Classification of the Pathological Range of Motion in Low Back Pain Using Wearable Sensors and Machine Learning.

Low back pain (LBP) is a highly common musculoskeletal condition and the leading cause of work absenteeism. This project aims to develop a medical test to help healthcare professionals decide on and assign physical treatment for patients with nonspecific LBP. The design uses machine learning (ML) models based on the classification of motion capture (MoCap) data obtained from the range of motion (ROM) exercises among healthy and clinically diagnosed patients with LBP from Imbabura-Ecuador. The following seven ML algorithms were tested for evaluation and comparison: logistic regression, decision tree, random forest, support vector machine (SVM), k-nearest neighbor (KNN), multilayer perceptron (MLP), and gradient boosting algorithms. All ML techniques obtained an accuracy above 80%, and three models (SVM, random forest, and MLP) obtained an accuracy of >90%. SVM was found to be the best-performing algorithm. This article aims to improve the applicability of inertial MoCap in healthcare by making use of precise spatiotemporal measurements with a data-driven treatment approach to improve the quality of life of people with chronic LBP.

BackMov: Individualized Motion Capture-Based Test to Assess Low Back Pain Mobility Recovery after Treatment.

Low back pain (LBP) is a common issue that negatively affects a person's quality of life and imposes substantial healthcare expenses. In this study, we introduce the (Back-pain Movement) BackMov test, using inertial motion capture (MoCap) to assess lumbar movement changes in LBP patients. The test includes flexion-extension, rotation, and lateralization movements focused on the lumbar spine. To validate its reproducibility, we conducted a test-retest involving 37 healthy volunteers, yielding results to build a minimal detectable change (MDC) graph map that would allow us to see if changes in certain variables of LBP patients are significant in relation to their recovery. Subsequently, we evaluated its applicability by having 30 LBP patients perform the movement's test before and after treatment (15 received deep oscillation therapy; 15 underwent conventional therapy) and compared the outcomes with a specialist's evaluations. The test-retest results demonstrated high reproducibility, especially in variables such as range of motion, flexion and extension ranges, as well as velocities of lumbar movements, which stand as the more important variables that are correlated with LBP disability, thus changes in them may be important for patient recovery. Among the 30 patients, the specialist's evaluations were confirmed using a low-back-specific Short Form (SF)-36 Physical Functioning scale, and agreement was observed, in which all patients improved their well-being after both treatments. The results from the specialist analysis coincided with changes exceeding MDC values in the expected variables. In conclusion, the BackMov test offers sensitive variables for tracking mobility recovery from LBP, enabling objective assessments of improvement. This test has the potential to enhance decision-making and personalized patient monitoring in LBP management.

Artificial intelligence based glaucoma and diabetic retinopathy detection using MATLAB - retrained AlexNet convolutional neural network.

Background: Glaucoma and diabetic retinopathy (DR) are the leading causes of irreversible retinal damage leading to blindness. Early detection of these diseases through regular screening is especially important to prevent progression. Retinal fundus imaging serves as the principal method for diagnosing glaucoma and DR. Consequently, automated detection of eye diseases represents a significant application of retinal image analysis. Compared with classical diagnostic techniques, image classification by convolutional neural networks (CNN) exhibits potential for effective eye disease detection. Methods: This paper proposes the use of MATLAB - retrained AlexNet CNN for computerized eye diseases identification, particularly glaucoma and diabetic retinopathy, by employing retinal fundus images. The acquisition of the database was carried out through free access databases and access upon request. A transfer learning technique was employed to retrain the AlexNet CNN for non-disease (Non_D), glaucoma (Sus_G) and diabetic retinopathy (Sus_R) classification. Moreover, model benchmarking was conducted using ResNet50 and GoogLeNet architectures. A Grad-CAM analysis is also incorporated for each eye condition examined. Results: Metrics for validation accuracy, false positives, false negatives, precision, and recall were reported. Validation accuracies for the NetTransfer (I-V) and netAlexNet ranged from 89.7% to 94.3%, demonstrating varied effectiveness in identifying Non_D, Sus_G, and Sus_R categories, with netAlexNet achieving a 93.2% accuracy in the benchmarking of models against netResNet50 at 93.8% and netGoogLeNet at 90.4%. Conclusions: This study demonstrates the efficacy of using a MATLAB-retrained AlexNet CNN for detecting glaucoma and diabetic retinopathy. It emphasizes the need for automated early detection tools, proposing CNNs as accessible solutions without replacing existing technologies.