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

Not Applicable

Not yet recruiting

• Conditions: Pain; Knee Osteoarthritis

• Registration Number: NCT05173064
• Lead Sponsor: The University of Hong Kong

Brief Summary

The goal of the study is to confirm the idea of AI-powered Technological Surrogate Physiotherapist (TSP), by demonstrating its effectiveness and value as a new technology-based contribution to OA healthcare. Participants will be randomized to one of three groups: (1) the conventional PT group receiving the exercise program delivered through in-person sessions; (2) the AI-guided group following the program through the TSP after an initial PT session; or (3) the combined group receiving both in-person PT sessions and AI-guided home exercise. All individuals will take part in the study for 12 weeks, and data will be collected at baseline and 12 weeks after randomization.

Detailed 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 12-week randomized controlled non-inferiority trial will be conducted to examine the effects of AI-powered Technological Surrogate Physiotherapist, comparing with the effects of the group receiving in-person sessions and effects of the combined group receiving both.

Study Timeline

• Study First Submitted: 2021-12-09
• Study First Submitted QC: 2021-12-10
• Study First Posted: 2021-12-29
• Status Verified: 2025-08
• Last Update Submitted: 2025-10-01
• Last Update Posted: 2025-10-07
• Study Start: 2025-10-30
• Primary Completion: 2027-01-31
• Study Completion: 2027-03-31

Recruitment & Eligibility

• Status: NOT_YET_RECRUITING
• Sex: All
• Target Recruitment: 264

Inclusion Criteria

Participants will be recruited if they

• age ≥ 50 years,
• report having pain in or around the knee for more than 12 weeks and on most days of the previous month,
• report being diagnosed with knee OA by a physician, have physician-diagnosed knee OA in the medical record, or have radiographic evidence of grade 2 to 3 knee OA on the Kellgren-Lawrence scale in the posteroanterior and/or skyline view or the presence of lateral/posterior osteophytes (the X-rays will be read and classified by our orthopaedic surgeons collaborators to decide on each patient's eligibility to be included in the study),
• are willing and physically and cognitively able to perform (technology-supported) exercises required in the study protocol
• have normal or corrected to normal vision,
• are able to speak and read Chinese,
• are able to provide written informed consent.

Exclusion Criteria

Individuals will be excluded if they have

• history of knee or hip replacement surgery,
• non-ambulatory status,
• systemic inflammatory arthritis (e.g., gout),
• history of trauma (e.g., fractures around the knee, dislocation, and sprains or tears of soft tissues, like ligaments) or surgical arthroscopy of either knee within the past 6 months,
• intra-articular injection to the knee within the past 6 months,
• cognitive impairment,
• involvement in a similar study in the past 6 months,
• recent or imminent surgery (within 12 weeks),
• medical co-morbidities that preclude participation in exercise.

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: PARALLEL

Primary Outcome Measures

Name	Time	Method
Changes in knee pain as assessed by a 11-point numerical pain rating scale as recommended by the OARSI	From baseline to 12 weeks	0 represents no pain and 10 represents the worst possible pain.
Changes in physical function as assessed by the Knee Injury and Osteoarthritis Outcome Score (KOOS) physical function sub-scale	From baseline to 12 weeks	The scale regards the degree of difficulty in performing usual daily activities and higher level activities that involve physical function of the knee. Each item will be rated on a 5-point Likert scale ranging from 'None' (i.e., no difficulty) to 'Extreme' (i.e., extreme difficulty), based on which a normalized total score will be calculated (0 indicating extreme symptoms and 100 indicating no symptoms).

Secondary Outcome Measures

Name	Time	Method
Changes in physical function as assessed by 30-second chair-stand test	From baseline to 12 weeks	30-second chair stand test (30CST), which measures the number of stands the participant can complete in 30 sec, will be used to assess the general leg strength and functional performance.
Changes in physical function as assessed by timed up-and-go test	From baseline to 12 weeks	Timed up and go (TUG) test, which measures the time it takes the participant to standup from the chair, walk 3 meters, walk back to the chair, and sit down, will be used to assess functional mobility.
Changes in physical function as assessed by maximal isometric strength of the quadriceps and hamstrings	From baseline to 12 weeks	The participant will be instructed to maximally extend/flex each knee for 3 trials, 3 sec each, with a 1-minute rest in between. Verbal encouragement will be given in each trial to ensure the participant makes the maximum effort. The highest force of each muscle in the three trials will be used for data analysis.; After each test trial, the severity of pain experienced by the participant during the trial will be assessed using the 11-point numerical pain rating scale.
Changes in physical function as assessed by active and passive ranges of motion of the hip and knee joints	From baseline to 12 weeks	Active and passive ranges of motion of the hip and knee joints will be assessed using a goniometer.
Changes in health-related quality of life assessed by the Chinese version of the 36-item Short Form Survey (SF-36)	From baseline to 12 weeks	Health-related quality of life will be assessed using the Chinese version of the 36-item Short Form Survey (SF-36).
Exercise adherence	From baseline to 12 weeks	Exercise adherence will be indicated by the proportion of sessions and proportion of exercises performed which will be recorded by the TSP system (only for intervention group) and by participants and researchers using a log book.
Satisfaction with the therapeutic exercise training	From baseline to 12 weeks	It will be rated by participants using a 7-point Likert scale with anchors of 'Extremely unsatisfied' and 'Extremely satisfied'.
Convenience in terms of location and time for accessing the exercise therapy	From baseline to 12 weeks	It will be assessed on an 11-point numerical rating scale, with 0 representing 'Extremely inconvenient' and 10 representing 'Extremely convenient'.

Trial Locations

Locations (1)

826, Haking Wong Building, Pokfulam, The University of Hong Kong, Hong Kong; 🇭🇰 Hong Kong, Hong Kong