David Burns

Dr. David Burns


Research Focus & Metrics

Academic Career Length

35Years (1992-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2018 in Physiological Measurement
Verified
Journal Article
Closed access
PDF file
DBDavid Burns
David Burns
NLNathan Eric Leung
Nathan Eric Leung
MHMichael Hardisty
Michael Hardisty
CWCari M Whyne
Cari M Whyne
PHPatrick Henry
Patrick Henry
SMStewart McLachlin
Stewart McLachlin
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.

26 October 2018 in Shoulder & Elbow
Verified
Journal Article
Closed access
PDF file
DBDavid Burns
David Burns
TFTym Frank
Tym Frank
CWCari M Whyne
Cari M Whyne
PHPatrick Dg Henry
Patrick Dg Henry
Background: Positioning of the glenoid component is one of the most challenging steps in shoulder arthroplasty, and prosthesis longevity as well as functional outcomes is considered highly dependent on accurate positioning. This review considers the evidence supporting surgical navigation and patient-specific instruments for glenoid implant positioning in anatomic and reverse total shoulder arthroplasty. Methods: A systematic literature search was performed for studies assessing glenoid implant positioning accuracy as measured by cross-sectional imaging on live subjects or cadaver models. Meta-analysis of controlled studies was performed to estimate the primary effects of navigation and patient-specific instruments on glenoid implant positioning error. Meta-analysis of absolute positioning outcomes was also performed for each group incorporating data from controlled and uncontrolled studies. Results: Nine studies, four controlled and five uncontrolled, with 258 total subjects were included in the analysis. Meta-analysis of controlled studies supported that both navigation and patient-specific instruments had a moderate statistically significant effect on improving glenoid implant positioning outcomes. Meta-analysis of absolute positioning outcomes demonstrates glenoid implant positioning with standard instrumentation results in a high rate of malposition. Discussion: Navigation and patient-specific instruments improve glenoid positioning outcomes. Whether the improvement in positioning outcomes achieved translate to better clinical outcomes is unknown.

11 March 2021 in JMIR Rehabilitation and Assistive Technologies
Verified
Journal Article
Open access
DBDavid Burns
David Burns
PBPhilip Boyer
Philip Boyer
HRHelen Razmjou
Helen Razmjou
RRRobin Richards
Robin Richards
CWCari Whyne
Cari Whyne
Background: Physiotherapy is considered to be essential for the successful operative and nonoperative management of rotator cuff pathology; however, the extent to which patients adhere to assigned physiotherapy activities and how this impacts recovery is unknown. Objective: The purpose of this study was to measure the rate and patterns of participation in physiotherapy for rotator cuff disorders, assess the dose response between physiotherapy activity and recovery, and explore patient factors predictive of physiotherapy participation. Methods: We report a prospective longitudinal study of 42 patients undergoing physiotherapy for symptomatic rotator cuff pathology. The patients were issued a smartwatch that recorded inertial sensor data while they performed physiotherapy exercises both in the clinic and in the home setting. A machine learning approach was used to assess total physiotherapy participation from smartwatch inertial data. Primary outcomes were the Disabilities of the Arm Shoulder and Hand and numeric pain rating scale assessed every 4 weeks until 12 weeks follow-up. The relationships between participation, outcomes, and clinical patient variables were assessed in univariable analyses. Results: Mean physiotherapy exercise participation in clinic and at home were 11 minutes per week and 33 minutes per week, respectively, with patients participating in physiotherapy on 41% of days assigned to treatment. Home physiotherapy participation decreased significantly over time (P=.03). There was a statistically significant and clinically meaningful relationship between cumulative physiotherapy participation and recovery demonstrated by pain scores at 8 weeks (P=.02) and 12 weeks (P=.05) and disability scores at 8 weeks (P=.04) and 12 weeks (P=.04). Low patient expectations and self-efficacy were associated with low rates of physiotherapy participation. Conclusions: There was a low rate of participation in home shoulder physiotherapy exercise, and a statistically and clinically significant dose response of physiotherapy on treatment outcome in patients with rotator cuff pathology. The findings highlight the opportunity to develop novel methods and strategies to improve the participation in and efficacy of physiotherapy exercises for rotator cuff disorders. International Registered Report Identifier (IRRID): RR2-10.2196/17841

29 December 2022 in Sensors
Verified
Journal Article
Open access
PDF file
CAColin Arrowsmith
Colin Arrowsmith
DBDavid Burns
David Burns
TMThomas Mak
Thomas Mak
MHMichael Hardisty
Michael Hardisty
CWCari Whyne
Cari Whyne
Access to healthcare, 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 participation. The aim of this study was to develop and evaluate the potential for performing automatic, unsupervised video-based monitoring of at-home low-back and shoulder physiotherapy exercises using a mobile phone camera. Joint locations were extracted from the videos of healthy subjects performing low-back and shoulder physiotherapy exercises using an open source pose detection framework. A convolutional neural network was trained to classify physiotherapy exercises based on the segments of keypoint time series data. The model’s performance as a function of input keypoint combinations was studied in addition to its robustness to variation in the camera angle. The CNN model achieved optimal performance using a total of 12 pose estimation landmarks from the upper and lower body (low-back exercise classification: 0.995 ± 0.009; shoulder exercise classification: 0.963 ± 0.020). Training the CNN on a variety of angles was found to be effective in making the model robust to variations in video filming angle. This study demonstrates the feasibility of using a smartphone camera and a supervised machine learning model to effectively classify at-home physiotherapy participation and could provide a low-cost, scalable method for tracking adherence to physical therapy exercise programs in a variety of settings.

27 September 2022 in Sensors
Verified
Journal Article
Open access
PDF file
KKKevin Kasa
Kevin Kasa
DBDavid Burns
David Burns
Mitchell GoldenbergMitchell Goldenberg
Mitchell Goldenberg
OSOmar Selim
Omar Selim
CWCari Whyne
Cari Whyne
MHMichael Hardisty
Michael Hardisty
This paper introduces a new dataset of a surgical knot-tying task, and a multi-modal deep learning model that achieves comparable performance to expert human raters on this skill assessment task. Seventy-two surgical trainees and faculty were recruited for the knot-tying task, and were recorded using video, kinematic, and image data. Three expert human raters conducted the skills assessment using the Objective Structured Assessment of Technical Skill (OSATS) Global Rating Scale (GRS). We also designed and developed three deep learning models: a ResNet-based image model, a ResNet-LSTM kinematic model, and a multi-modal model leveraging the image and time-series kinematic data. All three models demonstrate performance comparable to the expert human raters on most GRS domains. The multi-modal model demonstrates the best overall performance, as measured using the mean squared error (MSE) and intraclass correlation coefficient (ICC). This work is significant since it demonstrates that multi-modal deep learning has the potential to replicate human raters on a challenging human-performed knot-tying task. The study demonstrates an algorithm with state-of-the-art performance in surgical skill assessment. As objective assessment of technical skill continues to be a growing, but resource-heavy, element of surgical education, this study is an important step towards automated surgical skill assessment, ultimately leading to reduced burden on training faculty and institutes.

1 March 2021 in Sensors
Verified
Journal Article
Open access
PDF file
PBPhilip Boyer
Philip Boyer
DBDavid Burns
David Burns
CWCari Whyne
Cari Whyne
Out-of-distribution (OOD) in the context of Human Activity Recognition (HAR) refers to data from activity classes that are not represented in the training data of a Machine Learning (ML) algorithm. OOD data are a challenge to classify accurately for most ML algorithms, especially deep learning models that are prone to overconfident predictions based on in-distribution (IIN) classes. To simulate the OOD problem in physiotherapy, our team collected a new dataset (SPARS9x) consisting of inertial data captured by smartwatches worn by 20 healthy subjects as they performed supervised physiotherapy exercises (IIN), followed by a minimum 3 h of data captured for each subject as they engaged in unrelated and unstructured activities (OOD). In this paper, we experiment with three traditional algorithms for OOD-detection using engineered statistical features, deep learning-generated features, and several popular deep learning approaches on SPARS9x and two other publicly-available human activity datasets (MHEALTH and SPARS). We demonstrate that, while deep learning algorithms perform better than simple traditional algorithms such as KNN with engineered features for in-distribution classification, traditional algorithms outperform deep learning approaches for OOD detection for these HAR time series datasets.