Measuring Adherence to Home Shoulder Physiotherapy With Artificial Intelligence

NCT ID: NCT04629417

Last Updated: 2025-08-07

Basic Information

• Recruitment Status: COMPLETED
• Clinical Phase: NA
• Total Enrollment: 103 participants
• Study Classification: INTERVENTIONAL
• Study Start Date: 2019-05-14
• Study Completion Date: 2024-02-16

Brief Summary

An important part of recovery for shoulder injuries, is sticking to the exercise regimen that is prescribed by a physiotherapist. Currently, there is no proper way to measure whether patients are correcting doing their prescribed exercises at home. Researchers at Sunnybrook have tested out a Smart Physiotherapy Recognition System (SPARS), which consists of a watch that patients can wear while they are performing their physiotherapy exercises. The watch aims to learn how the exercises are done correctly when worn during supervised physiotherapy sessions, and then to record and compare whether those same exercises are being done correctly in a home setting. The main objectives of this study aims to test whether the SPARS system can effectively measure whether physiotherapy exercises are being done properly when they are done without physiotherapist supervision. Secondly, to examine whether the recovery process after shoulder injuries is improved if patients perform the physiotherapy exercises correctly.

Detailed Description

A research assistant will conduct in-person data collection on 120 patients, by recording patients' exercises during their supervised physiotherapy sessions each week using the SPARS smart watch. Each patient will wear smart watch on their affected arm only when performing prescribed exercises, and the watch will start recording inertial sensor data once the patient puts the watch on. The injured worker population will be recruited from referrals made to the Sunnybrook Working Condition Program (WCP) at the Holland Centre for a work-related shoulder injury. The patient population that is being funded by OHIP, will be recruited from referrals Sunnybrook Shoulder and Upper Extremity Program. Data collection will be collected at baseline (at time of informed consent), and at each supervised physiotherapy session during the course of a patient's treatment. A research assistant will be required to attend a minimum of one supervised physiotherapy session for each patient every two weeks, and record exercise type and technique, alongside the inertial data collection, based on feedback from the treating physiotherapist. Follow-up outcomes such as surveys and shoulder testing will be done at 6 weeks, monthly at a maximum of 3 months (OHIP-patients) and 5 months (WSIB) patients, final treatment session (if different than maximum amount), and 1 year after.

Conditions

Rotator Cuff Pathology

Study Design

• Allocation Method: NON_RANDOMIZED
• Intervention Model: PARALLEL
• Primary Study Purpose: TREATMENT
• Blinding Strategy: NONE

Study Groups

Injured Worker Population

Participants that have a confirmed rotator cuff pathology, and are undergoing physiotherapy at the Holland Centre for a work-related shoulder injury as part of the Working Condition Program.

Group Type: EXPERIMENTAL

Smart Physiotherapy Activity Recognition System (SPARS)

Intervention Type: DEVICE

Wearable smart watch that records inertial data such as (accelerometer, gyroscope magnetometer) while patients are performing physiotherapy exercises.

OHIP (funded) Patient Population

Participants that have a confirmed rotator cuff pathology, and are undergoing physiotherapy at the Holland Centre as part of the Shoulder Program.

Group Type: ACTIVE_COMPARATOR

Smart Physiotherapy Activity Recognition System (SPARS)

Intervention Type: DEVICE

Wearable smart watch that records inertial data such as (accelerometer, gyroscope magnetometer) while patients are performing physiotherapy exercises.

Interventions

Smart Physiotherapy Activity Recognition System (SPARS)

Wearable smart watch that records inertial data such as (accelerometer, gyroscope magnetometer) while patients are performing physiotherapy exercises.

Intervention Type: DEVICE

Eligibility Criteria

Inclusion Criteria

1. Males and females over the age of 18

2. Be diagnosed with rotator cuff tendinosis, shoulder impingement syndrome or a rotator cuff tear

3. Will be undergoing planned conservative management

4. Be able to participate in home physiotherapy exercises

Exclusion Criteria

1. Upper extremity neurological deficit

2. Have had a previous failed surgery on the shoulder that is currently being treated

3. Undergoing simultaneous treatment for both shoulders

• Minimum Eligible Age: 18 Years
• Eligible Sex: ALL
• Accepts Healthy Volunteers: No

Sponsors

Sunnybrook Health Sciences Centre

OTHER

Sponsor Role: lead

Responsible Party

Responsibility Role: SPONSOR

Principal Investigators

Robin Richards

Role: PRINCIPAL_INVESTIGATOR

Sunnybrook Health Sciences Centre

Locations

Sunnybrook Holland Orthopaedic & Arthritic Centre

Toronto, Ontario, Canada

Countries

Canada

References

Littlewood C, Bateman M, Clark D, Selfe J, Watkinson D, Walton M, Funk L. Rehabilitation following rotator cuff repair: a systematic review. Shoulder Elbow. 2015 Apr;7(2):115-24. doi: 10.1177/1758573214567702. Epub 2015 Jan 29.

Reference Type: BACKGROUND

PMID: 27582966 (View on PubMed)

Thomson S, Jukes C, Lewis J. Rehabilitation following surgical repair of the rotator cuff: a systematic review. Physiotherapy. 2016 Mar;102(1):20-8. doi: 10.1016/j.physio.2015.08.003. Epub 2015 Sep 8.

Reference Type: BACKGROUND

PMID: 26510584 (View on PubMed)

Jack K, McLean SM, Moffett JK, Gardiner E. Barriers to treatment adherence in physiotherapy outpatient clinics: a systematic review. Man Ther. 2010 Jun;15(3):220-8. doi: 10.1016/j.math.2009.12.004. Epub 2010 Feb 16.

Reference Type: BACKGROUND

PMID: 20163979 (View on PubMed)

Faber M, Andersen MH, Sevel C, Thorborg K, Bandholm T, Rathleff M. The majority are not performing home-exercises correctly two weeks after their initial instruction-an assessor-blinded study. PeerJ. 2015 Jul 21;3:e1102. doi: 10.7717/peerj.1102. eCollection 2015.

Reference Type: BACKGROUND

PMID: 26244112 (View on PubMed)

Bollen JC, Dean SG, Siegert RJ, Howe TE, Goodwin VA. A systematic review of measures of self-reported adherence to unsupervised home-based rehabilitation exercise programmes, and their psychometric properties. BMJ Open. 2014 Jun 27;4(6):e005044. doi: 10.1136/bmjopen-2014-005044.

Reference Type: BACKGROUND

PMID: 24972606 (View on PubMed)

Burns DM, Leung N, Hardisty M, Whyne CM, Henry P, McLachlin S. Shoulder physiotherapy exercise recognition: machine learning the inertial signals from a smartwatch. Physiol Meas. 2018 Jul 23;39(7):075007. doi: 10.1088/1361-6579/aacfd9.

Reference Type: BACKGROUND

PMID: 29952759 (View on PubMed)

Beaton DE, Katz JN, Fossel AH, Wright JG, Tarasuk V, Bombardier C. Measuring the whole or the parts? Validity, reliability, and responsiveness of the Disabilities of the Arm, Shoulder and Hand outcome measure in different regions of the upper extremity. J Hand Ther. 2001 Apr-Jun;14(2):128-46.

Reference Type: BACKGROUND

PMID: 11382253 (View on PubMed)

Staples MP, Forbes A, Green S, Buchbinder R. Shoulder-specific disability measures showed acceptable construct validity and responsiveness. J Clin Epidemiol. 2010 Feb;63(2):163-70. doi: 10.1016/j.jclinepi.2009.03.023. Epub 2009 Aug 14.

Reference Type: BACKGROUND

PMID: 19683414 (View on PubMed)

Other Identifiers

SPARS2019

Identifier Type: -

Identifier Source: org_study_id