Abstract
This paper mainly introduces the relevant contents of automatic assessment of upper limb mobility after stroke, including the relevant knowledge of clinical assessment of upper limb mobility, Kinect sensor to realize spatial location tracking of upper limb bone points, and GCRNN model construction process. Through the detailed analysis of all FMA evaluation items, a unique experimental data acquisition environment and evaluation tasks were set up, and the results of FMA prediction using bone point data of each evaluation task were obtained. Through different number and combination of tasks, the best coefficient of determination was achieved when task 1, task 2, and task 5 were simultaneously used as input for FMA prediction. At the same time, in order to verify the superior performance of the proposed method, a comparative experiment was set with LSTM, CNN, and other deep learning algorithms widely used. Conclusion. GCRNN was able to extract the motion features of the upper limb during the process of movement from the two dimensions of space and time and finally reached the best prediction performance with a coefficient of determination of 0.89.
Highlights
Cerebral apoplexy (CA), known as cerebral stroke or cerebral vascular accident (CVA), is a kind of acute cerebrovascular disease and is due to the sudden rupture of blood vessels in the brain or due to blood circulation obstruction caused by blood vessel damage caused by a group of diseases
According to the 2018 Report on Stroke Prevention and Treatment in China, the number of stroke patients in residents over 40 years old has reached 12.42 million, and since 2002, the incidence of the first stroke in residents between 40 and 74 years old has increased by 8.3% on average every year, and the number of deaths caused by stroke has reached 1.96 million every year
In order to avoid the interference of background and other external factors, improve the quality of data, and ensure the consistency, we first set up a unique experimental environment for the collection experiment of bone point position sequence required by model training. e Kinect V2 is mounted 1.5 meters away from a chair with a small armrest. e subject will sit in this chair and complete the rating task. e Kinect V2 connects to a PC via a USB cable to transfer data and instructions
Summary
Cerebral apoplexy (CA), known as cerebral stroke or cerebral vascular accident (CVA), is a kind of acute cerebrovascular disease and is due to the sudden rupture of blood vessels in the brain or due to blood circulation obstruction caused by blood vessel damage caused by a group of diseases. With the development of modern medicine, the level of treatment in the acute stage of the disease has been improved, and the number of death cases caused by stroke has gradually decreased, but the residual dysfunction has led to a gradual increase in the rate of disability, which greatly affects the healthy life of patients and their families. Sensor technology and artificial intelligence were integrated to carry out the research on automatic assessment of stroke upper limb motor function based on deep learning. Mullick et al discussed the influence of motion observation training based on the mirror neuron system on upper limb motor function of stroke patients [2]. In order to objectively quantify the upper limb motor injuries of stroke patients with hemiplegia, Fu et al proposed an assessment method based on motion coordination quantization and multimodal fusion. Fusion in sensor technology and artificial intelligence in this paper, based on in-depth study of the upper limb movement function stroke automatic evaluation of research, probes into the upper limb after stroke activity ability to automatically assess the related content, including the clinical ability of upper limb activity in clinical evaluation of relevant knowledge, called sensors for upper limb bones point spatial location tracking, and GCRNN model building process
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
