Quantification and identification of movement disorders in Parkinson's patients based on support vector machine

Abstract

The invention belongs to the technical field of signal recognition, and specifically relates to a support vector machine-based method for quantifying and identifying movement disorders of Parkinson's patients, aiming to solve the problem that the prior art cannot accurately quantify and identify the movement disorders of Parkinson's patients. The invention includes: obtaining wrist motion signals and ankle motion signals of the measured object and healthy persons; resampling and signal synthesis of the signals; extracting walking intervals through sliding windows; and extracting gait characteristics of the measured object and healthy persons respectively ; normalize the gait features and classify them through the trained support vector machine; calculate the Pr value, the interval Pr>0.9, 0.9>Pr≥0.6, 0.6>Pr≥0.5, Pr<0.5 respectively correspond to the measured object Severe Parkinson's patients, moderate Parkinson's patients, mild Parkinson's patients, non-Parkinson's patients. The present invention has high accuracy rate and high precision in the quantification and identification of Parkinson's patient's dyskinesia, takes up less resources, is also applicable to telemedicine, reduces costs, and improves efficiency.

Description

technical field [0001] The invention belongs to the technical field of signal identification, and in particular relates to a method for quantifying and identifying movement disorders of Parkinson's patients based on a support vector machine. Background technique [0002] Parkinson's disease is a chronic neurological disorder characterized by bradykinesia, tremor, stiffness, and abnormal posture and gait. At present, there are more than 6 million Parkinson's patients in the world, most of them are elderly people, and they need to be tested much longer than young people. It has been found in some medical research that extrapyramidal diseases represented by Parkinson's disease have the characteristics of high morbidity, high disability rate, and complex and diverse forms of movement disorders. In clinical work, clinicians mainly rely on clinical experience to determine the severity and judgment of Parkinson's patients. However, because clinical experience is too subjective, it...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned problems in the prior art, that is, the problem that the prior art cannot accurately realize the quantification and identification of Parkinson's patients' dyskinesias, the present invention provides a method for quantifying and identifying Parkinson's patients' dyskinesias based on a support vector machine. Methods include:

Images