Acoustic Emission Biomarkers for the Detection and Monitoring of Early Knee Osteoarthritis

Overview

The aim of this exploratory study is to further investigate the potential of acoustic emission biomarkers, assessed by the inmodi knee brace, to diagnose osteoarthritis (OA) at earlier stages. Therefore, 20 healthy participants and 100 patients with increased risk of knee OA will be recruited from the Schulthess Klinik in Zurich and examined twice with 9 ± 3 months' time interval. Anthropometric data, EOS radiographs and MR images of both knees, PROMs and acoustic emission data will be collected and evaluated. Artificial Intelligence algorithm will then be used to identify and validate the most promising acoustic emission biomarkers with a prognosis value in the prediction of knee osteoarthritis progress.

Disease background Osteoarthritis (OA) is a highly prevalent and disabling condition that affects over 7% of people globally (528 million people). It is significantly limiting their mobility and independent lifestyle. OA is mainly described by loss of cartilage, structural changes in bone, and inflammation of the synovium and joint capsule. Common risk factors include aging, obesity, prior joint injury and overuse. OA takes several years to develop, before the patient sees the doctor when pain intensifies. In early stages patients are asymptomatic or only experience activity related pain. The pain becomes constant over time with intermittent intense pain episodes. In regions around the world, the average annual cost of OA for an individual is estimated between USD $700-$15,600 (2019). Consequently, OA has a large socioeconomic impact due to its high medical costs, early retirements, and high absenteeism from work. OA typically affects the hips, knees, hands, feet, and spine, with a high prevalence of polyarticular involvement. This study focuses on OA of the knee. Current standard of assessment The current gold-standard assessment of the severity of knee OA is based on plain radiography, using the Kellgren-Lawrence (KL) grading system, which was accepted as a standard by the World Health Organization in 1961. This system does not evaluate the primary affected tissue - cartilage - but only the overall aspect of the joint. It is therefore unable to detect early stages of OA and the diagnosis is often established at a late stage, with few treatment options besides knee arthroplasty. Alternative assessment methods Earlier diagnostic and improved patient stratification is required to deploy preventive OA treatments. Possible early diagnostic options include Magnetic Resonance Imaging (MRI) and biochemical markers. MRI can be used to assess changes in cartilage volume, thickness or even quality, however, widespread use of MRI is limited by its high cost, availability, and the absence of a validated international score. Many biochemical markers are currently under investigation, but so far they lack specificity to joint tissues and to particular joints, and sensitivity and specificity are still not high enough for widespread clinical use. Recently, there has been a growing interest in acoustic analysis as an alternative to conventional biomarkers, particularly for the knee joint where poorly lubricated moving joint surfaces generate abnormal sounds that acoustic analysis could reveal. Relevance of the project The inmodi knee brace, developed at the ETH Lausanne is a device designed for an in-motion knee health assessment. Its core technology combines acoustic, thermal, and kinematic sensors and an artificial intelligence (AI)-based data analysis to extract relevant biomarkers of joint function. Preliminary data suggests that this combined approach may enable a non-invasive early diagnosis of OA. In horses, a strong association was found between the joint condition and the power of acoustic emission (AE) signals analysed. Combination of data (acoustic data/motion data) contains likely more information about the knee functional health, but such data is very heavy (computationally) and an algorithmic approach like AI seems the best option to extract meaningful parameters and combine them into clinically useful biomarkers. Recently, the investigators tested a prototype of inmodi knee brace in seventeen patients from the clinic shortly before total knee arthroplasty (TKA). These patients suffered from severe OA on the leg undergoing surgery and mild to moderate on the contralateral one. A machine learning algorithm was able to discriminate the leg states with a specificity of 0.96 (perfect = 1). The aim of this new project is to further explore the potential of the inmodi system to diagnose OA at earlier stages. For this the investigators will develop a preliminary reference database in a subpopulation at risk of developing OA. The identification and validation of novel biomarkers with an AI algorithm requires a training dataset and a test dataset, both with potential biomarkers and gold standard clinical outcomes for validation. This database will require a sample size large enough to be statistically sound to prevent statistical overfitting. Non-invasive knee health diagnostics should help identifying patients at risk at a relatively low cost and without radiation exposure and enable preventive measures to be implemented earlier than with standard radiographic measures. Risk category A (minimal): Imaging procedures contain (1) MRI of both knees, which is non-ionizing and (2) EOS full leg scan with much lower radiation dose of conventional radiography. Another procedure is the functional test with the inmodi knee brace of both legs. The probability that a biological effect on cells will occur from x-ray radiation is very low. Other risks are psychological, related to "screening overdiagnosis", or claustrophobic stress and noise discomfort in the MRI scanner. Further there is a risk on data privacy, which the investigators try to minimize by following the legal and internal data protection rules.