On the Early and Affordable Diagnosis of Joint Pathologies Using Acoustic Emissions, Deep Learning Decompositions and Prediction Machines.

The condition of a joint in a human being is prone to wear and several pathologies, particularly in the elderly and athletes. Current means towards assessing the overall condition of a joint to assess for a pathology involve using tools such as X-ray and magnetic resonance imaging, to name a couple. These expensive methods are of limited availability in resource-constrained environments and pose the risk of radiation exposure to the patient. The prospect of acoustic emissions (AEs) presents a modality that can monitor the joints' conditions passively by recording the high-frequency stress waves emitted during their motion. One of the main challenges associated with this sensing method is decoding and linking acquired AE signals to their source event. In this paper, we investigate AEs' use to identify five kinds of joint-wear pathologies using a contrast of expert-based handcrafted features and unsupervised feature learning via deep wavelet decomposition (DWS) alongside 12 machine learning models. The results showed an average classification accuracy of 90 ± 7.16% and 97 ± 3.77% for the handcrafted and DWS-based features, implying good prediction accuracies across the various devised approaches. Subsequent work will involve the potential application of regressions towards estimating the associated stage and extent of a wear condition where present, which can form part of an online system for the condition monitoring of joints in human beings.

A biomechanical confirmation of the relationship between critical shoulder angle (CSA) and articular joint loading.

BACKGROUND: The critical shoulder angle (CSA) has been shown to be correlated with shoulder disease states. The biomechanical hypothesis to explain this correlation is that the CSA changes the shear and compressive forces on the shoulder. The objective of this study is to test this hypothesis by use of a validated computational shoulder model. Specifically, this study assesses the impact on glenohumeral biomechanics of modifying the CSA. METHODS: An inverse dynamics 3-dimensional musculoskeletal model of the shoulder was used to quantify muscle forces and glenohumeral joint forces. The CSA was changed by altering the attachment point of the middle deltoid into a normal CSA (33°), a reduced CSA of 28°, and an increased CSA of 38°. Subject-specific kinematics of slow and fast speed abduction in the scapular plane and slow and fast forward flexion measured by a 3-dimensional motion capture system were used to quantify joint reaction shear and compressive forces. RESULTS: Increasing the CSA results in increased superior-inferior forces (shearing forces; integrated over the range of motion; P < .05). Reducing CSA results in increased lateromedial (compressive) forces for both the maximum and integrated sum of the forces over the whole motion (P < .01). DISCUSSION/CONCLUSION: Changes in the CSA modify glenohumeral joint biomechanics with increasing CSA producing higher shear forces that could contribute to rotator cuff overuse, whereas reducing the CSA results in higher compressive forces that contribute to joint wear.

Multivariate analysis of factors related to radiographic knee osteoarthritis based on the comparison between football players and matched nonsportsmen.

PURPOSE: Knee osteoarthritis (KOA) is the most common joint pathology worldwide and a major cause of later disability. It is unknown if the bone mass density (BMD) is correlated with KOA. This study aimed to investigate the prevalence of radiographic KOA among retired professional football players by comparing with matched nonsportsmen, and assess the correlation between BMD and KOA. METHODS: A cross-sectional, descriptive study was performed on a group of retired professional football players without history of knee injury. A control group of nonsporting volunteers was matched to the football player group in terms of age, height, weight, and body mass index (BMI). Uni- and multivariate analyses were performed to identify risk factors for KOA and predictors for knee function. RESULTS: Eighty-six retired male professional football players, with a mean age of 53 (51-58) years and an average period of professional career of 19.8 ± 6.3 years, were enrolled into the study group. Eighty-six subjects were included in the control group. Radiographic KOA was more common in the control group (45.3%) than in the study group (15.1%; χ 2 = 18.633, P < 0.001). While the HSS, IKS score, and BMD of spine, femoral neck, and trochanter were all higher among sportsmen than the nonsportsmen (z = 10.250, z = 10.450, z = 7.237, z = 8.826, z = 8.776, all P < 0.001). Independent risk factors for ROA were age (55-60 + years, aOR 9.159, P < 0.001) and BMD (decrease, aOR 16.226, P = 0.001; osteoporosis, aOR 8.176, P = 0.005). The mathematical model of multiple linear regression for the HSS and IKS score were Y = 127.217-3.334 age + 8.971 BMD + 4.752 occupation and Y = 57.784-3.022 age + 7.241 BMD + 4.730 occupation, respectively. CONCLUSIONS: This study reveals that low BMD and advanced age are independent risk factors for KOA. High BMD and regular exercise have a positive impact on knee function as evaluated with the use of HSS and IKS. Our findings guarantee further study to investigate the possibility that KOA may be caused by low BMD.