Predicting recovery after knee replacement using smart insoles and AI
Official title: Prediction of Patient-reported Outcome Measure and Performance-based Measure After Total Knee Arthroplasty Using Instrumented Insoles and Deep Neural Networks
Run by Yonsei University · NCT07367789 · Data updated 2026-11-12
This study will test whether preoperative clinical information and walking data from instrumented insoles can help predict recovery six weeks after total knee replacement for adults with knee osteoarthritis.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 19 Years and up |
| Sex | All |
| Enrollment | 200 (estimated) |
| Sponsor | Yonsei University Academic / other |
| Locations | 1 site (Yongin-si, Gyeonggi-do) |
| Status | Recruiting |
| Started | June 1, 2021 |
| Main results expected | December 31, 2026 |
| Study ends | December 31, 2026 |
| Registry record updated | January 26, 2026 |
| Trial ID | NCT07367789 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults aged 19 or older with radiographic knee osteoarthritis scheduled for primary total knee arthroplasty who can walk independently (FAC ≥ 3) at the participating hospitals are ideal candidates.
✕Probably not a fit
Patients who are non-ambulatory, have a prior TKA on the same knee, have neurological or musculoskeletal disorders that affect gait, are pregnant, or cancel their surgery are unlikely to benefit from the predictive models.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This multicenter prospective observational study will collect preoperative demographic data, body composition, muscle strength, comorbidity profiles, Kellgren-Lawrence radiographic grade, and gait data from instrumented insoles during the Timed Up and Go Test. Participants will complete validated patient-reported outcome measures (WOMAC) and performance-based mobility tests before surgery and at six weeks after surgery. Prediction models including linear regression, random forest, and deep neural networks will be trained using the same input variables and compared using accuracy and ROC-AUC. The protocol involves only gait assessments and questionnaires and is expected to pose minimal additional risk.
Why it matters
Potential benefit: If successful, the approach could provide individualized predictions of short-term improvement after TKA to help guide patient expectations and rehabilitation planning.
How similar studies have gone: Previous work using wearable sensors and machine-learning has shown promise for predicting mobility and patient-reported outcomes, but combining instrumented insoles with deep neural networks specifically for TKA recovery is relatively novel.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Age ≥ 19 years * Diagnosed with knee osteoarthritis (Kellgren-Lawrence grade 1-4) * Scheduled for primary Total Knee Arthroplasty (TKA) at either study site * Able to walk independently on level ground (Functional Ambulation Categories, FAC ≥ 3) Exclusion Criteria: * Cancellation of scheduled TKA * History of TKA on the same knee * Neurological or musculoskeletal disorders affecting gait * Pregnancy or possibility of pregnancy * Any condition deemed inappropriate for study participation by the investigator
Where it's running
-
Yongin Severance Hospital
Yongin-si, Gyeonggi-do, South Korea Recruiting
Study contacts
- Principal investigator: Na Young Kim, MD, PhD — Severance Hospital
- Study coordinator: Na Young Kim, MD, PhD
- Email: kny8452@yuhs.ac
- Phone: +82 010 9127 4482
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
AI-assisted anatomical visualization to reduce anxiety and fear of movement before knee replacement
This trial tests whether AI-enhanced visualization training helps people 55+ with knee osteoarthritis see and understand their knee replacement better and fear less about moving after surgery.
-
Oral vs IV Dexamethasone in Knee Replacement Recovery
This real-world study compares how giving dexamethasone by mouth or by IV around knee replacement affects early pain, movement, and recovery.
-
Smart knee implants and patient satisfaction after knee replacement
This study will see if smart knee implants that send recovery data can help people recover, stay satisfied, and reduce clinic visits after knee replacement.
-
Effects of virtual reality on walking in adults with knee osteoarthritis
This study tests how immersive virtual reality environments—designed to feel safe or to provoke fear—affect walking and worry about movement in adults 50 and older with knee osteoarthritis and in healthy peers.
-
Weekly berobenatide for knee osteoarthritis in adults who are overweight or obese
This study tests whether weekly berobenatide helps reduce knee pain and improve function, while also affecting body weight, in adults with knee osteoarthritis who are overweight or obese (with or without type 2 diabetes).
-
Autologous adipose-derived stem cell injections for knee osteoarthritis
We’re testing whether injecting a patient’s own fat-derived stem cells into the knee can help people with knee OA feel less pain and move better, compared with a standard hyaluronic acid treatment.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.