were analyzed using a counts threshold method and an MLM. Prediction accuracy, recall, sensitivity, f1-score, 'total minutes functional activity' and 'percentage functionally active' were considered. (3) Results: Despite a good MLM accuracy (0.77-0.90), recall, and specificity, the f1-score was poor. An overestimation of the 'total minutes functional activity' and 'percentage functionally active' was found by the MLM. Between the video-annotated data and the functional activity determined by the MLM, the mean differences were 0.14% and 0.10% for the left and right side, respectively. For the video-annotated data versus the counts threshold method, the mean differences were 0.27% and 0.24%, respectively. (4) Conclusions: An MLM is a better alternative than the counts threshold method for distinguishing functional from non-functional arm movements. However, the abovementioned wrist accelerometer-based assessment methods overestimate UL functional activity.

Differences in Tridimensional Shoulder Kinematics between Asymptomatic Subjects and Subjects Suffering from Rotator Cuff Tears by Means of Inertial Sensors: A Cross-Sectional Study

Background: The aim of this study was to analyze differences in three-dimensional shoulder kinematics between asymptomatic subjects and patients who were diagnosed with rotator cuff tears. Methods: This cross-sectional study recruited 13 symptomatic subjects and 14 asymptomatic subjects. Data were obtained from three inertial sensors placed on the humerus, scapula and sternum. Kinematic data from the glenohumeral, scapulothoracic and thoracohumeral joints were also calculated. The participants performed shoulder abductions and flexions. The principal angles of movements and resultant vectors in each axis were studied. Results: The glenohumeral joint showed differences in abduction (p = 0.001) and flexion (p = 0.000), while differences in the scapulothoracic joint were only significant during flexion (p = 0.001). The asymptomatic group showed higher velocity values in all sensors for both movements, with the differences being significant (p < 0.007). Acceleration differences were found in the scapula during abduction (p = 0.001) and flexion (p = 0.014), as well as in the sternum only during shoulder abduction (p = 0.022). Conclusion: The results showed kinematic differences between the patients and asymptomatic subjects in terms of the mobility, velocity and acceleration variables, with lower values for the patients.

Optical Motion Capture Systems for 3D Kinematic Analysis in Patients with Shoulder Disorders

Shoulder dysfunctions represent the third musculoskeletal disorder by frequency. However, monitoring the movement of the shoulder is particularly challenging due to the complexity of the joint kinematics. The 3D kinematic analysis with optical motion capture systems (OMCs) makes it possible to overcome clinical tests' shortcomings and obtain objective data on the characteristics and quality of movement. This systematic review aims to retrieve the current knowledge about using OMCs for 3D shoulder kinematic analysis in patients with musculoskeletal shoulder disorders and their corresponding clinical relevance. The Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines were used to improve the reporting of the review. Studies employing OMCs for 3D kinematic analysis in patients with musculoskeletal shoulder disorders were retrieved. Eleven articles were considered eligible for this study. OMCs can be considered a powerful tool in orthopedic clinical research. The high costs and organizing complexities of experimental setups are likely outweighed by the impact of these systems in guiding clinical practice and patient follow-up. However, additional high-quality studies on using OMCs in clinical practice are required, with standardized protocols and methodologies to make comparing clinical trials easier.

Assessing the validity of inertial measurement units for shoulder kinematics using a commercial sensor-software system: A validation study

Background and  Aims

Wearable inertial sensors may offer additional kinematic parameters of the shoulder compared to traditional instruments such as goniometers when elaborate and time-consuming data processing procedures are undertaken. However, in clinical practice simple-real time motion analysis is required to improve clinical reasoning. Therefore, the aim was to assess the criterion validity between a portable "off-the-shelf" sensor-software system (IMU) and optical motion (Mocap) for measuring kinematic parameters during active shoulder movements.

Methods

24 healthy participants (9 female, 15 male, age 29 ± 4 years, height 177 ± 11 cm, weight 73 ± 14 kg) were included. Range of motion (ROM), total range of motion (TROM), peak and mean angular velocity of both systems were assessed during simple (abduction/adduction, horizontal flexion/horizontal extension, vertical flexion/extension, and external/internal rotation) and complex shoulder movements. Criterion validity was determined using intraclass-correlation coefficients (ICC), root mean square error (RMSE) and Bland and Altmann analysis (bias; upper and lower limits of agreement).

Results

ROM and TROM analysis revealed inconsistent validity during simple (ICC: 0.040-0.733, RMSE: 9.7°-20.3°, bias: 1.2°-50.7°) and insufficient agreement during complex shoulder movements (ICC: 0.104-0.453, RMSE: 10.1°-23.3°, bias: 1.0°-55.9°). Peak angular velocity (ICC: 0.202-0.865, RMSE: 14.6°/s-26.7°/s, bias: 10.2°/s-29.9°/s) and mean angular velocity (ICC: 0.019-0.786, RMSE:6.1°/s-34.2°/s, bias: 1.6°/s-27.8°/s) were inconsistent.

Conclusions

The "off-the-shelf" sensor-software system showed overall insufficient agreement with the gold standard. Further development of commercial IMU-software-solutions may increase measurement accuracy and permit their integration into everyday clinical practice.

Three-Dimensional Kinematics during Shoulder Scaption in Asymptomatic and Symptomatic Subjects by Inertial Sensors: A Cross-Sectional Study

Shoulder kinematics is a measure of interest in the clinical setting for diagnosis, evaluating treatment, and quantifying possible changes. The aim was to compare shoulder scaption kinematics between symptomatic and asymptomatic subjects by inertial sensors. Methods: Scaption kinematics of 27 subjects with shoulder symptomatology and 16 asymptomatic subjects were evaluated using four inertial sensors placed on the humerus, scapula, forearm, and sternum. Mobility, velocity, and acceleration were obtained from each sensor and the vector norm was calculated from the three spatial axis (x,y,Z). Shoulder function was measured by Upper Limb Functional Index and Disabilities of the Arm, Shoulder, and Hand questionnaires. One way ANOVA was calculated to test differences between the two groups. Effect size was calculated by Cohen’s d with 95% coefficient Intervals. Pearson’s correlation analysis was performed between the vector norms humerus and scapula kinematics against DASH and ULFI results in symptomatic subjects. Results: The asymptomatic group showed higher kinematic values, especially in the humerus and forearm. Symptomatic subjects showed significantly lower values of mobility for scapular protraction-retraction (Cohen’s d 2.654 (1.819–3.489) and anteriorisation-posteriorisation (Cohen’s d 1.195 (0.527–1.863). Values were also lower in symptomatic subjects for velocity in all scapular planes of motion. Negative correlation showed that subjects with higher scores in ULFI or DASH had lower kinematics values. Conclusion: Asymptomatic subjects tend to present greater kinematics in terms of mobility, velocity, and linear acceleration of the upper limb, and lower humerus and scapula kinematics in symptomatic subjects is associated with lower levels of function.

The Ergonomic Association between Shoulder, Neck/Head Disorders and Sedentary Activity: A Systematic Review

Background

Work-associated upper limb and neck disorders are common occupational disorders throughout the world. These disorders are usually observed more in workers who spend a long time sitting, referred to as sedentary activity (SA). The immediate and distorted risk of sedentary-related problems was considered high in Europe, Australia, and the United States. Even though mediation is convenient, it is likely to reduce office workers' risks of developing cervical and upper body pain due to sedentary work. This systematic review addresses risk factors and evaluates the relationship between SA and upper body disorders in office workers (i.e., shoulder and neck/head).

Methods

PubMed, Scopus, and Web of Science were searched for articles published between January 2010 and August 2021 in the English language. The three keywords “sedentary,” “upper body elements,” and “work” (and their derivatives) were searched to identify studies and carry out this systematic review. The articles were searched so that all three keywords or at least a derivation of each keyword should appear. Findings. Of the 40 articles that met the enclosure criteria, 32 studies examined the association of SA and upper body elements during both office and computer work. However, three articles were evaluated in the sit-stand work environment, and in the remaining five studies, one was evaluated during teaching, two during hospital work, and two during mixed working conditions.

Conclusions

Research related to SA focuses mainly on extended risk factors, but there was no focus on other aspects, such as muscle and tendon contractions. As there is a convincing connection between SA and the upper body, our close examination identifies the need to institutionalize a system for collecting, analyzing, and describing the impact and short-term effects of SA on the upper body. Additionally, some suggestions were made to minimize the risk in a sedentary working environment.

Assessing Smoothness of Arm Movements With Jerk: A Comparison of Laterality, Contraction Mode and Plane of Elevation. A Pilot Study

Measuring the quality of movement is a need and a challenge for clinicians. Jerk, defined as the quantity of acceleration variation, is a kinematic parameter used to assess the smoothness of movement. We aimed to assess and compare jerk metrics in asymptomatic participants for 3 important movement characteristics that are considered by clinicians during shoulder examination: dominant and non-dominant side, concentric and eccentric contraction mode, and arm elevation plane. In this pilot study, we measured jerk metrics by using Xsens^® inertial measurement units strapped to the wrists for 11 different active arm movements (ascending and lowering phases): 3 bilateral maximal arm elevations in sagittal, scapular and frontal plane; 2 unilateral functional movements (hair combing and low back washing); and 2 unilateral maximal arm elevations in sagittal and scapular plane, performed with both arms alternately, right arm first. Each arm movement was repeated 3 times successively and the whole procedure was performed 3 times on different days. The recorded time series was segmented with semi-supervised algorithms. Comparisons involved the Wilcoxon signed rank test (p < 0.05) with Bonferroni correction. We included 30 right-handed asymptomatic individuals [17 men, mean (SD) age 31.9 (11.4) years]. Right jerk was significantly less than left jerk for bilateral arm elevations in all planes (all p < 0.05) and for functional movement (p < 0.05). Jerk was significantly reduced during the concentric (ascending) phase than eccentric (lowering) phase for bilateral and unilateral right and left arm elevations in all planes (all p < 0.05). Jerk during bilateral arm elevation was significantly reduced in the sagittal and scapular planes versus the frontal plane (both p < 0.01) and in the sagittal versus scapular plane (p < 0.05). Jerk during unilateral left arm elevation was significantly reduced in the sagittal versus scapular plane (p < 0.05). Jerk metrics did not differ between sagittal and scapular unilateral right arm elevation. Using inertial measurement units, jerk metrics can well describe differences between the dominant and non-dominant arm, concentric and eccentric modes and planes in arm elevation. Jerk metrics were reduced during arm movements performed with the dominant right arm during the concentric phase and in the sagittal plane. Using IMUs, jerk metrics are a promising method to assess the quality of basic shoulder movement.

Assessment of shoulder range of motion using a commercially available wearable sensor-a validation study

BACKGROUND

Our study aims to validate a commercially available inertial measurement unit (IMU) system against a standard laboratory-based optical motion capture (OMC) system for shoulder measurements in a clinical context.

METHODS

The validation analyses were conducted on 19 healthy male volunteers. Twelve reflective markers were placed on each participant's trunk, scapula and across the arm and one IMU was attached via a self-adhesive strap on the forearm. A single tester simultaneously collected shoulder kinematic data for four shoulder movements: flexion, extension, external rotation, and abduction. Agreement between OMC system and IMU measurements was assessed with Bland-Altman analyses. Secondary analysis included mean biases, root mean square error (RMSE) analysis and Welch's t-test.

RESULTS

Bland-Altman limits of agreement (LoA) exceeded the acceptable range of mean difference for 95% of the population (-22.27°, 11.31°). The mean bias showed high levels of agreement within 8° for all four movements. More than 60% of participants demonstrated mean bias less than 10° between methods. Statistically significant differences were found between measurements for abduction (P<0.001) and flexion (P=0.027) but not for extension and external rotation (P≥0.05).

CONCLUSIONS

Our study shows preliminary evidence for acceptable accuracy of a commercially available IMU against an OMC system for assessment of shoulder movements by a single tester. The IMU also exhibits similar whole degree of error compared to a standard goniometer with potential for application in remote rehabilitation.

Measuring 3D In-vivo Shoulder Kinematics using Biplanar Videoradiography

The shoulder is one of the human body's most complex joint systems, with motion occurring through the coordinated actions of four individual joints, multiple ligaments, and approximately 20 muscles. Unfortunately, shoulder pathologies (e.g., rotator cuff tears, joint dislocations, arthritis) are common, resulting in substantial pain, disability, and decreased quality of life. The specific etiology for many of these pathologic conditions is not fully understood, but it is generally accepted that shoulder pathology is often associated with altered joint motion. Unfortunately, measuring shoulder motion with the necessary level of accuracy to investigate motion-based hypotheses is not trivial. However, radiographic-based motion measurement techniques have provided the advancement necessary to investigate motion-based hypotheses and provide a mechanistic understanding of shoulder function. Thus, the purpose of this article is to describe the approaches for measuring shoulder motion using a custom biplanar videoradiography system. The specific objectives of this article are to describe the protocols to acquire biplanar videoradiographic images of the shoulder complex, acquire CT scans, develop 3D bone models, locate anatomical landmarks, track the position and orientation of the humerus, scapula, and torso from the biplanar radiographic images, and calculate the kinematic outcome measures. In addition, the article will describe special considerations unique to the shoulder when measuring joint kinematics using this approach.

Wireless Motion Capture System for Upper Limb Rehabilitation

This work is devoted to the presentation of a Wireless Sensor System implementation for upper limb rehabilitation to function as a complementary system for a patient’s progress supervision during rehabilitation exercises. A cost effective motion capture sensor node composed by a 9 Degrees-of-Freedom (DoF) Inertial Measurement Unit (IMU) is mounted on the patient’s upper limb segments and sends wirelessly the corresponding measured signals to a base station. The sensor orientation and the upper limb individual segments movement in 3-Dimensional (3D) space are derived by processing the sensors’ raw data. For the latter purpose, a biomechanical model which resembles that of a kinematic model of a robotic arm based on the Denavit-Hartenberg (DH) configuration is used to approximate in real time the upper limb movements. The joint angles of the upper limb model are estimated from the extracted sensor node’s orientation angles. The experimental results of a human performing common rehabilitation exercises using the proposed motion capture sensor node are compared with the ones using an off-the-shelf sensor. This comparison results to very low error rates with the root mean square error (RMSE) being about 0.02 m.

Patterns of enhancement in paretic shoulder kinematics after stroke with musical cueing

Musical cueing has been widely utilised in post-stroke motor rehabilitation; however, the kinematic evidence on the effects of musical cueing is sparse. Further, the element-specific effects of musical cueing on upper-limb movements have rarely been investigated. This study aimed to kinematically quantify the effects of no auditory, rhythmic auditory, and melodic auditory cueing on shoulder abduction, holding, and adduction in patients who had experienced hemiparetic stroke. Kinematic data were obtained using inertial measurement units embedded in wearable bands. During the holding phase, melodic auditory cueing significantly increased the minimum Euler angle and decreased the range of motion compared with the other types of cueing. Further, the root mean square error in the angle measurements was significantly smaller and the duration of movement execution was significantly shorter during the holding phase when melodic auditory cueing was provided than when the other types of cueing were used. These findings indicated the important role of melodic auditory cueing for enhancing movement positioning, variability, and endurance. This study provides the first kinematic evidence on the effects of melodic auditory cueing on kinematic enhancement, thus suggesting the potential use of pitch-related elements in psychomotor rehabilitation.

Adherence Tracking With Smart Watches for Shoulder Physiotherapy in Rotator Cuff Pathology: Protocol for a Longitudinal Cohort Study

Background

Physiotherapy is essential for the successful rehabilitation of common shoulder injuries and following shoulder surgery. Patients may receive some training and supervision for shoulder physiotherapy through private pay or private insurance, but they are typically responsible for performing most of their physiotherapy independently at home. It is unknown how often patients perform their home exercises and if these exercises are performed correctly without supervision. There are no established tools for measuring this. It is, therefore, unclear if the full benefit of shoulder physiotherapy treatments is being realized.

Objective

The proposed research will (1) validate a smartwatch and machine learning (ML) approach for evaluating adherence to shoulder exercise participation and technique in a clinical patient population with rotator cuff pathology; (2) quantify the rate of home physiotherapy adherence, determine the effects of adherence on recovery, and identify barriers to successful adherence; and (3) develop and pilot test an ethically conscious adherence-driven rehabilitation program that individualizes patient care based on their capacity to effectively participate in their home physiotherapy.

Methods

This research will be conducted in 2 phases. The first phase is a prospective longitudinal cohort study, involving 120 patients undergoing physiotherapy for rotator cuff pathology. Patients will be issued a smartwatch that will record 9-axis inertial sensor data while they perform physiotherapy exercises both in the clinic and in the home setting. The data collected in the clinic under supervision will be used to train and validate our ML algorithms that classify shoulder physiotherapy exercise. The validated algorithms will then be used to assess home physiotherapy adherence from the inertial data collected at home. Validated outcome measures, including the Disabilities of the Arm, Shoulder, and Hand questionnaire; Numeric Pain Rating Scale; range of motion; shoulder strength; and work status, will be collected pretreatment, monthly through treatment, and at a final follow-up of 12 months. We will then relate improvement in patient outcomes to measured physiotherapy adherence and patient baseline variables in univariate and multivariate analyses. The second phase of this research will involve the evaluation of a novel rehabilitation program in a cohort of 20 patients. The program will promote patient physiotherapy engagement via the developed technology and support adherence-driven care decisions.

Results

As of December 2019, 71 patients were screened for enrollment in the noninterventional validation phase of this study; 65 patients met the inclusion and exclusion criteria. Of these, 46 patients consented and 19 declined to participate in the study. Only 2 patients de-enrolled from the study and data collection is ongoing for the remaining 44.

Conclusions

This study will provide new and important insights into shoulder physiotherapy adherence, the relationship between adherence and recovery, barriers to better adherence, and methods for addressing them.

International Registered Report Identifier (IRRID)

DERR1-10.2196/17841

Evaluation of Machine Learning Models for Classifying Upper Extremity Exercises Using Inertial Measurement Unit-Based Kinematic Data

The amount of home-based exercise prescribed by a physical therapist is difficult to monitor. However, the integration of wearable inertial measurement unit (IMU) devices can aid in monitoring home exercise by analyzing exercise biomechanics. The objective of this study is to evaluate machine learning models for classifying nine different upper extremity exercises, based upon kinematic data captured from an IMU-based device. Fifty participants performed one compound and eight isolation exercises with their right arm. Each exercise was performed ten times for a total of 4500 trials. Joint angles were calculated using IMUs that were placed on the hand, forearm, upper arm, and torso. Various machine learning models were developed with different algorithms and train-test splits. Random forest models with flattened kinematic data as a feature had the greatest accuracy (98.6%). Using triaxial joint range of motion as the feature set resulted in decreased accuracy (91.9%) with faster speeds. Accuracy did not decrease below 90% until training size was decreased to 5% from 50%. Accuracy decreased (88.7%) when splitting data by participant. Upper extremity exercises can be classified accurately using kinematic data from a wearable IMU device. A random forest classification model was developed that quickly and accurately classified exercises. Sampling frequency and lower training splits had a modest effect on performance. When the data were split by subject stratification, larger training sizes were required for acceptable algorithm performance. These findings set the basis for more objective and accurate measurements of home-based exercise using emerging healthcare technologies.

Assessment of Scapulothoracic, Glenohumeral, and Elbow Motion in Adhesive Capsulitis by Means of Inertial Sensor Technology: A Within-Session, Intra-Operator and Inter-Operator Reliability and Agreement Study

Adhesive capsulitis (AC) is a glenohumeral (GH) joint condition, characterized by decreased GH joint range of motion (ROM) and compensatory ROM in the elbow and scapulothoracic (ST) joint. To evaluate AC progression in clinical settings, objective movement analysis by available systems would be valuable. This study aimed to assess within-session and intra- and inter-operator reliability/agreement of such a motion capture system. The MVN-Awinda® system from Xsens Technologies (Enschede, The Netherlands) was used to assess ST, GH, and elbow ROM during four tasks (GH external rotation, combing hair, grasping a seatbelt, placing a cup on a shelf) in 10 AC patients (mean age = 54 (±6), 7 females), on two test occasions (accompanied by different operators on second occasion). Standard error of measurements (SEMs) were below 1.5° for ST pro-retraction and 4.6° for GH in-external rotation during GH external rotation; below 6.6° for ST tilt, 6.4° for GH flexion-extension, 7.1° for elbow flexion-extension during combing hair; below 4.4° for GH ab-adduction, 13° for GH in-external rotation, 6.8° for elbow flexion-extension during grasping the seatbelt; below 11° for all ST and GH joint rotations during placing a cup on a shelf. Therefore, to evaluate AC progression, inertial sensors systems can be applied during the execution of functional tasks.

Instrumented assessment of shoulder function: A study of inertial sensor based methods

BACKGROUND

Inertial sensors have the potential to provide objective and practical methods to assess joint and limb function in the clinical setting. The aim of this study is to evaluate the psychometric properties of inertial sensor metrics in the assessment of patients with subacromial shoulder pain.

METHODS

25 patients with unilateral subacromial shoulder pain and 50 control subjects were recruited. Assessments were carried out on both shoulders for all participants during a short movement procedure. Patients had assessments repeated after receiving three months of physiotherapy. Inertial metrics evaluated included a smoothness measure and speed and power scores derived from the range of angular velocity and acceleration profiles. Individual shoulder scores and asymmetry scores were both evaluated in terms of reliability, known-group validity, convergent validity and responsiveness.

FINDINGS

Regression analysis identified age to be a significant predictor for all scores, therefore an age matched sub-cohort of control subjects was used for comparative analyses. All scores demonstrated inter-rater reliability (ICC = 0.48-0.82), were able to differentiate pathological from healthy shoulders (AUC = 0.62-0.91) and displayed significant changes following treatment. Scores derived from the range of acceleration and velocity profiles demonstrated the largest effect sizes (Cohens d = 0.8-1.35), and displayed the highest correlation with the Oxford Shoulder Score (r = -0.40 - -0.58).

INTERPRETATION

The scores investigated demonstrate good psychometric properties and have potential to complement existing methods of assessment in the clinical or research setting. Further work is required to fully understand their clinical relevance and optimise assessment methods and interpretation.

Efficient Multiaxial Shoulder-Motion Tracking Based on Flexible Resistive Sensors Applied to Exosuits

This article describes the performance of a flexible resistive sensor network to track shoulder motion. This system monitors every gesture of the human shoulder in its range of motion except rotations around the longitudinal axis of the arm. In this regard, the design considers the movement of the glenohumeral, acromioclavicular, sternoclavicular, and scapulothoracic joints. The solution presented in this work considers several sensor configurations and compares its performance with a set of inertial measurement units (IMUs). These devices have been put together in a shoulder suit with Optitrack visual markers in order to be used as pose ground truth. Optimal configurations of flexible resistive sensors, in terms of accuracy requirements and number of sensors, have been obtained by applying principal component analysis techniques. The data provided by each configuration are then mapped onto the shoulder pose by using neural network algorithms. According to the results shown in this article, a set of flexible resistive sensors can be an adequate alternative to IMUs for multiaxial shoulder pose tracking in open spaces. Furthermore, the system presented can be easily embedded in fabric or wearable devices without obstructing the user's motion.

Wearable technology in stroke rehabilitation: towards improved diagnosis and treatment of upper-limb motor impairment

Stroke is one of the main causes of long-term disability worldwide, placing a large burden on individuals and society. Rehabilitation after stroke consists of an iterative process involving assessments and specialized training, aspects often constrained by limited resources of healthcare centers. Wearable technology has the potential to objectively assess and monitor patients inside and outside clinical environments, enabling a more detailed evaluation of the impairment and allowing the individualization of rehabilitation therapies. The present review aims to provide an overview of wearable sensors used in stroke rehabilitation research, with a particular focus on the upper extremity. We summarize results obtained by current research using a variety of wearable sensors and use them to critically discuss challenges and opportunities in the ongoing effort towards reliable and accessible tools for stroke rehabilitation. Finally, suggestions concerning data acquisition and processing to guide future studies performed by clinicians and engineers alike are provided.

Adherence monitoring of rehabilitation exercise with inertial sensors: A clinical validation study

BACKGROUND

Rehabilitation has an established role in the management of a wide range of musculoskeletal conditions. Much of this treatment relies on self-directed exercises at home, where adherence of execution is unknown. Demonstrating treatment fidelity is necessary to draw conclusions about the efficacy of rehabilitation interventions in both clinical and research settings. There is a lack of tools and methods to achieve this.

RESEARCH QUESTION

This study aims to evaluate the feasibility of using a single inertial sensor to recognise and classify shoulder rehabilitation activity using supervised machine learning techniques.

METHODS

Twenty patients with shoulder pain were monitored performing five rehabilitation exercises routinely prescribed for their condition. Accelerometer, gyroscope and magnetometer data were collected via a device mounted onto an arm sleeve. Non-specific motion data was included in the analysis. Time and frequency domain features were calculated from labelled data segments and ranked in terms of their predictive importance using the ReliefF algorithm. Selected features were used to train four supervised learning algorithms: decision tree, k-nearest neighbour, support vector machine and random forests. Performance of algorithms in accurately classifying exercise activity was evaluated with ten-fold cross-validation and leave-one-subject-out-validation methods.

RESULTS

Optimal predictive accuracies for ten-fold cross-validation (97.2%) and leave-one-subject-out-validation (80.5%) were achieved by support vector machine and random forests algorithms, respectively. Time domain features derived from accelerometer, magnetometer and orientation data streams were shown to have the highest predictive value for classifying rehabilitation activity.

SIGNIFICANCE

Classification models performed well in differentiating patient exercise activity from non-specific movement and identifying specific exercise type using inertial sensor data. A clinically useful account of home rehabilitation activity will help guide treatment strategies and facilitate methods to improve patient engagement. Future work should focus on evaluating the performance of such systems in natural and unsupervised settings.

Shoulder physiotherapy exercise recognition: machine learning the inertial signals from a smartwatch

OBJECTIVE

Participation in a physical therapy program is considered one of the greatest predictors of successful conservative management of common shoulder disorders. However, adherence to these protocols is often poor and typically worse for unsupervised home exercise programs. Currently, there are limited tools available for objective measurement of adherence in the home setting. The goal of this study was to develop and evaluate the potential for performing home shoulder physiotherapy monitoring using a commercial smartwatch.

APPROACH

Twenty healthy adult subjects with no prior shoulder disorders performed seven exercises from an evidence-based rotator cuff physiotherapy protocol, while 6-axis inertial sensor data was collected from the active extremity. Within an activity recognition chain (ARC) framework, four supervised learning algorithms were trained and optimized to classify the exercises: k-nearest neighbor (k-NN), random forest (RF), support vector machine classifier (SVC), and a convolutional recurrent neural network (CRNN). Algorithm performance was evaluated using 5-fold cross-validation stratified first temporally and then by subject.

MAIN RESULTS

Categorical classification accuracy was above 94% for all algorithms on the temporally stratified cross validation, with the best performance achieved by the CRNN algorithm (99.4%). The subject stratified cross validation, which evaluated classifier performance on unseen subjects, yielded lower accuracies scores again with CRNN performing best (88.9%).

SIGNIFICANCE

This proof of concept study demonstrates the technical feasibility of a smartwatch device and supervised machine learning approach to more easily monitor and assess the at-home adherence of shoulder physiotherapy exercise protocols.