7 results about "Ventricular premature beats" patented technology

The patent discloses a ventricular premature beat detection method based on beat-in feature subwave complex network, first, through electrocardiosignal pretreatment, the collected electrocardiosignal is denoised and QRS wave is detected, the pretreated electrocardiosignal is segmented by heartbeats to obtain heartbeat signals, a single heartbeat is segmented by subwaves and the features of each part are calculated; for the obtained feature sequence, a detrending method is used to eliminate the regional difference of long-term electrocardiosignal features in different states and remove the slight fluctuations, so as to eliminate the influence of slight fluctuations on subsequent sequence coding; symbol dynamics is used for coding, and a beat-in feature subwave complex network is constructed, the network feature parameters of the complex network are calculated, finally, the electrocardiosignal features reflecting the characteristics of electrocardiosignal are extracted, and the classification of electrocardiosignal is realized through a machine learning classification algorithm.

The invention relates to an emergency treatment electrocardiogram grading early warning method and system based on edge intelligence, and the method comprises the steps: S1, carrying out the preprocessing and feature extraction of emergency treatment electrocardiogram data collected on an emergency ambulance through wavelet transform, and setting a dynamic threshold value; s2, anomaly detection and graded early warning are carried out on the preprocessed ECG signals through a support vector machine algorithm, and multi-stage emergency response is triggered according to early warning levels; s3, finely classifying the heart rhythm signals through a one-dimensional convolutional neural network, and identifying a plurality of arrhythmia types, including normal, supraventricular premature contraction, ventricular premature beat, fusion waves and unknown types; and S4, performing fusion decision on the multi-dimensional electrocardiogram evaluation indexes through an intelligent contract system based on a block chain, and generating an auditable comprehensive risk score. According to the method, real-time processing, anomaly detection, fine classification and credible decision-making of electrocardiogram data can be realized on the edge side of an emergency ambulance and the like, the dependence on stable connection of a cloud end is reduced, and the early warning timeliness and reliability are improved.

The invention provides an electrocardio fuzzy shielding pulse neural network method for ventricular premature beat detection, belongs to the technical field of electrocardio signal processing and intelligent diagnosis of arrhythmia, and solves the technical problems of poor origin lead adaptability, insufficient PVC (polyvinyl chloride) time sequence feature capture and low early recognition rate in 18-lead electrocardio signal ventricular premature beat detection. The method comprises the following steps: firstly, preprocessing 18 lead signals based on a ventricular premature beat data set; then, a learnable fuzzy coefficient module is designed, and four redundant leads irrelevant to ventricular premature beat are dynamically identified and shielded; then, reserving the time sequence characteristics of the ventricular premature beat QRS wave through threshold-time pulse coding; then, constructing a time attention LIF pulse neural network of the focused ventricular premature beat QRS wave; and finally, jointly training the optimization model to realize ventricular premature beat high-precision detection. According to the method, the dynamic time sequence difference of PVC can be efficiently captured, and an efficient auxiliary tool is provided for clinical ventricular premature beat screening and curative effect evaluation.

The invention provides a cross-dimension cross-task domain bio-electricity signal analysis method for migrating computer vision knowledge. The method comprises the following steps: performing feature extraction on a two-dimensional computer vision image and a one-dimensional bio-electricity signal by adopting a parallel encoding-decoding module; maintaining the discrimination capability of the specific features of the domain by reconstructing the loss; effective migration of knowledge from a computer vision domain with rich labels to a bio-electricity signal domain is realized by using a sharing classification module; and constructing a multi-core maximum mean value difference-based measurement module to realize cross-task domain self-adaption. According to the method, an end-to-end cross-dimension cross-task domain knowledge migration framework is provided, high-precision bio-electricity signal analysis under the condition of scarcity of labeled data can be achieved, and the application range of the method covers electrocardiosignal and cardiac beat recognition, ventricular premature beat detection and other bio-electricity signal classification tasks; the method has important application value in the fields of medical artificial intelligence, cardiovascular disease research, cross-domain knowledge migration and the like.

The invention discloses a cardiac ectopic origin point position prediction method and related equipment. The method comprises the following steps: training a cardiac ectopic origin point position prediction model on the basis of a pre-established premature beat standard database; in a training stage, correlation modeling is carried out in a cross-modal attention fusion module based on heart geometric feature representation output by a first deep learning sub-network and a second geometric deep learning sub-network; inputting the twelve-lead ECG time sequence of the target subject into a first deep learning sub-network, and inputting a personalized three-dimensional heart geometric model into a second geometric deep learning sub-network, and obtaining heart ectopic origin point confidence distribution at each candidate position on the surface of the personalized three-dimensional heart geometric model in a cross-modal attention fusion module. The problems that when premature beat of different ectopic origin points such as atrial premature, ventricular premature and border premature is clinically treated at present, a traditional method highly depends on personal experience of cardiologists, time is consumed, and the failure rate is high can be solved.

The invention discloses radix astragali and radix ginseng palpitation relieving granules and a quality detection method thereof. The optimal forming process of the radix astragali and radix ginseng palpitation relieving granules is screened out through a large number of experiments. According to the invention, the optimal thin-layer chromatography development condition is screened out, and qualitative identification research is carried out on salvia miltiorrhiza, radix astragali preparata and ligusticum wallichii in the quality detection method of the radix astragali, radix astragali and radix astragali palpitation relieving granules. According to the present invention, the optimal fluidity composition, the gradient elution mode and other chromatographic conditions are screened through a large number of experiments, the fingerprint detection method with characteristics of high precision, good stability and high accuracy is established, and the contents of the effective components such as calycosin-7-glucoside, ferulic acid, dihydroquercetin, ammonium glycyrrhizinate, nardosinone and the like can be simultaneously determined; and a quality detection method is provided for ensuring the safety and the effectiveness.

The application relates to a self-correlation clustering ectopic heartbeat recognition method, which comprises the following steps: step 1, collecting electrocardio signal data; step 2, data preprocessing; step 3, moving sliding window; step 4, establishing a function; step 5, obtaining atrial premature beat, ventricular premature beat and normal heartbeat correlation data sets; step 6, obtaining the minimum Euclidean distance of vectors in the atrial premature beat, ventricular premature beat and normal heartbeat correlation data sets; step 7, obtaining the maximum Euclidean distance of vectors in the atrial premature beat, ventricular premature beat and normal heartbeat correlation data sets; step 8, obtaining a to-be-detected electrocardio signal segment and performing data preprocessing, constructing a correlation data set phi of the signal segment, and constructing a function of phi and the Euclidean distance in the previous step; and step 9, judging the type of the to-be-detected electrocardio signal according to the function in step 8. The application has the beneficial effect that the position of an R wave and the heartbeat type can be given simultaneously, and the superposition of errors is avoided.