Effectiveness of AI-Supervised Mobile Exercise Application in Patients With Knee Osteoarthritis

NCT07066514 | Withdrawn

• 1 other identifier: 2025-2/19
• Study Type: interventional
• Target: N/A
• Locations: 1 country
• Sites: 1

Brief Summary

This study aims to evaluate the effectiveness of an artificial intelligence (AI)-supported mobile application that supervises home-based exercise programs in patients with knee osteoarthritis. A total of 80 participants aged 40 to 80 will be randomly assigned to one of two groups: a mobile application exercise group or a home exercise booklet group. Both groups will receive the same standardized stretching, strengthening, and range of motion exercises designed for knee osteoarthritis. The mobile app provides real-time feedback and supervision using the device's camera and artificial intelligence algorithms to track and guide exercise performance. Participants in the app group will perform exercises with supervision via the app interface, while the control group will follow the same exercises using printed instructions. Both groups will exercise 3 to 4 times per week for 4 weeks. The study will compare pain levels, physical function, and balance before and after the intervention using validated outcome measures such as the WOMAC Index and the Visual Analog Scale. This study may help determine whether AI-supported digital tools can improve exercise adherence and outcomes in patients with knee osteoarthritis.

Conditions

Knee Osteoarthritis

Outcome Measures

Primary Outcomes (6)

• Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC)

  The WOMAC is a validated questionnaire used to assess pain, stiffness, and physical function in patients with knee osteoarthritis. It consists of 24 items: 5 for pain, 2 for stiffness, and 17 for physical function. Each item is scored on a 5-point Likert scale (0 = none to 4 = extreme), with a total score range of 0 to 96. Higher scores indicate worse symptoms.

  Baseline and Week 4

• Visual Analog Scale (VAS)

  Change in pain severity measured by the Visual Analog Scale (VAS; range: 0-10; higher scores indicate worse pain) at baseline and at 6 weeks.

  Baseline and Week 4

• Timed Up and Go (TUG) Test

  Baseline and Week 4

• Functional Reach Test (FRT)

  Baseline and Week 4

• Single-Leg Stance Test

  Baseline and Week 4

• Exercise Execution Accuracy Assessed by Mobile Application

  Accuracy of exercise adherence detection by the AI algorithm compared to physiotherapist assessment (% agreement)

  Before and during the 4-week intervention

Study Arms (2)

AI-Based Mobile Home Exercise Group

EXPERIMENTAL

Behavioral: AI-Supervised Mobile Exercise Program

Standard Home Exercise Group

EXPERIMENTAL

Behavioral: Booklet-Guided Home Exercise Program

Interventions

Booklet-Guided Home Exercise Program BEHAVIORAL

This intervention provides patients with a standardized home exercise program in printed booklet format. The program includes the same evidence-based stretching, strengthening, and range of motion exercises used in the mobile application group, performed 3-4 times per week for 4 weeks. Participants receive one-time in-person instruction on proper form but no ongoing supervision or feedback during the program. Adherence and technique are self-monitored.

Standard Home Exercise Group

AI-Supervised Mobile Exercise Program BEHAVIORAL

This intervention involves the use of an artificial intelligence (AI)-supported mobile application that delivers a personalized exercise program to patients with knee osteoarthritis. The app supervises exercise execution in real time using the device's camera and AI algorithms to track movements, count repetitions, and assess form accuracy. The program includes stretching, strengthening, and range of motion exercises performed 3-4 times per week for 4 weeks. The app provides instructional videos, personalized feedback, reminders, and records user performance. No video or personal images are stored; only anonymized motion data are collected and securely stored.

AI-Based Mobile Home Exercise Group

Eligibility Criteria

• Age: 40 Years - 80 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Aged between 40 and 80 years
• Diagnosed with knee osteoarthritis according to ACR criteria
• Referred to physical therapy by a physician for knee osteoarthritis
• Able to use a smartphone or tablet
• Having regular access to the internet
• Voluntarily agrees to participate in the study

You may not qualify if:

• History of knee surgery or currently undergoing surgical treatment
• Received physical therapy or rehabilitation for knee OA within the past 6 months
• Lack of access to a mobile device or internet
• Any neurological, cardiovascular, or musculoskeletal condition that prevents safe participation in exercise
• Cognitive impairment or psychiatric disorder interfering with exercise adherence
• Inability to follow instructions or use the mobile app interface
• Any condition that would contraindicate participation in a home-based exercise program

Sponsors & Collaborators

• Uludag University: lead

Study Sites (1)

Bursa Uludag University

Bursa, Nilüfer, Turkey (Türkiye)

Location

Related Publications (2)

• Nelligan RK, Hinman RS, Kasza J, Crofts SJC, Bennell KL. Effects of a Self-directed Web-Based Strengthening Exercise and Physical Activity Program Supported by Automated Text Messages for People With Knee Osteoarthritis: A Randomized Clinical Trial. JAMA Intern Med. 2021 Jun 1;181(6):776-785. doi: 10.1001/jamainternmed.2021.0991.

  PMID: 33843948 BACKGROUND

• Xiang XN, Wang ZZ, Hu J, Zhang JY, Li K, Chen QX, Xu FS, Zhang YW, He HC, He CQ, Zhu SY. Telehealth-Supported Exercise or Physical Activity Programs for Knee Osteoarthritis: Systematic Review and Meta-Analysis. J Med Internet Res. 2024 Aug 2;26:e54876. doi: 10.2196/54876.

  PMID: 39094114 BACKGROUND

MeSH Terms

Conditions

Osteoarthritis, Knee

Condition Hierarchy (Ancestors)

Osteoarthritis; Arthritis; Joint Diseases; Musculoskeletal Diseases; Rheumatic Diseases

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: DOUBLE
• Who Masked: PARTICIPANT, INVESTIGATOR
• Purpose: TREATMENT
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Asst Prof

Study Record Dates

• First Submitted: July 4, 2025
• First Posted: July 15, 2025
• Study Start: August 1, 2025
• Primary Completion: September 1, 2025
• Study Completion: October 1, 2025
• Last Updated: May 6, 2026

Record last verified: 2025-07

Locations

TU (1)