Physiotherapy is a critical element in successful conservative management of low back pain (LBP). The aim of this study was to develop and evaluate a system with wearable inertial sensors to objectively detect sitting postures and performance of unsupervised exercises containing movement in multiple planes (flexion, extension, rotation).

A set of 8 inertial sensors were placed on 19 healthy adult subjects. Data was acquired as they performed 7 McKenzie low-back exercises and 3 sitting posture positions. This data was used to train two models (Random Forest (RF) and XGBoost (XGB)) using engineered time series features. In addition, a convolutional neural network (CNN) was trained directly on the time series data. A feature importance analysis was performed to identify sensor locations and channels that contributed 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 the best performing algorithm(s) for exercise classification. Models were evaluated using F1-score in a 10-fold cross validation approach.

The optimal hardware configuration was identified as a 3-sensor setup using lower back, left thigh, and right ankle sensors with acceleration, gyroscope, and magnetometer channels. The XBG model achieved the highest exercise (F1=0.94±0.03) and posture (F1=0.90±0.11) classification scores. The CNN achieved similar results with the same sensor locations, using only the accelerometer and gyroscope channels for exercise classification (F1=0.94±0.02) and the accelerometer channel alone for posture classification (F1=0.91±0.03).

This study demonstrates the potential of a 3-sensor lower body wearable solution (e.g. smart pants) that can identify proper sitting postures and exercises in multiple planes, suitable for low back pain. This technology has the potential to improve the effectiveness of LBP rehabilitation by facilitating quantitative feedback, early problem diagnosis, and possible remote monitoring.

Access to health care, including physiotherapy, is increasingly occurring through virtual formats. At-home adherence to physical therapy programs is often poor and few tools exist to objectively measure low back physiotherapy exercise participation without the direct supervision of a medical professional. The aim of this study was to develop and evaluate the potential for performing automatic, unsupervised video-based monitoring of at-home low back physiotherapy exercises using a single mobile phone camera.

24 healthy adult subjects performed seven exercises based on the McKenzie low back physiotherapy program while being filmed with two smartphone cameras. Joint locations were automatically extracted using an open-source pose estimation framework. Engineered features were extracted from the joint location time series and used to train a support vector machine classifier (SVC). A convolutional neural network (CNN) was trained directly on the joint location time series data to classify exercises based on a recording from a single camera. The models were evaluated using a 5-fold cross validation approach, stratified by subject, with the class-balanced accuracy used as the performance metric.

Optimal performance was achieved when using a total of 12 pose estimation landmarks from the upper and lower body, with the SVC model achieving a classification accuracy of 96±4% and the CNN model an accuracy of 97±2%.

This study demonstrates the feasibility of using a smartphone camera and a supervised machine learning model to effectively assess at-home low back physiotherapy adherence. This approach could provide a low-cost, scalable method for tracking adherence to physical therapy exercise programs in a variety of settings.

Aims

An objective technological solution for tracking adherence to at-home shoulder physiotherapy is important for improving patient engagement and rehabilitation outcomes, but remains a significant challenge. The aim of this research was to evaluate performance of machine-learning (ML) methodologies for detecting and classifying inertial data collected during in-clinic and at-home shoulder physiotherapy exercise.

Participation in a physical therapy program is considered one of the greatest predictors for successful conservative management of common shoulder disorders, however, adherence to standard exercise protocols is often poor (around 50%) and typically worse for unsupervised home exercise programs. Currently, there are limited tools available for objective measurement of adherence and performance of shoulder rehabilitation 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. We hypothesize that shoulder physiotherapy exercises can be classified by analyzing the temporal sequence of inertial sensor outputs from a smartwatch worn on the extremity performing the exercise.

Twenty healthy adult subjects with no prior shoulder disorders performed seven exercises from a standard evidence-based rotator cuff physiotherapy protocol: pendulum, abduction, forward elevation, internal/external rotation and trapezius extension with a resistance band, and a weighted bent-over row. Each participant performed 20 repetitions of each exercise bilaterally under the supervision of an orthopaedic surgeon, while 6-axis inertial sensor data was collected at 50 Hz from an Apple Watch. Using the scikit-learn and keras platforms, four supervised learning algorithms were trained to classify the exercises: k-nearest neighbour (k-NN), random forest (RF), support vector machine classifier (SVC), and a deep convolutional recurrent neural network (CRNN). Algorithm performance was evaluated using 5-fold cross-validation stratified first temporally and then by subject.

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± 0.2%). The subject stratified cross validation, which evaluated classifier performance on unseen subjects, yielded lower accuracies scores again with CRNN performing best (88.9 ± 1.6%).

This proof-of concept study demonstrates the feasibility of a smartwatch device and machine learning approach to more easily monitor and assess the at-home adherence of shoulder physiotherapy exercise protocols. Future work will focus on translation of this technology to the clinical setting and evaluating exercise classification in shoulder disorder populations.

Anatomic studies have demonstrated that bipolar glenoid and humeral bone loss have a cumulative impact on shoulder instability, and that these defects may engage in functional positions depending on their size, location, and orientation, potentially resulting in failure of stabilisation procedures. Determining which lesions pose a risk for engagement remains a challenge, with Itoi's 3DCT based glenoid track method and arthroscopic assessment being the accepted approaches at this time. The purpose of this study was to investigate the interaction of humeral and glenoid bone defects on shoulder engagement in a cadaveric model. Two alternative approaches to predicting engagement were evaluated; 1) CT scanning the shoulder in abduction and external rotation 2) measurement of Bankart lesion width and a novel parameter, the intact anterior articular angle (IAAA), on conventional 2D multi-plane reformats.

Hill-Sachs and Bony Bankart defects of varying size were created in 12 cadaveric upper limbs, producing 45 bipolar defect combinations. The shoulders were assessed for engagement using cone beam CT in various positions of function, from 30 to 90 degrees of both abduction and external rotation. The humeral and glenoid defects were characterised by measurement of their size, location, and orientation. The abduction external rotation scan and 2D IAAA approaches were compared to the glenoid track method for predicting engagement.

Engagement was predicted by Itoi's glenoid track method in 24 of 45 specimens (53%). The abduction external rotation CT scan performed at 60 degrees of glenohumeral abduction (corresponding to 90 degrees of abduction relative to the trunk) and 90 degrees of external rotation predicted engagement accurately in 43 of 45 specimens (96%), with sensitivity and specificity of 92% and 100% respectively. A logistic model based on Bankart width and IAAA provided a prediction accuracy of 89% with sensitivity and specificity of 91% and 87%. Inter-rater agreement was excellent (Kappa = 1) for classification of engagement on the abduction external rotation CT, and good (intraclass correlation = 0.73) for measurement of IAAA.

Bipolar lesions at risk for engagement can be identified using an abduction external rotation CT scan at 60 degrees of glenohumeral abduction and 90 degrees of external rotation, or by performing 2D measurements of Bankart width and IAAA on conventional CT multi-plane reformats. This information will be useful for peri-operative decision making around surgical techniques for shoulder stabilisation in the setting of bipolar bone defects.