299 results about "Cardiac sounds" patented technology

The present invention relates to a heart disease automatic classification system based on heart sound analysis. It includes the following several portions: heart sound sensor, it is used for converting heart sound vibration signal of tested person into electric signal and outputting said electric signal; computer with multimedia function, it is connected with heart sound sensor by means of data acquisition card and can be used for recording the heart sound signal of tested person which is outputted by heart sound sensor and storing said signal in storage unit; and heart sound sectionalization program, heart sound characteristics extraction program and classification device which are mounted in the computer. Said invention also provides its working principle and its concrete operation method.

The invention discloses a fiber-optic sensing intelligent garment and heart sound and blood pressure parameter processing methods thereof. The fiber-optic sensing intelligent garment comprises a garment body, a fiber Bragg grating pulse sensor, a fiber Bragg grating heart sound/breath sensor, an optical signal processing unit and an information processing terminal; the optical signal processing unit is used for wavelength demodulation and signal transmission; the information processing terminal is used for parameter information displaying, storage and remote communication. The heart sound parameter processing method of the fiber-optic sensing intelligent garment is a method of judging mathematical morphological peaks of heart sounds and mathematical morphological start-stop points through linear structure elements and cosine structure elements. The blood pressure parameter processing method of the fiber-optic sensing intelligent garment includes blood pressure model establishing and blood pressure estimating. The fiber-optic sensing intelligent garment has high electromagnetic interference resistance and high detection sensitivity, is applicable to places with strong magnetic field, high electromagnetic noise, strong radiation or the like and is applicable to body sign monitoring in magnetic resonance imaging, safety monitoring for physical conditions of mine workers, clothing of astronauts, safety clothing of fire fighters and the like.

A computer-based detection method employable with a sleeping subject for aiding in the differential-character diagnosis and treatments of apneic events includes gathering heart-sound data, including S1 data and S2 data. A combined time-frequency-intensity (TFI) analysis, of the gathered data is performed, in a continuous manner, over a selected time period. Based on the performing and the performed TFI analysis, an output is produced which is indicative of the presence and character of any detected apneic event.

A handheld auscultatory scanner continuously obtains a heart sound signal from a patient, using a noninvasive passive acoustic sensor, allowing free-form protocol, analysis and display of the heart sound signal on a handheld processing unit in a graphical manner such that a single heart cycle is displayed in a synchronized manner, along with summary results of the processing of the acoustic signal. The results are presented in terms of standard auscultatory findings. The combination of summary findings, heart sound display and audible signal provides a method for assisting in patient screening for heart conditions and for teaching auscultation techniques.

An intelligent clothing based on MEMS technique for acquiring human physiological parameters including cardioelectric signals and cardiac sound features the integration of a flexible film containing sensor array with fabric. Its preparing process includes such steps as using MEMS technique to prepare sound/electricity transducers and electric interconnection on a wafer, etching to generate Si-island pattern on the back of wafer, coating polymer on both surfaces of wafer, photoetching to form sensor windows and sewing holes on a film, and integrating it with fabric by sewing.

The present invention is computerized multifunctional medical detecting and monitoring method and apparatus. Various signals of human body are first acquired by means of different kinds of sensors, such as electrocardiac sensor, temperature sensor, cardiac sound sensor, etc; and then amplified, filtered, shaped, A/D converted and transmitted to the computer via the data communication interface. The computer with human body detecting and monitoring application program performs analysis and calculation on the signals, shows the results in the display, stores selectively in the fixed disk, and sends out alarm signal in case of finding abnormal human body parameters via the Internet and computer network. The present invention is suitable for household medical monitoring and remote diagnosis.

The invention relates to a method and a system for identifying heart-lung sound signals. The method includes the steps of acquiring heart/lung sounds initial detection signals, acquiring correspondingenvironment sound signals, and subjecting the heart/lung sounds initial detection signals to differential noise reduction processing, so as to prevent the influence of the peripheral environment on the cardio-pulmonary sound signals, prevent influence of signals irrelevant to the cardio-pulmonary sound signals on the identification precision, and effectively improve the collection and identification precision of the cardio-pulmonary sound signals. The heart sound simulation signals is processed through combination of EMD (Empirial Mode Decomposition) and a high-order shannon entropy algorithm, and a wavelet decomposition is used for processing the lung sound digital signals. Accurate recognition of the characteristics of the heart sound signals and the lung sound signals is achieved, andthe identification steps of the cardio-pulmonary sound signals are effectively simplified. The real-time performance is higher, and the cost is low.

The invention discloses a wearable cardiac sound monitoring device. The wearable cardiac sound monitoring device comprises a wearable cardiac sound acquiring and sensing module, a mobile phone cardiac sound signal receiving and processing information module and a central server, wherein the wearable cardiac sound acquiring and sensing module consists of a microphone, a signal amplifying and transmitting circuit, a microprocessor, a wireless transmission module, an earphone shell and a wearable fixing device; a cardiac sound signal of a user is collected through the wearable cardiac sound acquiring and sensing module, and passes through the signal amplifying and transmitting circuit, namely, a circuit amplifying circuit and an A/D (Analog to Digital) sampling circuit to obtain a cardiac sound electronic signal; the cardiac sound electronic signal is transmitted to mobile phone equipment through wireless transmission equipment; the corresponding cardiac sound signal receiving and processing information module is arranged on a mobile phone; the received cardiac sound electronic signal is subjected to digital filtration and computation to obtain corresponding cardiac sound information; the acquired cardiac sound information is transmitted to the central server through the mobile phone. An algorithm is implemented through an algorithm, an entropy relation between a fuzzy signal and a signal is used for predicting the future health state of heart through computation, and the user is promoted of matters needing attention in advance.

The invention relates to a method for detecting the pulmonary artery blood pressure by using a heart sound analysis method of a multilayer feedforward network. The method comprises the steps of: extracting a heart sound signal; preprocessing the heart sound signal by fast Fourier transform and normalized average Shannon energy distribution to obtain heart sound signal features; filtering the heart sound signal features by using a principal component analysis method; and performing training learning on the filtered hear sound signal features by using a perceptron neural network or a multilayer perceptron feedforward neural network to obtain an optimal neural network between the heart sound signal features and a pulmonary artery blood pressure value. The heart sound signal features are signal features of a first heart sound and a second heart sound; the heart sound signal features comprise crest frequency, average frequency, crest amplitude, average amplitude, duration and time interface of heart sounds. By adopting the method for detecting the pulmonary artery blood pressure by using the heart sound analysis method of the multilayer feedforward network, provided by the invention, the pulmonary artery blood pressure can be easily and conveniently detected at low cost in a non-intrusive and no risk manner.

The invention discloses a health reserve evaluation method. The health reserve evaluation method comprises the following steps: a system converts received human pulse beat signals, heart sound signalsand ECG signals into point process signal data; the system performs composite variable analysis of a health reserve value on the point process signal data, and forms a monotonic function reflecting the healthy reserve state; and the system performs qualitative and quantitative determination of human health according to statistical distribution parameters of the health reserve values of the population. A health reserve evaluation system/device includes a data acquisition unit, a data conversion unit, a data analysis unit, a health status evaluation unit, and a health reserve evaluation application. The evaluation method of the health state and change thereof is simple and reliable, is easy to implement, can perform repeat measurement and evaluation, can be widely used in many fields such as health evaluation, health guidance, exercise rehabilitation guidance and the like of the general population.

The invention provides a Doppler fetal cardiac sound instantaneous heart rate detecting method based on blind separation. The detection method comprises the following steps that the Doppler fetal cardiac sound is subjected to denoising preprocessing through a low-pass filter; the processed ultrasonic Doppler fetal cardiac sound is subjected to time-frequency analysis, and the short-time Fourier transform is utilized for solving the time-frequency diagram of the ultrasonic Doppler fetal cardiac sound signals; several characteristic frequency bands are selected from the time-frequency diagram according to the priori knowledge of the periodic characteristic of the time-frequency diagram of the fetal cardiac sound signals, then, different selected frequency band signals are subjected to Fast ICA analysis, independent components are worked out, then, the independent component IC which is most matched with the fetal cardiac sound signals is determined, next, a self-correlation function of the most matched independent component IC is calculated, the peak value is detected, and finally, the fetal cardiac sound heart rate is calculated. The Doppler fetal cardiac sound instantaneous heart rate detecting method is used for calculating the instantaneous heart rate on the clinically collected ultrasonic Doppler fetal cardiac sound signals and has the advantages that the method is simple, the calculation speed is high, the flexibility is good, and the accuracy is high.

The invention discloses a blue tooth wireless heart function parameter monitoring system comprising a embed blue tooth wireless patient monitor, a blue tooth switch-in terminal, and a platform of medical monitoring system, wherein, the embedded blue tooth wireless monitor is connected to the platform of medical monitoring system via the blue tooth switch-in terminal. The invention also discloses the application of said blue wire heart function parameter monitoring system for the patient side monitoring, the short-range central monitoring and the remote medical monitoring. In addition, the invention can reflects the physical status of human body in reality with lower cost and higher reliability; and the invention can collect variable physiological parameters as electro-cardio-signal, heart rate, cardiophonogram, the blood oxygen saturation and the body temperature to be wireless transmitted by the blue tooth technique. So it can help the medical staff monitor the state of patient and prevent the exacerbation of the condition.

The invention relates to a portable wireless electrocardiogram, cardiac sound and breath sound acquisition, display and storage device which comprises a cardiac sound/breath sound sensor, a first low-noise amplifier, a second low-noise amplifier, a signal conditioning circuit, an electrocardiogram sensor, a low and high pass filter, an A/D (Analog to Digital) converter, a CPU (Central Processing Unit) processor, a keyboard, a wireless transmitting/receiving module and an LED indicator light, wherein the cardiac sound/breath sound sensor is connected with the signal conditioning circuit through the first low-noise amplifier and then connected with the CUP processor through the A/D converter; the electrocardiogram sensor is connected with the low and high pass filter through the second low-noise amplifier and then connected with the CPU processor through the A/D converter; and the CPU processor is used for carrying out wireless transmission of signals through the wireless transmitting/receiving module. The device has the characteristics of synchronously acquiring physiological parameter data such as electrocardiograms, cardiac sound, breath sound, and the like of a human body and transmitting the data to a display and storage machine in real time through the wireless transmitting/receiving module, displaying and storing or replaying the electrocardiograms and frequency spectrograms of the cardiac sound and the breath sound and playing the cardiac sound and the breath sound, and providing more visual diagnostic data for doctors; and the device can provide quick diagnosis information of common diseases such as arrhythmia, structural heart diseases, lung diseases, and the like.

The invention provides an abnormal heart sound recognition method based on sub-band energy envelope autocorrelation characteristics and relates to an abnormal heart sound recognition method. The abnormal heart sound recognition method is used for solving the problems in heart sound recognition that heart sound segmentation is depended, longer signals cannot be processed, and adaption to the characteristic extraction and classified recognition in a real noise environment cannot be realized. The method comprises the steps: carrying out energy standardization on input heart sound signals, then, carrying out down-sampling, and carrying out band-pass filtering; respectively computing an autocorrelation sequence of approximate sub-band energy envelope signals and an autocorrelation sequence of detailed sub-band energy envelope signals, and respectively intercepting first M values, which serve as approximate sub-band energy envelope autocorrelation characteristics and approximate sub-band energy envelope autocorrelation characteristics of the input heart sound signals, from the two sequences; respectively constructing two RM-space-to-Re-space scattering mappings, which act on the energy envelope autocorrelation characteristics, according to the energy envelope autocorrelation characteristics; carrying out dimensionality reduction, and then, merging to obtain the energy envelope autocorrelation characteristics of the heart sound signals; carrying out characteristic extraction on test data, and classifying the data by imputing the test data in a classification model. According to the method, a heart sound segmentation process is avoided, and the robustness in a noise environment is improved.

The present invention relates to A system for monitoring the cardiovascular system using a heart sound, which comprises a heart sound receiving means(100) for receiving a heart sound(HS); DSP (Digital Signal Processor) module(200) for converting the heart sound(HS) received from said heart-sound receiving means(100) to a digital signal; and an arithmetic section(300) for calculating phonocardiogram(PCG) from the digital signal converted in the DSP module (200) and calculating information related to a preload or information related to a cardiac contractile force or information related to a respiratory change.

The invention discloses a heart sound, lung sound and fetal heart sound acquisition and health management system, which comprises an acquisition terminal, a transmission system, a platform processing system and a storage and display system, wherein the acquisition terminal is used for acquiring the heart sound or lung sound or fetal heart sound condition of a human body, and converting the heart sound or lung sound or fetal heart sound condition into an electric signal; the acquisition terminal is in communication connection with the transmission system through a wired network or a wireless network, and the transmission system is a mobile phone; the transmission system is in communication connection with the platform processing system through the wireless network, and the platform processing system is a health management service cloud platform; the storage and display system is a mobile phone, and is in communication connection with the platform processing system through the wireless network. According to the system, the heart sound, the lung sound and the fetal heart sound of the human body are acquired by the acquisition terminal or a microphone, are transmitted to the mobile phone after being subjected to processing such as data conversion and amplification filtration, and are transmitted to the health management service cloud platform through the mobile phone, and a health management report of the human body is obtained for the timely query of the human body through the mobile phone.

The invention discloses a non-negative matrix factorization-based heart and lung sound separation method. The method comprises the steps of firstly filtering a mixed signal of heart and lung sounds in a time domain to obtain a priori heart sound signal and a priori lung sound signal; secondly performing short-time Fourier transform and sparse non-negative matrix factorization on the priori heart sound signal and the priori lung sound signal; and finally obtaining a basis matrix of the mixed signal. The sparse non-negative matrix factorization process is equivalent to a learning process of the basis matrix, and has a clustering effect; the basis matrix can be mined effectively from the priori heart sound signal and the priori lung sound signal; and a heart sound signal and a lung sound signal are accurately separated from the mixed signal of the heart and lung sounds in the time domain according to the basis matrix in the subsequent steps. The invention furthermore discloses a non-negative matrix factorization-based heart and lung sound separation apparatus, which has the abovementioned beneficial effects.

The invention provides a heart sound classification method and system based on CNN combined with improved frequency wavelet slice transformation, and the method comprises the steps: carrying out the preprocessing of an obtained heart sound signal, finding the position of each cardiac cycle through a hidden half Markov model, and carrying out the interception of each cardiac cycle signal; converting each intercepted one-dimensional cardiac cycle signal into a two-dimensional time-frequency image by using improved frequency slice wavelet transform; calculating sample entropies of the acquired heart sound signals respectively; comparing the two-dimensional time-frequency image with a preset sample entropy threshold, when the sample entropy of the heart sound signal is greater than the presetsample entropy threshold, performing network training and classification according to the two-dimensional time-frequency image by using a first convolutional neural network, otherwise, performing network training and classification according to the two-dimensional time-frequency image by using a second convolutional neural network; firstly, signals with different interference degrees are distinguished by using sample entropy, and then classification is performed by using different convolutional neural network models for different signals, so that the accuracy of heart sound signal classification is greatly improved.

Devices, systems, and methods for non-invasively detecting and monitoring medical conditions using multiple modalities of sensing include at least two electrodes configured to be positioned on a subject, an acoustic sensor configured to be positioned on a subject, a thoracic impedance measurement module connected to the electrodes, for measuring a first impedance between the electrodes, and a heart acoustic measurement module connected to the acoustic sensor, for detecting and measuring a heart sound from the acoustic sensor.

The invention discloses a multi-channel congenital heart disease rapid screening device and a screening method thereof. The multi-channel congenital heart disease rapid screening device comprises a handheld type gun body, a sleeve, a heart sound sensor array, an environment noise collector, an oxyhemoglobin saturation collecting sensor and a displaying screen. The sleeve is detachably connected toa gun head of the handheld type gun body, the heart sound sensor array is integrated on the front end face of the sleeve, the heart sound sensor array is arranged according to the position where a signal needs to be collected, the environment noise collector is arranged on the side wall of the sleeve, the displaying screen is arranged above a handheld part of the handheld type gun body, the oxyhemoglobin saturation collecting sensor is connected with the handheld type gun body, and an internally-arranged circuit board and a lithium battery are arranged in the handheld type gun body. Comparedwith the prior art, the multi-channel congenital disease rapid screening device and the screening method thereof have the beneficial effects that the detection process of congenital heart disease is simplified to a large extent, rapid collecting and intelligent analysis of heart disease data are achieved, and the rapid screening device is a novel device which can be applied to newborn congenital heart disease screening.

The invention provides an abnormal heart sound recognition method and device based on a multi-scale attention neural network. The method comprises the steps of: carrying out preprocessing on collectedoriginal heart sound signals, and enabling the preprocessed heart sound signals to serve as training samples; carrying out heart sound quality labeling on the training samples; training an abnormal heart sound recognition model according to the training samples and the labeling content of the training samples; and inputting to-be-detected heart sound data into the trained abnormal heart sound recognition model to obtain a heart sound quality prediction result, and recognizing abnormal heart sounds according to the heart sound quality prediction result. Heart sound signals are objectively andquantitatively analyzed, so that the heart sound auscultation result is more accurate, and a doctor can be more effectively assisted in heart sound recognition and diagnosis.

This invention is concerned with a method and apparatus for measuring and controlling the quality of physiological acoustic signals, which include tracheal breathing sounds, lung sounds, heart sounds, blood flow sounds, joint sounds, and gastrointestinal sounds. The interface between the skin and the device is carefully controlled to achieve a desirable acoustic coupling. A pneumatic feedback control system automatically adjusts of the pressure applied to the skin; another pneumatic control system adjusts the pressure inside an airtight chamber for housing the acoustic sensor. A processor assesses the signal qualities, such as amplitude and frequency spectrum, and provides feedback controls to the interface if needed. The resulting method and apparatus eliminates operator's variability and acquires physiological acoustic signals with consistent and desirable qualities for various medical diagnostic purposes.