44 results about "Cardiac sounds" patented technology

The utility model discloses a kind of postoperative atrial fibrillation monitoring alarm systems, it is related to the technical field of atrial fibrillation monitoring, and it includes: main control module, detection module, storage module, display module, input-output module and alarm module;Detection module detects the electrocardiosignal, pulse voltage signal and heart sound signal of postoperative patient, sends to main control module;Main control module carries out sampling to electrocardiosignal, pulse voltage signal and heart sound signal, and stores to storage module;According to the instruction of input-output module, the signal after selection sampling is displayed through display module, and the signal stored is selected from storage module and is displayed through display module;Threshold comparison unit of main control module sends signal to alarm module according to heart rate signal, pulse signal, heart sound signal and threshold value, and alarm module sends alarm prompt.The utility model can monitor the sign data of postoperative patient and send alarm, remind medical staff to handle in time, reduce the influence of postoperative atrial fibrillation on patient recovery.

A kind of heart sound sensing structure and its preparation method, the structure includes double SOI substrate, center mass, elastic support beam, piezoresistive sensing unit and capacitive sensing unit.The front surface of center mass is provided with additional mass layer, and the back surface is kept bottom layer silicon to increase thickness;Elastic support beam connects mass and frame;Piezoresistive sensing unit is composed of four piezoresistors to form wheatstone bridge, and capacitive sensing unit includes movable and fixed comb-tooth capacitive plate crossing each other.When the sound pressure gradient of heart sound signal drives mass to deviate, elastic support beam bends to change piezoresistive value, and at the same time, comb-tooth capacitive plate overlapping area changes to cause capacitive value change, to realize piezoresistive and capacitive dual-mode synchronous detection.Two kinds of detection mechanisms calibrate each other, which significantly improves the sensitivity and anti-interference ability of low-frequency heart sound signal.The preparation method is based on double SOI substrate, integrated by ion implantation, etching, metal deposition and 3D printing process, suitable for miniaturized wearable heart sound monitoring application.

This utility model relates to a blood pressure monitor, disclosing a multifunctional blood pressure monitor including a main unit and a secondary unit. A cuff is installed at the lower end of the main unit, and a first main control board is installed inside the main unit. The secondary unit contains a second main control board and a battery, which is connected to and powers the second main control board. Electrodes are also installed on the secondary unit and connected to the second main control board. The main unit and the secondary unit are detachably connected. When the secondary unit is mounted on the main unit, the battery is connected to the first main control board via the second main control board. The battery in the secondary unit not only ensures the normal operation of its own ECG and heart sound measurement functions but also, when mounted on the main unit, powers the first main control board of the main unit via the second main control board. This power supply mode solves the problem of separate power supply for the main unit and achieves the organic integration of blood pressure, ECG, and heart sound measurement functions. Users do not need to prepare multiple power supply devices, reducing operating costs.

This invention discloses a non-contact electrocardiogram (ECG) measurement method using millimeter-wave radar. First, the original chest wall displacement signal acquired by the millimeter-wave radar is preprocessed to obtain a displacement feature branch input. Then, the original displacement signal undergoes cardiac sound band enhancement, wavelet denoising, and envelope extraction to obtain radar cardiac sound features. A hidden semi-Markov model is constructed to model the states of the first heart sound, systole, second heart sound, and diastole in the cardiac cycle, obtaining the posterior probability of the state at each time point. Next, the displacement features, radar cardiac sound features, and state probability features are input into a multi-branch convolutional fusion network, combined with a bidirectional long short-term memory network to achieve temporal correlation modeling, finally outputting the reconstructed human ECG result. This invention achieves non-contact ECG measurement without skin electrode contact by fusing the original mechanical displacement of the chest wall, the mechanical vibration features of the heart sounds, and the explicit state prior information of the cardiac cycle.

An in-ear device (IED) of a wearable system captures audio data from within the ear canal of a user indicative of the user's heartbeat. The IED when worn occludes the user's ear canal, causing amplification of low frequency sounds due to the occlusion effect, and improving the ability of the acoustic sensor to detect the user's heartbeat sounds. The wearable system classifies the audio data to identify portions of the audio data corresponding to a first heart sound and a second heart sound, which correspond to different portions of the heartbeat of the user. The wearable system estimates a blood pressure level of the user based upon the identified heart sounds.

This invention discloses a method and apparatus for heart sound segmentation based on a Hidden Markov Model (HMM) cardiac cycle. The method involves: extracting the signal envelope from the heart sound signal using Hilbert's algorithm; obtaining the peak positions of the first heart sound (S1) and the second heart sound (S2) after Hilbert envelope extraction based on preset baselines for different leads; locating the peaks based on the cardiac cycle; extracting the diastolic phase based on an improved HMM; locating the optimal time span of heart sound signals S1 and S2 using an improved Viterbi algorithm; and segmenting the original heart sound signal using the time span and the peak positions of S1 and S2. This invention employs an improved HMM and an improved Viterbi forward algorithm to calculate the duration of heart sound intervals S1 and S2, combined with the cardiac cycle, to accurately locate the peak positions of heart sound intervals, thus improving the performance of heart sound segmentation.

The application discloses a kind of based on heart sound double-flow feature coordination's intelligent identification method for children's congenital heart disease, belong to biomedical signal processing technical field.The method obtains child heart sound audio signal and carries out pretreatment, respectively extracts heart sound time-frequency energy feature and heart sound gamma pass feature, is coupled and is constructed double-flow multidimensional heart sound feature map after time domain resolution synchronous processing;Characteristic map is input hierarchical time-frequency analysis network, with noise suppression unit filters out environmental disturbance, with key feature focusing unit highlights abnormal heart sound feature;Combined with difficult and easy sample balance strategy training model, output classification prediction probability.The application is improved through double-flow feature complementation and multi-stage feature enhancement, heart sound feature expression and anti-interference ability, help to improve the stability and reliability of the intelligent identification of children's heart sound anomaly.

The present application relates to the technical field of artificial intelligence, and in particular to a cardiovascular health risk prediction method and device, equipment and medium. In the present application, the phase encoding feature is embedded into the electrocardiogram encoding feature and the heart sound encoding feature to obtain the enhanced electrocardiogram feature and the enhanced heart sound feature, realizing the time sequence alignment enhancement of the phase information to the electrocardiogram signal and the heart sound signal. The embedding mechanism enables the model to explicitly perceive the relative time sequence position relationship of the electrocardiogram signal and the heart sound signal in the cardiac cycle, and strengthens the correlation expression of different modal signals at the same phase moment. The enhanced electrocardiogram feature and the enhanced heart sound feature are fused along the feature dimension, providing rich multi-modal representation basis for accurate prediction of cardiovascular health risk. Based on the fused features, the cardiovascular health risk is predicted, which can fully utilize the complementary information of the electrocardiogram signal and the heart sound signal, and significantly improve the accuracy of the cardiovascular health risk prediction.

The application discloses a kind of heart sound abnormality detection method and system based on earphone, belong to signal processing technical field.The method includes: obtaining the earphone microphone collected ear sound signal;Based on the physical information neural network constructed in advance, the ear sound signal is calculated inversely;Based on the constructed neural network, the mapping of inverse signal and real heart sound label is completed, and the reconstructed heart sound chart is obtained;Based on the reconstructed heart sound chart, abnormality detection identification is carried out;Physical information neural network includes source pulse wave inversion network HemoNet and source heart sound inversion network CardiNet;HemoNet is obtained in ear drum at arterial pulse pressure wave by ear sound signal inversion, and source pulse wave is obtained at heart;CardiNet is inverted into source heart sound signal at heart by heart sound collected in thoracic cavity;MappingNet generates heart sound signal by source pulse wave signal mapping, and obtains reconstructed heart sound chart.Improve the physical consistency and accuracy of reconstructed signal, realize accurate inversion source pulse wave signal and heart sound reconstruction, improve the convenience and accuracy of heart rate monitoring.

1. The name of the design product: heart sound detector. 2. The use of the design product: for detecting electrocardio and heart sound data. 3. The design points of the design product: in shape. 4. The picture or photo that best shows the design points: perspective view.

The application discloses a heart sound positioning method, system, device and computer readable storage medium, and relates to the technical field of physiological signal processing. The method comprises the following steps: acquiring a PPG signal and a PCG signal collected, performing envelope extraction on the PCG signal to obtain a PCG envelope line; identifying a wave trough position time point of the PPG signal, determining a target time window based on the wave trough position time point, wherein the target time window comprises a first target time window and / or a second target time window, the first target time window is a time window before the wave trough position time point, and the second target time window is a time window containing the wave trough position time point or after the wave trough position time point; identifying a peak time point of the PCG envelope line in the target time window, and determining the peak time point as a heart sound positioning result for the PCG signal. The application improves the robustness and accuracy of heart sound positioning.

Disclosed are an interaction apparatus of wrist-worn device and a wrist-worn device. The interaction apparatus of wrist-worn device includes a main structure including a housing and a mainboard disposed on the housing, and a signal acquisition portion disposed protruding from a side peripheral surface of the housing, the signal acquisition portion includes a physiological sound sensor used for detecting heart sound signals or lung sound signals. The physiological sound sensor collects a vibration signal of the heart or lung and transmits the signal to the mainboard, the mainboard processes the signal to monitor the heart or lung. According to the present disclosure, the cost of replacing the wristband is reduced; the original inner structure of the housing is prevented from being modified; and when the hand is lifted, the signal acquisition portion can be directly attached to the heart position or the lung position for signal detection.

To provide a heart sound detector and a heart sound detection method capable of presenting to a medical care worker such as a doctor, states of A2 and P2 constituting an II sound, in a manner of capable of easily grasping the states.SOLUTION: A heart sound detector comprises: an acquisition part for acquiring a heart sound diagram of a subject; an II sound position detecting part for detecting a position of an II sound included in the heart sound diagram; a wavelet transformation part for performing wavelet transformation to the heart sound diagram with a prescribed window width including, the II sound position detected by the II sound detecting part; and a display part for displaying a time frequency analysis image being obtained by the wavelet transformation.SELECTED DRAWING: Figure 6

The application discloses a kind of based on heart sound double-flow feature coordination's intelligent identification method for children's congenital heart disease, belong to biomedical signal processing technical field.The method obtains child heart sound audio signal and carries out pretreatment, respectively extracts heart sound time-frequency energy feature and heart sound gamma pass feature, is coupled and is constructed double-flow multidimensional heart sound feature map after time domain resolution synchronous processing;Characteristic map is input hierarchical time-frequency analysis network, with noise suppression unit filters out environmental disturbance, with key feature focusing unit highlights abnormal heart sound feature;Combined with difficult and easy sample balance strategy training model, output classification prediction probability.The application is improved through double-flow feature complementation and multi-stage feature enhancement, heart sound feature expression and anti-interference ability, help to improve the stability and reliability of the intelligent identification of children's heart sound anomaly.

This application discloses a method and electronic device for analyzing heart sounds, relating to the field of biomedical signal processing technology. The method includes: acquiring a target electrocardiogram (ECG) signal, a target heart sound signal, and a target pulse signal; determining a first heart sound and a second heart sound from the target heart sound signal based on a first time point corresponding to the R-wave peak point in the target ECG signal and a second time point corresponding to the trough point in the target pulse signal, and determining the first heart sound envelope peak value and the second heart sound envelope peak value; identifying three valid heart sound peak points in the first heart sound based on the first heart sound envelope peak value, and identifying two valid heart sound peak points in the second heart sound based on the second heart sound envelope peak value; and performing heart sound analysis based on the five valid heart sound peak points to obtain the heart sound analysis result. This application can more accurately resolve heart sound signals in low signal-to-noise ratio environments, thereby improving the practicality and reliability of heart sound signals in health monitoring and clinical decision support.

This invention discloses a method, apparatus, device, and medium for detecting atrial fibrillation heart sounds in a small sample. The method includes: preprocessing heart sound signals, constructing a source domain dataset and a heart sound feature extraction network, training the heart sound feature extraction network using labeled data to obtain pre-trained weights; using heart sound data diagnosed with atrial fibrillation as target domain small sample data, freezing the shallow parameters in the heart sound feature extraction network, and employing an imbalanced learning strategy to obtain a fine-tuned model adapted to the target domain; using the fine-tuned model to predict unlabeled or weakly labeled heart sound data; calculating confidence based on the obtained atrial fibrillation prediction probability, selecting heart sound data with confidence higher than a preset confidence threshold, and generating pseudo-labels; using labeled data, target domain small sample data, and heart sound data with pseudo-labels to form a mixed training set, iteratively retraining the heart sound feature extraction network to obtain an atrial fibrillation heart sound recognition model, and using this model to predict atrial fibrillation in detected heart sound signals.

The invention discloses an agent-guided pruning lightweight heart sound classification method, and relates to the technical field of medical signal processing and artificial intelligence, and the method comprises the steps: obtaining heart sound data of patients with different cardiovascular diseases, marking the types, and forming a heart sound data set; preprocessing the acquired heart sound data; constructing a double-pooling lightweight self-adaptive Mangbar model and training the model; and outputting a heart sound classification result through a double-pooling lightweight self-adaptive Mangbar model and intelligent agent guided pruning quantification processing. According to the method, the features of different types of heart sounds can be deeply extracted in combination with a double-pooling lightweight self-adaptive Mangbar model, accurate feature extraction of the heart sounds is realized by introducing depth separable convolution, designing a state space model and a self-adaptive wavelet activation function, and it is ensured that the efficient and stable heart sound classification capacity is still kept in a changeable environment; the size of the model is further compressed by utilizing the pruning quantification processing model guided by the intelligent agent, the parameter quantity of the model is reduced, and the operation efficiency of the model is improved.

A system and method for determining heart-related biometric data is presented that includes an earpiece device device to receive audio signals and isolate right and left heartbeat signals from the received audio signals, an extraction module to process the isolated right and left heartbeat signals to generate right and left PCG1, PCG2 signals, a pre-processing module to perform signal processing on the PCG1, PCG2 signals to determine PTT11, PTT12 signals, and a processing module to perform signal processing on the PTT11, PTT12 data signals to provide an indication of heart-related conditions. Furthermore, incorporating morphological detection techniques on the PCG1, PCG2, PTT11, PTT12 signals to generate an MD data signal and incorporating a user-wearable device to generate a third heart-related signal that is further processed to generate PTT2, PTT3 data signals.

This utility model relates to health monitoring equipment, disclosing a combined ECG and heart sound monitoring device, including a housing, a stethoscope head, a first electrode pad, and a second electrode pad. A main control board is installed inside the housing, and a display module is mounted on the upper surface of the housing, connected to the main control board. The stethoscope head is mounted on the lower surface of the housing and connected to the main control board via wiring. The main control board collects audio signals through the stethoscope head, processes them, and displays them on the display module. The first and second electrode pads are respectively mounted at both ends of the housing and connected to the main control board. The main control board collects ECG signals through the first and second electrode pads, processes them, and displays them on the display module. The first and second electrode pads, mounted at opposite ends of the housing, enable more accurate and stable ECG signal collection. The device offers excellent ease of operation; its integrated design combines display, acquisition, and processing functions, avoiding complex operating procedures, making it easy for both professional medical personnel and ordinary users to use.

The application discloses a blood pressure estimation method, a wearable device and a readable storage medium, and relates to the technical field of signal processing. The method comprises the following steps: collecting a physiological signal, wherein the physiological signal comprises at least one of a heart sound signal, an electrocardio signal and a pulse signal; inputting the physiological signal into a blood pressure estimation model which is pre-trained, wherein the blood pressure estimation model comprises a feature extraction network and a result estimation network; performing multi-scale feature extraction on the physiological signal by the feature extraction network, and fusing the extracted signal features of different scales to obtain fused features; and estimating the blood pressure based on the fused features by the result estimation network to obtain a blood pressure estimation result. The application realizes long-term blood pressure estimation with high accuracy.

The application relates to a data collection method and device, computer equipment and a computer readable storage medium. The method comprises the following steps: in response to a timer interrupt instruction, entering a timer interrupt program, starting a clock counter and recording an initial count value; in the timer interrupt program, starting an electrocardiogram measurement module, a heart sound measurement module and a blood pressure measurement module according to a preset order according to preset assembly instructions, and measuring state data corresponding to a user; when the current count value of the clock counter reaches a threshold value, closing the electrocardiogram measurement module, the heart sound measurement module and the blood pressure measurement module according to the preset order based on the corresponding assembly instructions to obtain a target data set; based on the initial count value and the current count value, a data collection duration is obtained, and based on the target data set and the data collection duration, target state data is obtained. The method can realize high-precision synchronous collection of electrocardiogram data, heart sound data and brachial artery pressure data.

The application discloses an intelligent heart sound classification method based on real-time streaming signal denoising and bispectrum characteristics, and comprises the following steps: S1, collecting heart sound signals through a heart sound sensor, amplifying and filtering the initial signals, and completing envelope extraction and digitization conversion of the heart sound signals; S2, pre-processing and intelligently denoising the digital signals, and extracting bispectrum characteristics of the denoised pure digital signals; S3, inputting the bispectrum characteristic two-dimensional image tensor into a trained heart sound intelligent classification network model, and outputting the probability distribution of five states of normal heart sound, aortic valve stenosis, mitral valve regurgitation, mitral valve stenosis and mitral valve prolapse. According to clinical data verification, the accuracy rate of the application in the abnormal heart sound recognition task reaches 96%, and the accuracy rate is improved by about 5% compared with similar algorithms.

The application discloses a flexible electrode for integrated sensing of electrocardio and heart sound. The dry electrode is used for noninvasive collection of human body surface Laplace electrocardio signals. The dry electrode and a collection system thereof are composed of three parts. The first part is a multilayer bioelectric dry electrode based on silk screen printing, which is composed of a. an electrocardio signal collection electrode (right limb RA), b. an electrocardio signal collection electrode (left limb LA) and c. an electrocardio signal collection electrode (right leg RL). The second part is d. a front-end signal conditioning circuit, which is composed of a filter circuit and a power follower. The filter circuit is used for filtering high-frequency noise such as electromyographic noise and part of low-frequency baseline drift signals. The power follower is used for inhibiting signal attenuation, providing low output impedance, enhancing signal anti-interference ability, improving system signal-to-noise ratio and ensuring signal integrity. The third part is e. a system processing and transmission circuit, which is composed of a filter, a main control chip and a Bluetooth module. The main control chip part completes processing of the Laplace signal, and obtains a Laplace electrocardiogram.

This application provides a method, system, electronic device, and storage medium for processing electrocardiogram (ECG) and heart sound data. A terminal processor simultaneously acquires ECG and heart sound data of a target user through an ECG and heart sound monitoring device and body status data of the target user through a body status monitoring device within a first time period. Based on the body status data, the reliability of the ECG and heart sound data is determined. If the reliability exceeds a preset value, a first analysis strategy for the ECG and heart sound data is calculated based on the current data processing pressure of the terminal processor and the current data processing pressure of the cloud server. The first analysis strategy includes the analysis content of the terminal processor and the analysis content of the cloud server, and the analysis content of the cloud server is uploaded to the cloud server. The cloud server analyzes the analysis content of the cloud server according to the determined analysis method to determine the cloud analysis result. This application can improve the efficiency of ECG and heart sound detection.

The application relates to the technical field of medical artificial intelligence, and particularly discloses a heart mechanical efficiency evaluation method based on a strain-blood flow coupling model, which comprises the following steps: synchronously collecting electrocardio, heart sound and photoelectric volume pulse wave signals, adopting master-slave clock synchronization and R wave triggering alignment to realize multi-modal signal timing calibration; extracting myocardial strain rate, stroke volume and systolic energy consumption coefficient based on the calibrated signals, and constructing a strain-blood flow coupling efficiency index; dynamically calibrating the coupling efficiency index through a double-parameter self-calibration mechanism of heart rate drift and heart rate change rate; and finally combining multi-scale feature extraction and a gradient boosting decision tree model to output a heart mechanical efficiency grade and an ischemia risk probability; the application solves the problems of missing dynamic load evaluation, isolated multi-modal parameters and insufficient individual difference adaptability in the prior art, and realizes early myocardial ischemia detection sensitivity and wearable device-level real-time monitoring capability.

The application relates to the technical field of wearable fetal heart detection, in particular to a fetal heart rate estimation and event detection method and system based on a multi-modal quality factor driving, which comprises the following steps: collecting multi-modal data in multiple channels and aligning; selecting a maternal R peak sequence as a time anchor point in electrocardiogram data to construct a maternal heart sound template and a maternal electrocardiogram template and calculate heart sound residuals and electrocardiogram residuals; performing blind source separation to obtain a plurality of different classified sources and performing optimization sorting; performing time-frequency transformation on a target source and decomposing a plurality of bases, and applying rhythm constraints to construct a plurality of candidate FHR paths and perform cutting; detecting a fetal heart R peak sequence, comparing the fetal heart R peak sequence with the maternal R peak sequence, estimating a heart rate curve and realizing maternal-fetal separation; constructing a quality factor, classifying a segment set corresponding to each time window based on the quality factor, and outputting a fetal heart rate result. The application can improve fetal heart rate monitoring and analysis effect.

This invention discloses a non-contact ECG generation method based on radar signals and enhancement strategies. First, synchronously acquired radar heart sound signals and ECG signals are preprocessed and enhanced in multiple dimensions to construct training samples. Then, an encoder network is used to extract deep features from the radar heart sound signals step by step. Next, a multi-head self-attention mechanism and a bidirectional long short-term memory network are used to capture long-range waveform dependencies and temporal context. A high-fidelity ECG is then reconstructed via a hierarchical upsampling decoder. Finally, a four-dimensional loss function that integrates amplitude, phase, R-wave localization, and frequency domain consistency is used to optimize the model parameters. This method can reconstruct clinically diagnostic ECGs with high accuracy from non-contact radar signals. While effectively preserving key waveform morphologies such as the P wave, QRS complex, and T wave, it significantly improves waveform correlation, key feature localization accuracy, and the accuracy of long-term heart rate variability analysis.

This invention discloses a wearable heart sound detection system, comprising: an acoustic sensing device for collecting heart sound signals from the body, performing preprocessing such as signal amplification, filtering, and digitization on the collected heart sound signals, and outputting a preprocessed heart sound signal; an external computing electronic device communicatively coupled to the acoustic sensing device for acquiring the preprocessed heart sound signal; and a cloud database communicatively coupled to the external computing electronic device; wherein the acoustic sensing device includes a capacitive sound sensor, a piezoelectric sound sensor, and a circuit module, the circuit module being electrically connected to the capacitive sound sensor and the piezoelectric sound sensor respectively; the circuit module, the capacitive sound sensor, and the piezoelectric sound sensor are mounted on a flexible substrate.

The utility model discloses a portable heart sound pulse wireless synchronous acquisition device, including the casing, be equipped with battery, microcontroller and signal acquisition board in the casing, microcontroller installs on the signal acquisition board, and battery electricity is connected to the signal acquisition board, and the front side of casing is embedded with heart sound sensor interface and pulse sensor interface, and heart sound sensor interface is detachably electrically connected with heart sound sensor, and pulse sensor interface is detachably electrically connected with pulse sensor, and the front side of casing is still embedded with power switch and power indicator, and the right side of casing is embedded with charging interface and charging indicator, the utility model discloses simple and easy integration structure design, wireless synchronous acquisition heart sound pulse signal, realized the synchronous acquisition of heart sound and pulse signal, utilize pulse signal auxiliary heart sound signal and carry out multimode analysis diagnosis, improve the accuracy rate of congenital heart disease diagnosis, expand the diagnosis type range of congenital heart disease and cardiovascular disease, further reduce the misdiagnosis because of the subjective consciousness of doctor.