15 results about "Cardiac status" patented technology

The application discloses a physiological signal monitoring method and a wearable device, relates to the technical field of detection, and mainly aims to solve the problem of poor accuracy of existing electrocardiogram for heart state judgment. The method comprises the following steps: acquiring user basic information and a physiological signal collected in real time, wherein the physiological signal comprises a heart electrocardiogram signal, a muscle electrocardiogram signal and an acceleration signal, the physiological signal is collected based on a multi-modal sensor on a wearable device, and the wearable device is fixed on the user body through a belt type connection assembly; performing multi-modal fusion on the physiological signal based on a multi-modal fusion algorithm to obtain physiological parameter data, and determining a monitoring task, wherein the multi-modal fusion algorithm comprises one of parallel fusion, serial fusion and attention fusion; calling a monitoring prediction model matched with the monitoring task and having completed model training to perform monitoring processing on the physiological parameter and the user basic information, obtaining a monitoring result, and performing feature comparison based on the monitoring result.

The invention discloses an electrocardiosignal identification method based on a diffusion model and Bi-LSTM (Bidirectional Long Short Term Memory). The method comprises the steps that firstly, an electrocardiosignal is preprocessed, and wavelet transform is used for conducting noise reduction on the electrocardiosignal; then learning real electrocardiosignal data characteristics by using a diffusion model; the method comprises the following steps of: firstly, acquiring heart beat data, then utilizing a convolutional neural network and a Bi-LSTM feature extractor to learn heart beat features, finally, inputting the learned features into a full connection layer, and then utilizing softmax to obtain the probability that the heart beat data belong to a corresponding category, thereby realizing classification of electrocardiosignals. Finally, in order to detect the heart state of the patient in real time, the fully trained classification model is stored and migrated to a cloud end, then signals, collected by electrocardiosignal collecting equipment in real time, of the patient are input into the model, whether the heart rhythm of the patient is normal or not is judged, a result is fed back to a user, and therefore the patient can conveniently see a doctor and treat the patient in time.

The application is suitable for the technical field of data processing, and provides a heart state evaluation method and device, a terminal equipment and a storage medium. The method comprises the following steps: acquiring heart rhythm sample data, wherein the heart rhythm sample data comprises sample heart rhythm features and sample labels; training a preset scoring model according to the heart rhythm sample data to obtain a heart rhythm scoring model; inputting to-be-identified heart rhythm features into the heart rhythm scoring model to obtain a heart state evaluation score. The application can solve the problems that the existing heart health prompt scheme is not intuitive, the evaluation granularity is coarse, and users are difficult to recognize the heart health degree.

The application discloses a non-contact electromagnetic heart monitoring method based on signal semantic deconstruction, comprising the following steps: collecting non-contact reflected electromagnetic signals to generate electromagnetic phase signal data; performing semantic bottleneck modeling to compress and retain key semantic information related to the heart to generate a latent semantic representation tensor; constructing a semantic invariant disturbance signal, which is input into an encoder together with the electromagnetic phase signal for self-supervised reconstruction; constructing an electrocardiogram semantic space and performing cross-modal semantic alignment between the latent semantic representation tensor and the electrocardiogram semantic space; outputting an enhanced latent semantic representation tensor by using an improved TSMixer model; extracting rhythm drift information based on the enhanced latent semantic representation, constructing an individual heart rhythm semantic atlas, and outputting a heart state recognition result. The application realizes semantic-level stable modeling of non-contact heart monitoring, improves the accuracy, robustness and explainability of heart rhythm recognition, and is suitable for intelligent health monitoring and remote medical scenarios.

Provided are an information processing method and the like capable of supporting determination of a state of a heart on the basis of feature amounts calculated from an electrocardiogram, a heart sound waveform, or a pulse wave waveform. According to the present invention, a computer acquires an electrocardiogram, a heart sound waveform, and a pulse waveform of a patient. The computer acquires: a first feature amount by a first formula using a I sound position or a II sound position obtained from the heart sound waveform, a Q wave position obtained from the electrocardiogram, and a notch position and a pulse wave rising position obtained from the pulse wave waveform; a second feature amount by a second formula using a maximum amplitude of the I sound or an area obtained by time-integrating a waveform of the I sound, or the maximum amplitude of the II sound or the area obtained by time-integrating a waveform of the II sound; and a third feature amount by a third expression using an element feature amount obtained by using the pulse wave waveform. In a case in which the first feature amount to the third feature amount are input, the computer inputs the first feature amount to the third feature amount thus acquired to a trained model trained so as to output an estimated value of an intracardiac pressure of the patient, thereby acquiring the estimated value of the intracardiac pressure of the patient.

The application relates to the technical field of medical image diagnosis, and discloses a cardiovascular disease diagnosis model construction method based on image processing. The method comprises the following steps: collecting target patient heart medical image data, generating a standardized data set through pretreatment, and extracting a morphological and hemodynamic feature set; a heart state evolution feature map is established according to the feature dynamic evolution law, a pathological state space is divided, and the feature distribution density of a historical confirmed case is calculated; real-time image data of a patient to be diagnosed is acquired, and a real-time diagnosis feature vector is constructed; the vector is mapped to the pathological state space, the space matching degree is calculated to generate a pathological correlation index; a heart pathological probability prediction model is constructed in combination with the correlation index and the two types of feature sets, a pathological probability prediction value is output, and a grading diagnosis suggestion is generated. Through multi-dimensional feature analysis and space matching analysis, the method realizes accurate and grading diagnosis of cardiovascular diseases, and provides an efficient and feasible technical path for cardiovascular disease diagnosis.

The invention discloses an application of plasma mtDNA in predicting congenital heart disease related to gestational hyperglycemia, and the application comprises the following steps: detecting the copy number of plasma mtDNA of offspring, and comparing the copy number with a preset threshold value to predict the risk that the offspring suffers from the congenital heart disease related to the gestational hyperglycemia. According to the invention, animal experiments find that plasma mtDNA level change has clear correlation with fetal congenital heart disease induced by hyperglycemia in gestation period for the first time, show good stability and consistency in the animal experiments, and can objectively reflect the heart state; therefore, the prediction method for reflecting the occurrence risk of the fetal congenital heart disease under the hyperglycemia state in the gestation period is established by taking the plasma mtDNA as the biomarker, can be applied to basic research, risk assessment and related technology development of heart dysplasia related to the hyperglycemia in the gestation period, and has relatively high practical value and popularization significance.

This application provides a multi-source cardiac state assessment system based on adaptive weight allocation. The system includes: a signal quality assessment module for real-time calculation of the signal quality index of electrocardiogram (ECG), photoplethysmography (PPG), and echocardiography signals; a user motion state recognition module for identifying the user's current motion state; an adaptive weight allocation engine for dynamically allocating fusion weights for the ECG, PPG, and echocardiography signals in the cardiac state assessment based on the signal quality index and the user's motion state; and a cardiac state trend score generator for calculating a comprehensive trend score based on the weighted fusion features. The comprehensive trend score reflects the overall state and trend of cardiac function. This technical solution achieves continuous, personalized, and highly robust monitoring and risk warning of cardiac function.

A portable heart monitor includes a detecting unit to output a detecting light beam and receive a physiological response signal, wherein the physiological response signal is generated by the reaction of the detecting light beam and a finger of a user. The physiological response signal includes pulse waves of a perfusion index (PI). A processing and analyzing unit processes and analyzes the physiological response signal to acquire an analysis result, which is to be shown on a prompting unit. The analysis result includes heart status information based on processing of the pulse signals of the perfusion index (PI).

The invention discloses a non-contact electromagnetic heart monitoring method based on signal semantic deconstruction, and the method comprises the following steps: collecting a non-contact reflection electromagnetic signal, and generating electromagnetic phase signal data; semantic bottleneck modeling is carried out, key semantic information related to the heart is compressed and reserved, and a potential semantic representation tensor is generated; constructing a semantic invariant disturbance signal, and inputting the semantic invariant disturbance signal and the electromagnetic phase signal into an encoder for self-supervised reconstruction; constructing an electrocardio semantic space, and performing cross-modal semantic alignment on the potential semantic representation tensor and the electrocardio semantic space; outputting an enhanced potential semantic representation tensor by using an improved TSMIX model; and rhythm drift information is extracted based on the enhanced potential semantic representation, an individual heart rhythm semantic map is constructed, and a heart state recognition result is output. According to the method, semantic-level stable modeling of non-contact heart monitoring is achieved, the accuracy, robustness and interpretability of heart rhythm recognition are improved, and the method is suitable for intelligent health monitoring and remote medical scenes.

The utility model belongs to the technical field of medical auxiliary supplies, and particularly relates to a meridian auxiliary therapeutic apparatus. The device comprises a wearing part and a pressing main body; the wearing part can be worn on a limb, and a main control board is arranged on the wearing part; the number of the pressing bodies is multiple, the pressing bodies are arranged on the wearing body in the length direction of the wearing part in a sliding mode, monitoring probes used for monitoring the heart rate are arranged on the pressing bodies, and the monitoring probes are in signal connection with the main control panel. According to the main and collateral channel auxiliary therapeutic apparatus, the heart rate of a wearer can be monitored through the monitoring probe, the heart state of the wearer is judged according to the monitored heart rate information, and if the heart rate is irregular, the main control board can control the pressing main body to act so that the monitoring probe on the pressing main body can press the corresponding acupuncture point of the wearer, and the therapeutic effect is improved. Therefore, the symptom of arrhythmia of the wearer is relieved, and the situation of excessive fatigue of the heart is avoided.

The invention discloses a heart injury dynamic early warning method and system. The method comprises the following steps: collecting continuous real-time heart monitoring data, segmenting and aligning according to a time window to form a data fragment sequence, preprocessing data fragments, extracting heart injury monitoring indexes, and forming a real-time monitoring index sequence; constructing an individual statistical baseline based on the time window data meeting the stability criterion, calculating a center parameter and a discrete parameter, generating a control boundary, and carrying out online updating on the statistical baseline and the control boundary in the operation process; judging the real-time monitoring index by using the Shewhart control chart, and outputting a heart state evolution stage identifier; reconstructing operation parameters and reset rules of CUSUM change point detection by taking stage identification as a condition, and carrying out recursive calculation on a cumulative statistic sequence; and performing change point judgment based on the cumulative statistic sequence, and generating and outputting a dynamic early warning result in combination with the stage identifier. The invention belongs to the technical field of medical health data processing and intelligent monitoring and early warning.

The application provides a heart state risk prediction model training system, which comprises a data acquisition and preprocessing module, a multi-modal data adaptive fusion module, an attention mechanism-based deep prediction network and a risk prediction and visualization output module. The data acquisition and preprocessing module is used for acquiring multi-modal physiological signal data and preprocessing the data. The multi-modal data adaptive fusion module is used for receiving the preprocessed multi-modal physiological signal data, adaptively weighting and fusing the features of different modalities through a gating fusion mechanism and outputting a fused feature vector. The attention mechanism-based deep prediction network is used for receiving the fused feature vector, extracting time sequence features through a hybrid neural network and outputting a heart disease risk probability. The risk prediction and visualization output module is used for converting the heart disease risk probability into an understandable risk level and visually displaying the risk level. In the above technical solution, the individual differences of different populations and long-term health monitoring requirements are met.

Some aspects relate to systems, devices, and methods of assessing heart rate recovery. A patient's heart rate can be measured during a plurality of heart rate recovery events. Each heart rate recovery event of the plurality of heart rate recovery events includes a duration of time following an activity that causes an increase in heart rate. Heart rate recovery information can be determined based on the measured heart rate during each heart rate recovery event of the plurality of heart rate recovery events, and a cardiac status of the patient can be generated from the determined heart rate recovery information within the plurality of heart rate recovery events.

The application discloses a kind of ECG mapping signal characteristic value change heart state monitoring method, comprising the following steps: step 1, using electrocardiogram signal acquisition instrument obtains the ECG signal to be measured;Step 2, according to the signal to be measured obtained in step 1, establish transpose matrix;Step 3, the similarity of the transpose matrix of the signal to be measured in step 2 and the transpose matrix of reference signal is calculated;Step 4, according to the similarity calculated in step 3, whether the judgment of cardiac state anomaly is carried out.The application has the characteristics such as strong anti-noise interference ability, self-adaptability between different equipment, life state quick perception, can be quickly carried out after obtaining the robust identification of body state ECG signal.