Application of encoder-based motion analysis and machine learning for knee osteoarthritis detection - A pilot study

Aug 4, 2026

Upload by Ophelia

Osteoarthritis (OA) is the most common joint disorder and a major source of disability, often involving the knee. Conventional imaging-based diagnostics may reveal changes only in advanced stages, limiting early functional evaluation. This pilot study combines encoder-based motion analysis with machine learning to support earlier knee OA assessment. Ninety participants performed open and closed kinetic chain tasks using a rotary encoder orthosis; movement cycle features were used to train classifiers and compare groups.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Abstract

Introduction

Osteoarthritis burden and diagnosis

Encoder-based motion analysis and machine learning

Vibroacoustic diagnostics and vibroarthrography

Submitted: 2025-08-27 | Revised: 2025-09-30 | Accepted: 2025-10-13 CC-BY 4.0 Keywords: knee osteoarthritis, encoder-based motion analysis, machine learning, vibroarthrography, wearable sensors, knee joint, biomechanics Robert KARPIŃSKI 1, 2*, Arkadiusz SYTA 1 1 Lublin University of Technology, Poland, [r.karpinski@pollub.pl](r.karpinski@pollub.pl) 2 The John Paul II Catholic University of Lublin, Poland, [r.karpinski@pollub.pl](r.karpinski@pollub.pl), [a.syta@pollub.pl](a.syta@pollub.pl) * Corresponding author: [r.karpinski@pollub.pl](r.karpinski@pollub.pl) Application of encoder-based motion analysis and machine learning for knee osteoarthritis detection: A pilot study Abstract Osteoarthritis (OA) is the most common joint disease and a leading cause of disability, most commonly affecting the knee. Conventional diagnostics rely primarily on imaging, which often detects changes only in advanced stages. This pilot study explores an alternative approach -encoder-based motion analysis combined with machine learning-to support early functional assessment of knee OA. The study included 90 subjects: 45 patients with radiographic evidence of OA and 45 healthy controls. A high-resolution rotary encoder integrated into a stabilizing knee orthosis recorded joint flexion-extension angles and velocities during open kinetic chain (OKC) and closed kinetic chain (CKC) tasks. Each subject performed five repetitions for each condition. Statistical analyses (Mann-Whitney U-test) revealed significant differences between groups, particularly in the CKC condition, where OA patients consistently required more time to complete movements. Machine learning classifiers were trained on cycle duration features. For OKC, accuracy remained modest (Naive Bayes: 65. 6%), whereas CKC-based features provided stronger discrimination, with a narrow neural network achieving 80% accuracy and balanced sensitivity/specificity. The results demonstrate the feasibility of wearable encoder-based systems for objective, non-invasive assessment of knee function. CKC tasks showed higher diagnostic value, highlighting their potential for integration into clinical protocols. Future research should expand data sets, incorporate multimodal sensors, and use advanced algorithms to improve diagnostic performance and support real-world monitoring. 1. INTRODUCTION Osteoarthritis (OA) is the most common form of arthritis and a leading cause of disability in older adults worldwide (Karpiński et al., 2025a) . The condition is characterized by progressive cartilage degradation and degenerative changes throughout the joint, resulting in pain, stiffness, and decreased mobility (Allen et al., 2022; Gelber, 2024). According to the World Health Organization, approximately 528 million people will be affected by OA in 2019 (a 113% increase since 1990), with women accounting for nearly 60% ofcases. Current estimates suggest that the disease affects more than 7% of the world's population, and the number of cases continues to rise as populations age (Steinmetz et al., 2023) . The knee joint is the most commonly affected, with degenerative changes reported in hundreds of millions of people worldwide (Bryliński et al., 2025; Courties et al., 2024). For example, epidemiologic studies show that nearly 80% of people over the age of 65 have radiographic evidence of OA (Mohammadi et al., 2024) . Demographic changes, particularly the aging of the population, along with risk factors such as obesity and mechanical injuries, indicate that the burden of OA will continue to increase in the coming decades (Steinmetz et al., 2023) . In advanced stages, when conservative and minimally invasive treatments are no longer effective, joint replacement surgery (arthroplasty) often remains the last therapeutic option for patients with severe OA (Karpiński et al., 2024a, 2024b, 2024c) . OA is already recognized as a major factor impairing physical function and quality of life, contributing to

FAQs

Which task condition and features improved diagnostic discrimination?

Closed kinetic chain (CKC) tasks showed stronger group discrimination than open kinetic chain (OKC), using cycle duration features for machine learning classification.

Aug 4, 2026

Upload by Ophelia