This study aims to compare the effectiveness of an artificial intelligence (AI)-guided physical therapy program with a traditional physical therapy program in patients with knee osteoarthritis. Forty patients with knee osteoarthritis will be randomly assigned to one of two groups. The traditional physical therapy group will receive a conventional rehabilitation program including transcutaneous electrical nerve stimulation (TENS), strengthening, flexibility, and balance exercises. The AI-guided group will receive an individualized rehabilitation program generated using ChatGPT-4 based on standardized patient information and clinical assessment findings. Both groups will receive education regarding lifestyle modification and joint protection strategies. The effects of the two rehabilitation approaches will be evaluated by measuring pain intensity, knee range of motion, knee-related functional ability, and functional mobility and fall risk before and after the intervention. The study will determine whether an AI-guided physical therapy program can provide outcomes comparable or superior to those of traditional physical therapy in individuals with knee osteoarthritis.
This study is a prospective, single-blind, randomized controlled trial designed to compare the efficacy of an AI-guided physical therapy program with a traditional physical therapy program in patients with knee osteoarthritis. A total of 40 patients with knee osteoarthritis will be recruited from the Outpatient Clinic of the Faculty of Physical Therapy, Cairo University. Eligible participants will be aged 45-70 years and diagnosed with knee osteoarthritis according to the American College of Rheumatology criteria, with Kellgren-Lawrence grade II or III osteoarthritis. Participants will be randomly allocated into two equal groups. The control group will receive a conventional physical therapy program consisting of transcutaneous electrical nerve stimulation (TENS), strengthening exercises, flexibility exercises, and balance exercises. Treatment will be provided three times per week for 12 weeks. The AI-guided group will receive an individualized rehabilitation program generated using ChatGPT-4. Standardized patient information, including age, sex, pain intensity, functional disability, knee range of motion, symptom duration, and physical activity level, will be entered by the researcher to generate an evidence-based rehabilitation program for each participant. Both groups will also receive education regarding lifestyle modification and joint protection strategies. Outcome measures will be assessed before and after the intervention. Pain intensity will be evaluated using the Visual Analog Scale (VAS), knee range of motion using a digital goniometer, knee-related pain, stiffness, and physical function using the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), and functional mobility and fall risk using the Timed Up and Go (TUG) test. The study will compare changes in these outcomes between the two groups to determine the relative efficacy of AI-guided and traditional physical therapy programs for patients with knee osteoarthritis.
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
TREATMENT
Masking
SINGLE
Enrollment
40
Participants will receive an individualized physical therapy program generated using ChatGPT-4. The researcher will manually enter standardized patient data, including age, sex, pain intensity (VAS), functional disability (WOMAC), knee range of motion, symptom duration, and physical activity level. ChatGPT-4 will be prompted to generate an evidence-based, in-clinic rehabilitation program for adults with knee osteoarthritis.
Participants will receive a traditional physical therapy program including transcutaneous electrical nerve stimulation (TENS), strengthening exercises, flexibility exercises, and balance exercises. The intervention will be administered three sessions per week for 12 weeks.
Participants in both study arms will receive education on lifestyle modification and joint protection strategies as part of the management of knee osteoarthritis.
Faculty of physical therapy, Cairo University
Giza, Egypt
Pain Intensity
Pain intensity will be assessed using the Visual Analog Scale (VAS), a 10-cm scale ranging from 0 (no pain) to 10 (worst pain imaginable). Lower scores indicate less pain.
Time frame: 12 weeks
Knee Range of Motion
Active knee range of motion will be measured in degrees using a digital goniometer. Knee flexion and extension will be assessed before and after the intervention.
Time frame: 12 weeks
Knee Pain, Stiffness, and Physical Function
Knee-related pain, stiffness, and physical function will be assessed using the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). The questionnaire includes 24 items covering pain, stiffness, and physical function. Higher scores indicate greater symptom severity and functional limitation.
Time frame: 12 weeks
Functional Mobility and Fall Risk
Functional mobility and fall risk will be assessed using the Timed Up and Go (TUG) test. Participants will stand from a chair, walk 3 meters, turn, return to the chair, and sit down. The time required to complete the task will be recorded in seconds; longer times indicate poorer functional mobility and greater fall risk.
Time frame: 12 weeks
Rania Reda Mohamed, PhD
CONTACT
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.