Analysis and classification of gait patterns in osteoarthritic and asymptomatic knees using phase space reconstruction, intrinsic time-scale decomposition and neural networks.

Artificial intelligence (AI) has gained significant traction in medical applications. This study focuses on knee joint diseases, specifically osteoarthritis (OA) and rheumatoid arthritis, which often lead to pathological gait patterns in patients due to pain and mobility issues. The proposed technique put forth in this research aims to classify gait patterns in kinematic data of osteoarthritic and asymptomatic (AS) knees. Our approach utilizes Phase Space Reconstruction (PSR), Intrinsic Time-Scale Decomposition (ITD), and neural networks to extract features. Knee kinematic data, including translations and rotations, are analyzed using ITD to obtain dominant proper rotation components (PRCs) capturing most of the energy from the signals. The phase space of PRCs is then reconstructed, revealing nonlinear gait dynamics. By employing three-dimensional PSR and Euclidean distance, we extract features that capture the distinctive dynamics of osteoarthritic and AS knee gait patterns. Utilizing neural networks, we model and classify the gait system dynamics. Experimental evaluation on 22 knee OA patients and 28 age-matched AS control individuals demonstrates the effectiveness of our method in distinguishing between the two groups' gait patterns, achieving superior classification accuracies of 92 % and 96 % , respectively. These results suggest that our approach holds promise for aiding the identification of knee OA in clinical practice, leading to improved quality outcomes. By enabling accurate identification of knee OA in clinical practice, the proposed method has the potential to contribute to improved patient outcomes, such as timely interventions, personalized treatment plans, and enhanced monitoring of disease progression. This, in turn, can lead to better management of knee OA and improved quality outcomes for patients. [ABSTRACT FROM AUTHOR]