A SYSTEM FOR MONITORING THE PROGRESS OF REHABILITATION OF PATIENTS WITH MUSCULOSKELETAL DISORDER

The work is devoted to the development of a system for monitoring the rehabilitation process of patients with musculoskeletal disorders, as well as identifying possible postural distortions in both children and adults based on anthropometric data, which confirms the relevance and practical significance of the work during the period of military operations in Ukraine and a large number of people with musculoskeletal injuries. The paper proposes a model of a system consisting of two subsystems: a subsystem for collecting pododynamic parameters based on a dynamic baropodometric platform and a visual posture monitoring subsystem. The combination of different gait and posture analysis methods in a single system provides high diagnostic and prognostic value. The main purpose of the proposed system is to monitor the progress of patient rehabilitation using hardware and computer-optical diagnostic methods without radiation exposure with the ability to easily transport the created system, the possibility of high-precision diagnostics in real time, as well as the ability to store and analyze changes in the musculoskeletal system over time. For the collection and analysis of pododynamometric parameters, computer data visualization methods, methods of statistical and dynamic data analysis, and data segmentation methods were used. To collect and analyze anthropometric parameters, methods of detecting objects in the image, methods of computer classification, segmentation and image processing, methods of analyzing graphic information were used. In addition, the paper researches the influence of marker characteristics (shape, color model of representation) and lighting conditions during the acquisition of kinematic parameters on the accuracy of marker detection for further determination of the angles of the pelvis and shoulder line. The results obtained by using the hybrid marker detection algorithm show that the representation of any of the used shapes in all the colors under study in the presence of additional lighting gives 100% marker detection accuracy, only in the HSV color model for a simple scene. The RGB model provides 100% accuracy in detecting only yellow markers with additional lighting. In the absence of the possibility of using additional lighting, only round markers in all the studied colors represented in the HSV color model can achieve 100% accuracy. For a complex scene, representing the input images in the RGB color model does not allow achieving 100% accuracy for any of the marker shapes and colors, even with additional lighting. The highest accuracy for a complex scene is also shown by round markers colored in green or orange, regardless of the presence of additional lighting. Further research will focus on expanding the range of system parameters necessary for diagnosing the patient's condition and analyzing the course of treatment using electromyographic indicators.