Detection of abnormal gait pattern in knee joint using inertial measurement unit and machine learning

2022 Fiscal Year Final Research Report

• Project/Area Number: 20K23309
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Multi-year Fund
• Review Section: 0909:Sports sciences, physical education, health sciences, and related fields
• Research Institution: Sendai National College of Technology
• Principal Investigator: Komatsu Akira 仙台高等専門学校, 総合工学科, 助教 (10881469)
• Project Period (FY): 2020-09-11 – 2023-03-31
• Keywords: IMU / 歩行解析 / センサ・フュージョン / 時系列解析

Outline of Final Research Achievements

Quantitative gait analysis using optical motion capture has been extensively reported, while qualitative evaluations of anomaly movements through gait observation by medical doctor and physical therapists have been conducted for musculoskeletal disorders such as knee osteoarthritis, which can cause pain and deformity as the disease progresses. However, achieving a simple gait analysis has not been realized. In this study, we constructed a gait analysis system incorporating sensor fusion and time series analysis into a small and inexpensive inertial sensor (Inertial Measurement Unit, IMU), and verified the utility of these analysis systems. As a result, it was suggested that it was possible to achieve a quantitative assessment of kinematic changes specific to patients with knee osteoarthritis and that a system with minimal delay in detecting gait cycles could be constructed.

Free Research Field

バイオメカニクス

Academic Significance and Societal Importance of the Research Achievements

これまでに様々な歩行解析に関する研究が種々行われてきたが，その多くはモーションキャプチャを主として用いた研究であり，IMUを用いた研究の多くは健常者を対象としていたため患者歩行の定量評価については数少ない．本研究で構築したシステムによって病態進行を有する運動器疾患特有の運動変化を定量評価できると示唆されるため，今後応用することによって他の疾患においてもIMUを用いた歩行解析による評価が実施できることが期待される．