首页>
外国专利>
CGMS and ECG-based hypoglycemic prediction system and control method
CGMS and ECG-based hypoglycemic prediction system and control method
展开▼
机译：CGMS和基于ECG的低血糖预测系统和控制方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
In the present invention, continuous blood glucose is measured together with an electrocardiogram signal, and as electrocardiogram-related parameters, QTc (QT interval corrected by heart rate), low frequency band intensity (P LF ), high frequency band intensity (P HF ), low frequency band high frequency band intensity Detecting the ratio (P LF / P HF ratio), applying the electrocardiogram-related parameters and blood sugar values as inputs to a previously learned SVM (support vector machine, support vector machine), and outputting whether or not hypoglycemia is from the SVM, It relates to a system for predicting hypoglycemia based on a continuous blood glucose meter and an electrocardiogram, which analyzes hypoglycemia more accurately, and a method for controlling the same. In the method of driving a hypoglycemia prediction system of the present invention, the blood glucose signal level determining step, wherein the operation processing unit determines the level of the received blood glucose signal based on the blood glucose level table stored in the memory unit based on the blood glucose signal received from the continuous blood glucose measurement unit. ; R peak detection and RR interval calculation step, wherein the operation processing unit detects R peaks in the electrocardiogram signal received from the electrocardiogram detector and calculates the R peak as the RR interval; A QTc calculation step in which the operation processing unit detects the start point of the Q wave and the end point of the T wave based on the R peak obtained in the R peak detection and the RR interval calculation step, and detects the QT interval (QTc) corrected by the heart rate; In the ECG signal output in the R peak detection and RR interval calculation step, when the number of samples in each RR interval is smaller than a predetermined number, interpolation is performed to fill in zeros, and the interpolated ECG is sampled at 4 Hz. and resampling; Fast Fourier Transform (FFT) is performed on the ECG output from the interpolation and resampling step, and the low frequency band intensity (P LF ) and high frequency band intensity (P HF ) are obtained from the ECG signal subjected to fast Fourier transform, and the low frequency band high frequency band Detecting an intensity ratio (P LF /P HF ratio), an electrocardiogram characteristic parameter detection step in the frequency domain; The QT interval (QTc) corrected by the heart rate obtained in the QTc calculation step, the low frequency band intensity (P LF ), the high frequency band intensity (P HF ), and the low frequency to high frequency band intensity ratio (P LF / P HF ratio) input to the pre-trained artificial intelligence model, and storing the hypoglycemia occurrence value output from the artificial intelligence model in the memory unit, or outputting to the output unit, hypoglycemia analysis step; characterized by including; do it with
展开▼
