Vibroarthrographic signals for the low-cost and computationally efficient classification of aging and healthy knees. (September 2021)

• Record Type: Journal Article
• Authors: Gong, Rui; Ohtsu, Hajime; Hase, Kazunori; Ota, Susumu
• Is Part Of: Biomedical signal processing and control. Volume 70(2021)
• Publication Date: 2021-09
• Subjects: Spectrum Entropy -- Vibroarthrographic signal -- Knee aging -- Classification; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.103003
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: VAG signals were used to identify aging knees. An STFT-PCA-based noise reduction method was successfully applied to mechanical biosignals. The applicability of spectrum entropy in the classification was extended. This work lays a foundation for the non-invasive diagnosis of early knee aging. Abstract: Knee disorders are a common but easily overlooked disease and are often caused by natural or early aging. However, the aging process is difficult for the patient to self-diagnose until it deteriorates to osteoarthritis (OA). Vibroarthrographic (VAG) signals make the aging process visible and may contribute to reducing the incidence of disability caused by delayed medical diagnosis. Recently, although many studies have used VAG signals to diagnose knee joint disease, they have not yet been used in the diagnosis of knee aging. In this paper, a method is proposed to observe the aging process of the knee through VAG signal analysis. The accuracy of classifying naturally aging and healthy knees with this method is 0.9275, and the area under the receiver operating characteristic curve is 0.8928. The paper has filled the gap of using VAG signal to diagnose the natural knee aging process and laid the foundation for the non-invasive diagnosis of early knee aging.