Rapid eye movement period sleep behavior disorder classification method based on sleep electroencephalogram

Abstract

The invention discloses a rapid eye movement period sleep behavior disorder classification method based on sleep electroencephalogram. The method comprises the following steps: preprocessing an acquired sleep electroencephalogram signal of a patient, acquiring an electroencephalogram signal of an electroencephalogram interval in a sleep R period, cutting according to a preset signal length to acquire a plurality of sub-signal segments, layering an original electroencephalogram signal of each sub-signal segment, and enabling a frequency domain component after wavelet transform to approximatelycorrespond to different wave bands of original electroencephalogram according to the frequency of the electroencephalogram; carrying out empirical mode decomposition (EMD) to obtain a multilayer intrinsic mode function (IMF); performing feature extraction on the electroencephalogram signals of different wave bands and the multilayer intrinsic mode function, and performing dimensionality reductionon the feature set PCA to obtain a low-dimensional feature set; and carrying out classification and identification by using the feature set after dimension reduction, and classifying patients suffering from Parkinson's disease accompanied by rapid eye movement sleep disorder, Parkinson's disease not accompanied by rapid eye movement sleep disorder and idiopathic rapid eye movement period sleep behavior disorder. Complex PSG detection is simplified into electroencephalogram detection, a whole night does not need to be consumed, the number of times of measurement is reduced, an accurate recognition result is obtained, and then a very good auxiliary effect can be achieved on treatment of the illness state of a patient.

Description

technical field [0001] The present application relates to the field of biomedical technology, in particular to a classification method for rapid eye movement sleep behavior disorder based on sleep EEG. Background technique [0002] Parkinson's disease (PD) is a neurodegenerative disease that is more common in the elderly. The onset of PD is hidden. At present, the clinical diagnosis and treatment of PD mainly depends on the appearance of motor symptoms. The course of PD is chronic and progressive, with a long disease period and high disability rate. After about 5-8 years, half of the patients need help, which seriously affects the patient's life The standard of living and quality of life have brought great pain to patients and their families. [0003] Rapid eye movement sleep behavior disorder (RBD) is a sleep disorder characterized by dreams and physical activity during rapid eye movement (REM) sleep. Violent behavior during attacks can cause Self and bedmates injure and ...

AI Technical Summary

Problems solved by technology

The timeliness and continuity of the scale are low. Although PSG is widely used in RBD detection, it is expensive and time-consuming. Each measurement takes a whole night, and due to the uncontrollable behavior of patients during sleep In order to obtain accurate data, patients may need to take multiple measurements, which consumes time, energy, and financial resources. Patients often do not take the initiative to receive PSG diagnosis before the condition worsens, which leads to delays in the condition

Images