Smartphone Video-Based AI Gait Analysis Reports to Support Remote Follow-up After Total Knee Arthroplasty

NCT07892248 | Enrolling By Invitation DMC

• 1 other identifier: MDH003
• Study Type: observational
• Target: 36
• Locations: 1 country
• Sites: 1

Brief Summary

This study evaluates whether an artificial intelligence (AI)-assisted gait report generated from smartphone walking videos can support remote follow-up after total knee arthroplasty (TKA). Patients complete standardized walking video recordings and symptom assessments before surgery and at approximately 6 and 12 weeks after surgery. The system analyzes the videos and provides gait information, including walking speed, step characteristics, gait symmetry, gait phases, knee movement, and changes over time. A separate clinician evaluation examines whether these AI-generated gait reports improve remote clinical decision-making. Clinicians review postoperative cases using either usual remote information, including patient-reported symptoms and the original walking video, or the same information supplemented with the AI-generated gait report. The study evaluates the clinical acceptability of management recommendations, agreement with in-person clinical assessments, clinician confidence, need for additional information, and decision time. The study also evaluates the feasibility, usability, and trust associated with home-based smartphone gait assessment from both patient and clinician perspectives. The AI gait report is intended to support postoperative monitoring and communication and does not replace clinical diagnosis or scheduled in-person follow-up.

Conditions

Total Knee Arthroplasty

Keywords

Total Knee Arthroplasty; application; AI Gait Analysis

Outcome Measures

Primary Outcomes (1)

• Number and proportion of physician-case remote management recommendations classified as clinically acceptable compared with the in-person reference assessment

  At postoperative weeks 6 and 12, participating physicians review deidentified remote follow-up cases and provide a management recommendation. An independent senior orthopedic physician who is not involved in the remote case evaluation determines the clinically acceptable management option or range of options for each patient-timepoint case based on the concurrent in-person clinical assessment and available imaging information. Each physician-case recommendation is classified as clinically acceptable if it falls within the reference range and clinically unacceptable otherwise. The outcome is reported as the number and proportion of clinically acceptable physician-case evaluations among all valid evaluations in each study condition.

  6 and 12 weeks after TKA

Secondary Outcomes (7)

• Number and proportion of physician recovery-status assessments agreeing with the concurrent in-person reference assessment

  6 and 12 weeks after TKA

• Mean physician confidence score for remote management recommendations rated on a 0-100 scale

  6 and 12 weeks after TKA

• Number and proportion of physician-case assessments in which recovery status cannot be determined

  6 and 12 weeks after TKA

• Number and proportion of physician-case assessments in which a management recommendation cannot be provided because of insufficient information

  6 and 12 weeks after TKA

• Mean time in seconds required to complete each physician-case evaluation

  6 and 12 weeks after TKA

Study Arms (1)

Patients undergoing knee replacement

Device: Smartphone Video-Based AI Gait Analysis; Device: video recorded on a mobile phone (assessed by doctors)

Interventions

Smartphone Video-Based AI Gait Analysis DEVICE

After the video is recorded on a mobile phone, AI analyzes it to assess the patient's rehabilitation status. This is not an intervention; it is solely for observing the status of rehabilitation progress prior to the follow-up visit.

Patients undergoing knee replacement

video recorded on a mobile phone (assessed by doctors) DEVICE

After the video is recorded on a mobile phone, a doctor reviews it to analyze the patient's recovery status.

Patients undergoing knee replacement

Eligibility Criteria

• Age: 18 Years - 85 Years
• Sex: female
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Patients undergoing knee arthroplasty

You may qualify if:

• Age ≥18 years; cclinically diagnosed with knee osteoarthritis (KOA) and scheduled for knee surgery;
• Able to walk safely for short distances without assistance or daily assistive devices;
• Able to use a smartphone, or able to record videos and view reports with the assistance of a caregiver;
• Able to understand the study instructions and complete the questionnaires.

You may not qualify if:

• Presence of clinical red flags requiring immediate surgery;
• Presence of other conditions significantly affecting gait, severe hip disease, or recent lower-limb fractures;
• Severe cognitive, visual, or speech impairments preventing independent understanding of the study materials;
• Inability to safely complete the standardized walking video recording.

Sponsors & Collaborators

• Shanghai Jiao Tong University School of Medicine: lead

Study Sites (1)

Shanghai Jiao Tong University

Shanghai, Shanghai Municipality, 200140, China

Location

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: PROSPECTIVE
• Target Duration: 1 Day
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator

Study Record Dates

• First Submitted: October 5, 2026
• First Posted: October 23, 2026
• Study Start: January 1, 2026
• Primary Completion (Estimated): January 1, 2027
• Study Completion (Estimated): February 1, 2027
• Last Updated: October 23, 2026

Record last verified: 2025-11

Locations

CN (1)