Prediction of Postoperative Outcomes After TKA Using Instrumented Insoles and DNN

Yonsei University200 enrolled

Overview

This multicenter prospective observational study aims to evaluate whether preoperative clinical variables and wearable sensor-derived gait features can predict postoperative improvement after total knee arthroplasty (TKA). Participants will undergo standardized gait assessments using instrumented insoles and complete validated patient-reported outcome measures (PROMs). Prediction models including linear regression, random forest, and deep neural networks will be applied and their performance compared.

This study investigates predictive factors associated with postoperative improvement in both patient-reported outcomes and performance-based mobility measures among individuals undergoing total knee arthroplasty. Participants from two centers-Yongin Severance Hospital and Gachon University Gil Medical Center-will undergo preoperative collection of demographic data, body composition, muscle strength, comorbidity profiles, radiographic Kellgren-Lawrence grade, and wearable insole-derived gait data during the Timed Up and Go Test (TUGT). Postoperative outcomes at six weeks will include Western Ontario and McMaster Universities Arthritis Index (WOMAC) and TUGT. Prediction models (linear regression, random forest, and deep neural network models) will be applied using consistent input variables. Model performance will be evaluated using accuracy and Receiver Operating Characteristic-Area Under the Curve (ROC-AUC). This study does not involve any therapeutic intervention and poses minimal risk.

Study Type

OBSERVATIONAL

Enrollment

200

Conditions

Knee Osteoarthritis Total Knee Arthroplasty

Interventions

Eligibility

Sex: ALLMin age: 19 Years

Medical Language ↔ Plain English

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

Outcomes

Primary Outcomes

Western Ontario and McMaster Universities Arthritis Index (WOMAC) Improvement

Improvement in patient-reported symptoms as measured by the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). The WOMAC is a validated patient-reported outcome measure consisting of 24 items assessing pain (5 items), stiffness (2 items), and physical function (17 items). Each item is scored on a 5-point Likert scale (0-4), resulting in a total score ranging from 0 to 96, where higher scores indicate worse pain, stiffness, and functional limitation, and lower scores indicate better clinical status. Postoperative improvement is defined as a decrease of ≥15 points in the WOMAC total score compared with the preoperative baseline, corresponding to the minimal clinically important difference (MCID). Participants will be classified as "improved" or "not improved" based on this criterion (binary outcome).

Time frame: Preoperative baseline; postoperative 6 weeks, 3 months, 6 months, and 12 months

Secondary Outcomes

Timed Up and Go Test (TUGT) Improvement

Improvement defined as a decrease in TUGT completion time from baseline (binary).