Insole Systems for Disease Diagnosis and Rehabilitation: A Review

Abstract

Some chronic diseases, including Parkinson’s disease (PD), diabetic foot, flat foot, stroke, elderly falling, and knee osteoarthritis (KOA), are related to orthopedic organs, nerves, and muscles. The interaction of these three parts will generate a comprehensive result: gait. Furthermore, the lesions in these regions can produce abnormal gait features. Therefore, monitoring the gait features can assist medical professionals in the diagnosis and analysis of these diseases. Nowadays, various insole systems based on different sensing techniques have been developed to monitor gait and aid in medical research. Hence, a detailed review of insole systems and their applications in disease management can greatly benefit researchers working in the field of medical engineering. This essay is composed of the following sections: the essay firstly provides an overview of the sensing mechanisms and parameters of typical insole systems based on different sensing techniques. Then this essay respectively discusses the three stages of gait parameters pre-processing, respectively: pressure reconstruction, feature extraction, and data normalization. Then, the relationship between gait features and pathogenic mechanisms is discussed, along with the introduction of insole systems that aid in medical research; Finally, the current challenges and future trends in the development of insole systems are discussed.

Contemporary Machine Learning Approaches Towards Biomechanical Analysis in the Diagnosis and Prognosis Prediction of Knee Osteoarthritis: A Systematic Review

“…Kour et al (2022) and Bosel et al (2020), as explored within this review, have utilized simple 2-D video camera apparatus to gather biomechanical data, indicating possible areas for future inquiry [32,30]. Recent exploration of inertial sensor-based methods presents a more clinically applicable approach, in which wearable sensor technology is used to track and measure patient biomechanical data outside of a laboratory setting [14]. However, this alternative often comes at the expense of quality and the number of features able to be collected [52].…”

“…Existing studies have shown that alterations in the temporospatial and biomechanical parameters have been positively correlated to increasing severity of KOA [13]. While traditional approaches towards gait analysis utilize motion capture and cameras to capture parameters, often with high accuracy in laboratory settings, contemporary advancements in wearable sensor technology have facilitated a remote, cost-effective, and accessible method, often at the cost of accuracy and depth of information [14]. The ability for biomechanical data to be applied towards the diagnosis and prognosis prediction for KOA can increase accessibility for patients, and allow for earlier access to treatment, possibly relegating KOA to a preventable disease in the future [15].…”