Effects of a Machine Learning-based Lower Limb Exercise Training System for Knee Pain

Pain Clinical Trial

Official title:

Effects of a Machine Learning-based Lower Limb Exercise Training System for Older Adults With Knee Pain: A Proof-of-concept Randomized Controlled Trial

Clinical Trial Details — Status: Not yet recruiting

Administrative data

• NCT number: NCT05173064
• Other study ID #: Feedback System
• Status: Not yet recruiting
• Phase: N/A
• Start date: November 1, 2022
• Est. completion date: June 30, 2023

Study information

• Verified date: December 2021
• Source: The University of Hong Kong
• Contact: Calvin Kalun Or, PhD
• Phone: (852) 3917-2587
• Email: klor[@]hku.hk
• Is FDA regulated: No
• Study type: Interventional

Clinical Trial Summary

The study will be a 12-week randomized controlled trial that aims to examine the effects of a machine learning-based lower limb exercise training system for older adults with knee pain. Participants will be randomly allocated to either the machine learning-based lower limb exercise training system group (intervention arm), video-based exercise training system group (intervention arm), or usual care group (control arm). Data will be collected at baseline, and at 4, 8, and 12 weeks after randomization.

Description:

Knee pain, often caused by osteoarthritis, is a prevalent musculoskeletal disorder among older adults and significantly reduces physical function and quality of life. Exercise therapy has been shown to be an effective form of treatment for knee pain. However, the traditional delivery of exercise therapy requires that individuals attend clinics to participate in face-to-face exercise sessions, which can be expensive and inconvenient. In recent years, information technologies have been used to support the delivery of exercise programs. The programs have also shown great benefits in improving the management of knee pain. However, it remains a concern that physical therapists are not able to provide the patients with direct and immediate supervision when exercises are taken place remotely at home or in community centers, which can be detrimental to exercise performance and the management of knee pain.

Thus, the research team has developed a machine learning-based exercise training system to provide evidence-based lower limb exercise videos, real-time movement feedback, and tracking of exercise progress for older adults with knee pain. In this study, a proof-of-concept randomized controlled trial will be conducted to examine the effects of the machine learning-based exercise training system, comparing with the effects of video-based exercise training system (providing exercise videos alone but no real-time movement feedback or tracking of exercise progress) and effects of usual care.

Recruitment information / eligibility

• Status: Not yet recruiting
• Enrollment: 60
• Est. completion date: June 30, 2023
• Est. primary completion date: March 1, 2023
• Accepts healthy volunteers: No
• Gender: All
• Age group: 55 Years and older

Eligibility

Inclusion Criteria:

Participants will be recruited if they

• age = 55 years,

• have knee pain, stiffness, or both in one or both knees on most days for at least one month during the past 12 months, or have consulted healthcare professionals with their pain, stiffness, or both in one or both knees during the past 12 months,

• are able to perform the exercises required in physical assessments and exercise training,

• are able to speak and read Chinese,

• are able to provide written informed consent.

Exclusion Criteria:

Individuals will be excluded if they have

• inflammatory arthritis,

• acute trauma,

• malignancy,

• history of knee replacement,

• being on the waiting list for knee surgery,

• physical therapy for knee problems during the past three months,

• intra-articular injection to the knee within six months.

Related Conditions & MeSH terms

• Pain

Intervention

Device:
• Machine learning-based exercise training system
The video-based exercise training system will have three key features: Evidence-based exercise videos instructed by physical therapists Real-time movement feedback and performance score Exercise records.
• Video-based exercise training system
The video-based system will only include the exercise videos as those involved in the machine learning-based system. The features of real-time movement feedback and tracking of exercise progress will not be provided.

Locations

Country	Name	City	State
n/a

Sponsors (1)

Lead Sponsor	Collaborator
The University of Hong Kong

References & Publications (6)

Chen T, Or CK, Chen J. Effects of technology-supported exercise programs on the knee pain, physical function, and quality of life of individuals with knee osteoarthritis and/or chronic knee pain: A systematic review and meta-analysis of randomized controlled trials. J Am Med Inform Assoc. 2021 Feb 15;28(2):414-423. doi: 10.1093/jamia/ocaa282. — View Citation

Cottrell E, Roddy E, Foster NE. The attitudes, beliefs and behaviours of GPs regarding exercise for chronic knee pain: a systematic review. BMC Fam Pract. 2010 Jan 18;11:4. doi: 10.1186/1471-2296-11-4. Review. — View Citation

Hay EM, Foster NE, Thomas E, Peat G, Phelan M, Yates HE, Blenkinsopp A, Sim J. Effectiveness of community physiotherapy and enhanced pharmacy review for knee pain in people aged over 55 presenting to primary care: pragmatic randomised trial. BMJ. 2006 Nov 11;333(7576):995. Epub 2006 Oct 20. — View Citation

Hurley MV, Walsh NE, Mitchell H, Nicholas J, Patel A. Long-term outcomes and costs of an integrated rehabilitation program for chronic knee pain: a pragmatic, cluster randomized, controlled trial. Arthritis Care Res (Hoboken). 2012 Feb;64(2):238-47. doi: 10.1002/acr.20642. — View Citation

Hurley MV, Walsh NE, Mitchell HL, Pimm TJ, Patel A, Williamson E, Jones RH, Dieppe PA, Reeves BC. Clinical effectiveness of a rehabilitation program integrating exercise, self-management, and active coping strategies for chronic knee pain: a cluster randomized trial. Arthritis Rheum. 2007 Oct 15;57(7):1211-9. — View Citation

McAlindon TE, Cooper C, Kirwan JR, Dieppe PA. Knee pain and disability in the community. Br J Rheumatol. 1992 Mar;31(3):189-92. — View Citation

Outcome

Type	Measure	Description	Time frame	Safety issue
Other	Changes in acceptance of the interventions	The technology acceptance model will be used to examine the particpants' acceptance of interventions (i.e., machine learning-based exercise training system or video-based exercise training system). There will be four constructs: perceived usefulness (4 items), perceived ease of use (4 items), attitude (3 items), and intention to use (2 items). Each item will be rated on a 7-point Likert scale, ranging from 1 (very strongly disagree) to 7 (very strongly agree).	from baseline to 4 weeks, 8 weeks, and 12 weeks
Primary	Changes in knee pain as assessed by the 5-item pain subscale of the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC)	The items will be rated on a 5-point Likert scale which corresponds to "None (0)", "Mild (1)", "Moderate (2)", "Severe (3)", and "Extreme (4)".	from baseline to 4 weeks, 8 weeks, and 12 weeks
Primary	Changes in physical function as assessed by the 17-item physical function subscale of WOMAC	The items will be rated on a 5-point Likert scale which corresponds to "None (0)", "Mild (1)", "Moderate (2)", "Severe (3)", and "Extreme (4)".	from baseline to 4 weeks, 8 weeks, and 12 weeks
Secondary	Changes in severity of knee pain over the previous 7 days as assessed by an 11-point numerical rating scale	0 represents "no pain" and 10 represents the "worst possible pain".	from baseline to 4 weeks, 8 weeks, and 12 weeks
Secondary	Changes in physical function as assessed by 30-second chair-stand test		from baseline to 4 weeks, 8 weeks, and 12 weeks
Secondary	Changes in physical function as assessed by 40 m fast-paced walk test		from baseline to 4 weeks, 8 weeks, and 12 weeks
Secondary	Changes in physical function as assessed by timed up-and-go test		from baseline to 4 weeks, 8 weeks, and 12 weeks
Secondary	Changes in severity rating of patient nominated main functional problems over the previous 3 days	At baseline, participants will select three activities that they perform frequently, which they perceive as important in their life, and which knee pain makes difficult for them. The severity of each functional problem will be rated on an 11-point scale, with 0 representing "unable to perform the activity" and 10 representing "able to perform the activity at the same level as before the presence of knee pain".	from baseline to 4 weeks, 8 weeks, and 12 weeks
Secondary	Changes in self-efficacy as assessed by the 8-item Arthritis Self-efficacy Scale	Each item will be rated on a scale with response categories ranging from 1 (very uncertain) to 10 (very certain).	from baseline to 4 weeks, 8 weeks, and 12 weeks
Secondary	Changes in psychological distress as assessed by the Hospital Anxiety and Depression Scale	The 14 items will be rated on a 4-point Likert scale (range 0-3), with higher scores indicating a worse condition.	from baseline to 4 weeks, 8 weeks, and 12 weeks
Secondary	Changes in quality of life as assessed by the EQ-5D-5L	EQ-5D-5L includes 5 health-related dimensions measured on 5 levels (i.e., "no problems", "slight problems", "moderate problems", "severe problems", and "unable to do"), and health state rated on a visual analogue scale (VAS) with endpoints of 0 ("the best health you can imagine") and 100 ("the worst health you can imagine") with higher scores indicating a better condition.	from baseline to 4 weeks, 8 weeks, and 12 weeks
Secondary	Changes in participants' perceived global assessment of change in knee pain	It will be rated on a 5-point Likert scale: "Much worse (0)", "Worse (1)", "Same (2)", "Better (3)", and "Much better (4)	from baseline to 4 weeks, 8 weeks, and 12 weeks