Prediction of Postoperative Outcomes After TKA Using Instrumented Insoles and DNN

Official title

Prediction of Patient-reported Outcome Measure and Performance-based Measure After Total Knee Arthroplasty Using Instrumented Insoles and Deep Neural Networks

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.

Detailed description

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.

Interventions

• Other Instrumented Insole Gait Assessment
  Participants undergo gait assessment using an instrumented insole system during the Timed Up and Go Test. The device is used solely for data collection and does not provide therapeutic intervention.

Primary outcome measures

• Western Ontario and McMaster Universities Arthritis Index (WOMAC) Improvement [Time frame: Preoperative baseline; postoperative 6 weeks, 3 months, 6 months, and 12 months]

Secondary outcome measures (1)

• Timed Up and Go Test (TUGT) Improvement [Time frame: Preoperative baseline; postoperative 6 weeks, 3 months, 6 months, and 12 months]

Eligibility 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

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Observational model

Cohort

Study locations

South Korea · 1 center

• Yongin Severance Hospital — Yongin-si

Publications

• Srivastava AK; Surgical Management of Osteoarthritis of the Knee Work Group, Staff of the American Academy of Orthopaedic Surgeons. American Academy of Orthopaedic Surgeons Clinical Practice Guideline Summary of Surgical Management of Osteoarthritis of the Knee. J Am Acad Orthop Surg. 2023 Dec 15;31(24):1211-1220. doi: 10.5435/JAAOS-D-23-00338. Epub 2023 Oct 24. PMID 37883429
• Small SR, Bullock GS, Khalid S, Barker K, Trivella M, Price AJ. Current clinical utilisation of wearable motion sensors for the assessment of outcome following knee arthroplasty: a scoping review. BMJ Open. 2019 Dec 29;9(12):e033832. doi: 10.1136/bmjopen-2019-033832. PMID 31888943
• Ferreira AM, Salim R, Fogagnolo F, de Oliveira LFL, Riberto M, Kfuri M. The Value of a Standardized Knee Functional Assessment in Predicting the Outcomes of Total Knee Arthroplasty. J Knee Surg. 2022 Aug;35(10):1126-1131. doi: 10.1055/s-0040-1722321. Epub 2021 Jan 28. PMID 33511585
• Boekesteijn R, Smolders J, Busch V, Keijsers N, Geurts A, Smulders K. Objective monitoring of functional recovery after total knee and hip arthroplasty using sensor-derived gait measures. PeerJ. 2022 Sep 28;10:e14054. doi: 10.7717/peerj.14054. eCollection 2022. PMID 36193431
• Hsieh CY, Huang HY, Liu KC, Chen KH, Hsu SJ, Chan CT. Subtask Segmentation of Timed Up and Go Test for Mobility Assessment of Perioperative Total Knee Arthroplasty. Sensors (Basel). 2020 Nov 5;20(21):6302. doi: 10.3390/s20216302. PMID 33167444
• Salaffi F, Leardini G, Canesi B, Mannoni A, Fioravanti A, Caporali R, Lapadula G, Punzi L; GOnorthrosis and Quality Of Life Assessment (GOQOLA). Reliability and validity of the Western Ontario and McMaster Universities (WOMAC) Osteoarthritis Index in Italian patients with osteoarthritis of the knee. Osteoarthritis Cartilage. 2003 Aug;11(8):551-60. doi: 10.1016/s1063-4584(03)00089-x. PMID 12880577
• Tolk JJ, Janssen RPA, Prinsen CAC, Latijnhouwers DAJM, van der Steen MC, Bierma-Zeinstra SMA, Reijman M. The OARSI core set of performance-based measures for knee osteoarthritis is reliable but not valid and responsive. Knee Surg Sports Traumatol Arthrosc. 2019 Sep;27(9):2898-2909. doi: 10.1007/s00167-017-4789-y. Epub 2017 Nov 11. PMID 29128879
• Wilfong JM, Badley EM, Power JD, Gandhi R, Rampersaud YR, Perruccio AV. Discordance between self-reported and performance-based function among knee osteoarthritis surgical patients: Variations by sex and obesity. PLoS One. 2020 Jul 30;15(7):e0236865. doi: 10.1371/journal.pone.0236865. eCollection 2020. PMID 32730319

Identifiers

NCT: NCT07367789 · GBIRB2025-324

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗