A telehealth system framework for assessing knee-joint conditions using vibroarthrographic signals. (January 2020)

• Record Type: Journal Article
• Authors: Athavale, Yashodhan; Krishnan, Sridhar
• Is Part Of: Biomedical signal processing and control. Volume 55(2020)
• Publication Date: 2020-01
• Subjects: Vibroarthrography -- Actigraphy -- IoMT -- Edge computing -- Data compression -- Signal processing -- Adaptive segmentation -- Feature extraction -- Knee rehabilitation; 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.2019.101580
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A novel actigraphy encoding, segmentation and analysis system is proposed for processing vibroarthrography data to identify cartilage degeneration. The proposed algorithm includes two unique contributions in physiological signal pre-processing and adaptive segmentation. Two new actigraphy-specific features are introduced in this research which characterize limb movements using accelerometers. The proposed system in this research work has the potential to be applied in a telehealth framework. Abstract: Hectic lifestyle coupled sometimes with deficient choices in food and exercise, has led to an increase in the number of individuals being diagnosed with joint generation disorders. In addition, a substantial number of individuals in specialized occupations (such as army) or sports suffer from joint related injuries, thereby leading to surgical replacements and in some severe cases as disability. Standard methods of detecting joint disorders or disabilities include arthroscopy and arthrogram. Vibroarthrography (VAG) is a non-invasive technique wherein the specialist listens to sounds generated from joint movements recorded using actigraphs. In this study, we propose a system which encodes, analyses and segments actigraphy-based VAG data for assessing the severity of cartilage degeneration, and highlighting instances of activity which causes crackling sounds during limb movements. The proposed system encapsulates IoMT (Internet of Medical Things) requirements by providing efficient data compression and analysis at the source. Using an actigraphy dataset from 89 participants, our experiments yielded that the system is able to compress the actigraphy data into 3-bits per sample, thereby reducing the signal size by about 88%, without losing any vital limb movement information. This has been further validated using a simple pattern classification of 3-bit quantized VAG data from participants with healthy and unhealthy knee joints. The method, which yielded a recognition accuracy of 84.6%, as compared to raw VAG data which yielded 80% accurate results. In addition, the proposed adaptive segmentation scheme in the system, leverages the 3-bit encoding by correctly identifying 90% of the segments of interest from each VAG signal.