112 results about "Heart beat" patented technology

The invention relates to the technical field of electrocardiosignal analysis, and discloses a long-sequence electrocardiosignal disease recognition system based on a Transform architecture. The core defects that in traditional electrocardiogram analysis, waveform integrity is damaged by fixed window segmentation, a lead space topological relation is neglected, and long sequence modeling efficiency is low are overcome, a P-QRS-T waveform structure is completely reserved through the heart beat adaptive segmentation technology, and the fixed window truncation risk is eliminated; the lead anatomical topology and the space-time coding are fused, and multi-lead electrophysiological association is modeled; long sequence efficient processing is realized based on hierarchical sparse Transform, and the recognition sensitivity of complex pathologies such as arrhythmia and myocardial ischemia is improved; in combination with gradient directional regulation and control and a streaming processing mechanism, the clinical real-time requirement is met while the diagnosis accuracy is guaranteed, and finally, reliable, efficient and universal intelligent decision support is provided for early warning of heart diseases through lightweight deployment of an adaptive mobile terminal.

The invention discloses an arrhythmia recognition method and system based on electrocardio waveform dynamic feature reconstruction, and the method comprises the steps: obtaining an electrocardiogram of a user, extracting the electrocardio potential of each cardiac blog in the electrocardiogram, and calculating the deformation rate vector of each cardiac blog according to the electrocardio potential; according to the deformation rate vector, calculating a heart rhythm transition value between the heart blogs as a heart rhythm transition fingerprint, calculating heart beat form difference energy between the heart blogs, and generating a form fluctuation index of each heart blog according to the heart beat form difference energy; and acquiring a change acceleration of the form fluctuation index between heart blogs, mapping the change acceleration, the form fluctuation index and the cardiac rhythm transition value into a discrete symbol, and inputting the discrete symbol into a diagnosis synthesizer to output an arrhythmia identification result.

The invention relates to the technical field of biological radar signal processing, in particular to an FMCW radar-based heart beat interval estimation method, which comprises the following steps of: S1, converting a chest vibration echo phase time sequence obtained by irradiating a chest area of a monitored object by an FMCW radar into an acceleration time sequence by using a second-order time derivative; s2, dynamically mapping the center frequency and the wavelet order in a preset frequency analysis interval, constructing a self-adaptive wavelet dictionary, then executing multi-order wavelet time domain convolution operation on the acceleration time sequence by using the dictionary, and aggregating time-frequency energy distribution to generate a time-frequency energy diagram; and S3, performing a deconvolution operation reconstruction strategy based on an energy-guided multi-stage time-frequency feature screening technology and wavelet function conjugation, generating an approximate time domain signal of heart beat vibration, and completing heart beat information inversion. According to the method, the accuracy and robustness of IBI extraction can be effectively improved under the condition of low signal-to-noise ratio, so that stable monitoring of light and moderate HRV (heart rate variability) is supported.

The invention belongs to the field of non-contact vital sign detection, and particularly relates to a millimeter wave radar arrhythmia detection method based on particle swarm optimization variational mode decomposition and deep learning, and the method specifically comprises the steps: S1, obtaining a human chest micro-motion signal through a millimeter wave radar, performing static clutter filtering, phase extraction, unwrapping and detrending processing on the radar echo signal to obtain a chest displacement signal containing heartbeat and breathing information; s2, aiming at the thoracic cavity displacement signal, constructing a variational mode decomposition model, and carrying out adaptive optimization on a mode number and a penalty factor through a particle swarm optimization algorithm to obtain an optimal decomposition parameter and complete signal decomposition; s3, according to the center frequency and the energy distribution characteristics of each modal component, screening the modal components in the heartbeat frequency range and reconstructing the modal components to obtain heartbeat characteristic signals representing heart mechanical activities; s4, carrying out time sequence segmentation on the heartbeat characteristic signals, extracting local heart beat morphological characteristics by utilizing a convolutional neural network, and carrying out modeling on a long-time rhythm dependency relationship of the heartbeat signals in combination with a time sequence modeling network based on an attention mechanism to obtain heart rhythm depth characteristic representation; and S5, inputting the heart rhythm depth features into a heart rhythm discrimination model, analyzing the heart rhythm state of the detected person, and outputting an arrhythmia detection result. According to the method, adaptive selection of variational mode decomposition parameters is realized by introducing a particle swarm optimization mechanism, heartbeat signals and respiration and motion interference components are effectively separated, modeling is carried out on rhythm characteristics in combination with a deep learning model, and non-contact detection of arrhythmia is realized. The method does not need to wear an electrode or contact a human body, has the advantages of strong anti-interference capability, good adaptability and high detection precision, and has a good application prospect in the fields of heart rhythm health monitoring, disease screening and the like.

The invention provides a regional anesthesia puncture path planning method and system under ultrasonic guidance, and relates to the technical field of ultrasonic image.According to the regional anesthesia puncture path planning method and system, dynamic motion information of a tissue structure is obtained by collecting ultrasonic image data of a target region and conducting motion analysis, and electrocardiosignals are synchronously collected to determine heart beat time phase information; determining a vascular movement mode based on the two, learning a time change rule by using a long-short-term memory network, and establishing an association relationship between a vascular spatial position and a heart beat phase; constructing a motion prediction model to predict the future motion trend of the blood vessel, and fusing the respiratory motion information to correct to obtain the blood vessel motion information; and finally, a safe puncture window is calculated according to the information, a regional anesthesia puncture path is planned, vascular movement prediction and safe puncture window calculation based on vascular movement rule learning and breathing correction in regional anesthesia under ultrasonic guidance can be achieved, and then the puncture path is precisely planned.

The invention discloses a coronary plaque biomechanical property calculation method, and belongs to the field of computational biofluid mechanics in biomedical engineering. According to the method, the influence of cardiac pulsation, coronary blood vessel complex geometric distribution characteristics and coronary plaque composition factors is integrally considered, and the coronary plaque biomechanical characteristics are calculated; wherein the number of the fluid computational domains is two, and the two fluid computational domains are respectively a coronary vessel intracavity blood flow area and a plaque tissue fluid flow area surrounded by a fibrous membrane and a blood vessel; the two structural computational domains are respectively an elastic blood vessel wall and an ultrathin flexible plaque fiber membrane; the plaque fiber membrane generates deformation movement under the pressure of blood in blood vessels on two sides and tissue fluid in the plaque; the motion of the coronary plaque fibrous membrane is described by adopting an independently researched and developed immersion film method, and compared with a traditional coronary plaque biomechanical characteristic calculation method, the method has better information integrity, better accuracy and wider applicability.

The invention discloses a magnetocardiogram P-wave detection method based on wavelet analysis and a local noise self-adaptive threshold, which is characterized in that accurate and robust detection of a P wave is realized by searching on a characteristic scale which can highlight the P wave, a self-adaptive threshold confirmation mechanism based on local noise estimation is introduced, and a self-adaptive threshold confirmation mechanism is established for a time domain search window of each cardiac cycle. According to the method, the internal noise level is dynamically evaluated, and an estimated value capable of accurately reflecting the local noise condition of the current heart beat can be obtained by carrying out statistical analysis on wavelet coefficients in a characteristic scale in an area where P waves are most likely to appear.

The invention discloses a smart watch arrhythmia early warning method and system based on deep learning. The method comprises the steps that firstly, PPG signals are collected through a photoelectric volume pulse wave sensor, and denoising and standardization processing are conducted through an adaptive filtering algorithm; then, the heart beat position is recognized through a wavelet transform peak value detection algorithm, and a heart rate variability feature sequence is obtained; converting the one-dimensional heart rate variability feature sequence into a two-dimensional heart rhythm image by using an improved Gramian angular field transformation algorithm; and training an arrhythmia classification model by adopting a ResNet-50 convolutional neural network to realize automatic identification of different types of arrhythmia. And finally, continuous monitoring and timely alarming are realized through a sliding window technology and an early warning mechanism. The key technical problems of low detection precision, poor real-time performance, high equipment cost, poor user experience and the like in the existing arrhythmia detection technology are effectively solved, and an innovative solution is provided for heart rhythm health monitoring of the intelligent wearable equipment.

To perform synchronous reconfiguration to the periodic movement of a subject without using an external device.SOLUTION: A nuclear medicine diagnosis device analyzes a respiratory movement from list mode data of scanning in which the respiratory movement and heart beats occur, divides the list mode data for every respiratory phase to create first images, analyzes the heart beats for every respiratory phase, creates second images from data obtained by dividing the list mode data for every respiratory phase and data obtained by the division for every heart beat phase, acquires at least one of a first motion vector between the respiratory phases and a second motion vector between the heart beat phases, and applies the first motion vector to the second images and adds up the images, for every group of the second images different in the respiratory phase from each other and common in the heart beat phase, to create a first single phase image corresponding to a specific phase, or applies the motion vector to the second images and adds up the images, for every group of the second images different in the heart beat phase from each other and common in the respiratory phase, to create a second single phase image corresponding to the specific phase.SELECTED DRAWING: Figure 9

The application discloses an old person free breathing coronary artery scanning image lesion analysis system and relates to the technical field of scanning image lesion analysis. In order to solve the problem that the accurate condition of a patient cannot be obtained according to a scanning image. The application adopts a diameter method, an area method and a contrast agent filling condition to judge the stenosis degree and the hemodynamic change, analyzes the lesion from the morphological and functional double angles, provides comprehensive information for clinical decision-making, identifies the R wave peak value and divides the cardiac phase, matches the respiratory signal and the projection data in time, can accurately capture the characteristics of the heart in different motion states and the respiratory stage, effectively avoids the interference of the artifacts caused by the heart beat and the respiratory motion, makes the reconstructed image clearer and more accurate, sets the CT and the injector parameters in sequence from the scanning type confirmation, each link is closely related and the target is clear, improves the work efficiency, and is convenient for quality control and process management.

The present application relates to the field of respiratory heart rate monitoring, and discloses a non-contact heart rate and respiration recorder, which comprises a host computer, a wireless charging base, a charging cable and a terminal device, wherein the host computer is internally provided with a non-contact sensor module, a processor, a battery and a wireless communication module, and the shell adopts a waterproof sealing structure. In use, the host computer is placed under a pillow, and a heart beat and respiration channel signal is collected through the non-contact sensor, and after filtering, normalization and artifact removal, the signal forms a heart beat observation and a respiration observation under the action of parameters such as a sampling rate, a time window length, a vertical offset and a coupling stiffness, and is subjected to joint optimization under the constraints of spectral matching and cross-modal coherence, and finally outputs a heart rate and a respiration rate. The device does not need to wear an electrode, is stable in detection, and is suitable for long-term home health monitoring and clinical assistance.

An apparatus includes a photoplethysmography (PPG) sensor configured to measure a PPG signal associated with a user, an accelerometer configured to measure an acceleration signal associated with the user, and a processor operatively coupled to the PPG sensor and the accelerometer. The processor is configured to determine whether the user is engaging in movement based on the acceleration signal, in response to determining that the user is engaging in movement, determine a type of movement of the user based on the acceleration signal, generate a probability distribution associated with a pulse rate of the user based on the type of movement, and determine the pulse rate of the user based on the PPG signal, the acceleration signal, and the probability distribution.

The application provides a magnetocardiogram signal superposition average optimization method based on heart beat classification, and is suitable for the field of magnetocardiogram signal processing and analysis. The method comprises the following steps: obtaining a denoised magnetocardiogram signal; performing R wave detection on the denoised magnetocardiogram signal and performing heart beat segmentation; setting the segmented first heart beat as a heart beat classification, and calculating the correlation of subsequent heart beats with the first heart beat; the heart beat with a correlation greater than a threshold value is considered to belong to the existing classification, and the heart beat with a correlation less than the threshold value is taken as a new heart beat classification; repeating the above process until the correlation calculation of all heart beats is completed; superimposing and averaging all heart beats in the same classification; calculating the correlation between the superimposed and averaged results again, merging the classifications with high correlation, recalculating the superimposed average, and obtaining the result of the heart beat classification superimposed average. The present application improves the existing magnetocardiogram superposition average algorithm and provides a more accurate magnetocardiogram superposition average image.

The present application discloses a blood pump speed pulsation control method, system, and related products. The method: based on the electrical signal change information of the blood pump motor within a historical period, detects the start time of the N0 diastole and the start time of the N0 systole of the current patient's heart beat within the historical period; based on these start times, determines the start time of the N1 diastole and the start time of the N1 systole of the heart after the historical period. The method uses the patient's individual historical electrical signal change information as a basis to determine the future start time of the diastole and the start time of the systole of the current patient's heart, ensuring that the speed adjustment time of the blood pump motor is personalized to conform to the physiological contraction law of the individual heart, and realizing the specific output of the blood pump such as the blood pumping time and the blood pumping volume per time to flexibly follow the blood flow pulsation output of the heart beat, that is, to assist the blood pump in generating a pulsating flow synchronized with the natural heart beat, thereby effectively and reliably maintaining the patient's life safety.

Embodiments of the present application relate to a kind of electrocardiosignal processing method and device, the method includes: receiving first electrocardiosignal;Filtering processing generates second electrocardiosignal;Baseline drift elimination processing is respectively carried out to first, second electrocardiosignal, and third, fourth electrocardiosignal is generated;R point identification processing is carried out to fourth electrocardiosignal, and first R point sequence is generated;Electrocardiosignal segment intercepting processing is carried out to third, fourth electrocardiosignal, and first, second electrocardiosignal segment sequence is generated;Heart beat classification processing is carried out to first electrocardiosignal segment sequence, and first segment type sequence is generated;Interference classification processing is carried out to second electrocardiosignal segment sequence, and second segment type sequence is generated;Segment type fusion processing is carried out to first, second segment type sequence, and third segment type sequence is generated;First R point sequence and third segment type sequence are as electrocardiosignal processing result output.The processing efficiency of electrocardiosignal processing can be improved in the present application and the stability of processing quality is guaranteed.

The present application relates to magnetic resonance examination device technical field, specifically to a kind of cardiac magnetic resonance examination device, including fixed plate and electrocardiogram control patch, fixed plate is equipped with chest coil;Fixed plate is detachably connected with detection plate, detection plate is equipped with breathing training component for exerting chest pressure, breathing training component is electrically connected with control panel;Control panel records and draws fluctuation curve based on the pressure data detected by breathing training component, then obtains the breathing interval of patient based on fluctuation curve, sends breath-holding reminding instruction to voice module according to breathing interval;Detection plate side away from fixed plate is equipped with several electrocardiogram monitoring electrode pieces for detecting the quality of heart beat signal strength, detection plate is equipped with driving mechanism for driving electrocardiogram monitoring electrode piece to move in range;The present application is used to assist patient breathing breath control, realize the accurate matching of patient breathing breath opportunity and imaging sequence, reduce the generation of breathing artifact, guarantee the progress of cardiac magnetic resonance.

The invention provides a dynamic electrocardiogram heart beat classification method and device, equipment and a storage medium. Relates to the technical field of electrocardiogram cardiac beat classification. The method comprises the following steps: preprocessing a data set to obtain multi-view data of ECG heart beats, and performing feature extraction to obtain multi-view features; the multi-view feature embedding of a plurality of heart beats is grouped according to the neighborhood size increasing from 0 to 1, the features of each view in each group are unified into the same length on a time axis and are connected on a channel axis to form a multi-range group, and a multi-view cross attention mechanism is used for each range group to obtain a multi-view fusion feature; discriminative information is extracted from multiple groups of features in different ranges, and attention enhancement features are obtained; and inputting the attention enhancement feature and the R-R interval into a classification head together to obtain a classification prediction result. The inherent diversity of the ECG signals is effectively handled, and the generalization performance of the classification model is improved.

The present invention discloses a cardiopulmonary coupling quantification method and system based on multimodal coupling analysis, which relates to the technical field of electrocardiogram signal processing. The method comprises the following steps: collecting electrocardiogram (ECG) signals and respiratory signals of a subject; extracting a heart beat interval (R-R) interval time series from the collected ECG signals; decomposing the R-R interval time series and the respiratory signal using variational mode decomposition to obtain intrinsic mode functions (IMFs) of the two time series; selecting the IMF with the largest power as the dominant IMF among all IMFs of the respiratory signal; selecting the IMF with the frequency matching the dominant IMF of the respiratory signal among the IMFs of the R-R signal; calculating the synchronization index between the dominant IMF of the respiratory signal and the frequency matching IMF of the R-R sequence by using the instantaneous phase difference between the two; and finally, quantifying the instantaneous magnitude of RSA by calculating the power of the frequency matching IMF of the R-R interval sequence during its strong synchronization period.

The application discloses a method and device for arrhythmia analysis based on heart beat classification, equipment and medium, wherein the method comprises: generating a morphology amplitude coding vector of a target heart beat segment as a target morphology amplitude coding vector, the target heart beat segment being any one of the heart beat segment time series set; performing inner product calculation on the target morphology amplitude coding vector and each heart beat template vector in a preset heart beat template vector set to obtain an inner product value set; determining a target heart beat type corresponding to the target heart beat segment according to the inner product value set; and performing arrhythmia analysis on each target heart beat type corresponding to the heart beat segment time series set to obtain an arrhythmia analysis result. The application avoids the technical problems that the traditional method may have a large amount of calculation, ignores the amplitude difference of the waveform and easily ignores the morphology difference of the waveform when the amplitude is low, has simple steps and small calculation amount, and is thus suitable for real-time monitoring scenes.

1. Name of the designed product: running shoes (2405P031 heart beat). 2. Use of the designed product: the designed product is used for shoes. 3. Design points of the designed product: combination of shape and pattern. 4. Picture or photo best indicating the design points: perspective view.

The present application relates to the technical field of pattern recognition, in particular to a blood glucose detection region selection method based on blood perfusion imaging, comprising collecting continuous laser speckle original images of a to-be-detected skin region and a peripheral pulse wave signal of a subject, and constructing a bottom layer data matrix. The image sequence is converted into a perfusion contrast evolution sequence by calculating the ratio of the standard discrete degree and the average brightness of the pixel intensity in the three-dimensional data block. Frequency locking operation is performed using the main frequency of the pulse wave to separate out the perfusion fluctuation component synchronized with the heart beat rhythm, and the phase lag distribution map of each pixel point is determined through cross-correlation time delay analysis. The tissue damping coefficient of each pixel point is obtained by combining the tissue viscoelasticity kinetic damping model inversion, and the pixel set in the target response interval is screened and clustered according to the mapping relationship between the blood glucose concentration and the damping coefficient to determine the blood glucose detection target region. The present application realizes the locking of the detection region through tissue damping characteristic inversion and clustering screening.

The invention discloses a cardiac mechanical signal processing method and device based on wavelet reconstruction. The method comprises the following steps: performing trend removal and frequency band extraction on an original SCG signal, and reserving main mechanical energy components corresponding to a heart sound event; then wavelet decomposition and main scale reconstruction are carried out, and time domain features of key components such as S1 and S2 structures similar to PCG signals are strengthened, so that heart sound-like signals which are similar to PCG in form and clear in rhythm are generated. Compared with an original SCG signal, the heart sound-like signal obtained through reconstruction is remarkably improved in the aspects of rhythm definition, form consistency and peak stability. And further performing rhythm analysis on the reconstructed signal, introducing physiological constraints, and screening to obtain a cardiac trigger point sequence, thereby realizing high-precision cardiac recognition. The device can be integrated with medical image equipment and wearable equipment, and the functions of heart sound gating, synchronous triggering or auscultation auxiliary analysis and the like are achieved.

This invention provides a deep learning (DL) model for fast deformable image registration using 2D sagittal cine MRI acquired during radiation therapy. A DL model for fast deformable image registration is trained using cine MRI scans acquired during MR-Linac treatments of thoracic and abdominal tumors. The model uses a pair of cine MRI images as inputs and outputs a dense motion vector field (MVF) which aligns the images. The trained model is applied to predict frame by frame motion from cine MRIs in which both cardiac and respiratory motion are visible. The number of respirations and heart beats is automatically extracted by performing peak detection on high-frequency and low-frequency components of the MVF displacements corresponding to the chest wall and cardiac regions.

The invention discloses a household heart beat detection system based on multi-feature fusion and adaptive optimization, and the system achieves the stable collection of non-contact BCG signals through a dual-mode piezoelectric sensor array and a signal collection subsystem of a wireless transmission module. In order to solve the problem of weak anti-interference capability caused by dependence on a single feature in a traditional method, a multi-dimensional feature extraction scheme fusing a first-order derivative extreme point, a second-order derivative inflection point and a wavelet high-frequency feature is provided; the dynamic threshold detection subsystem is used for completing preliminary positioning of heart beats, the density clustering optimization subsystem is combined for filtering wrong heart beats of noise interference, a particle swarm optimization algorithm is used for conducting self-adaptive optimization on a heart beat template, and finally high-precision heart beat detection is achieved through intelligent template matching. The non-contact design adapts to various special crowds, the robustness and accuracy of heart beat detection are remarkably improved through the multi-feature fusion and self-adaptive optimization algorithm, and the method is suitable for time-history heart beat monitoring scenes of parents.

The application relates to an inter-board heartbeat monitoring method and system, which comprises the following steps: determining the access state of a sub-board on a main board; based on the determined access state, performing heartbeat count verification on each sub-board once per heartbeat monitoring period for all accessed sub-boards; wherein the heartbeat count verification comprises: sending main board information for requesting sub-board feedback of sub-board information to the accessed sub-board, wherein the sub-board information comprises sub-board heartbeat count; in the case of receiving the sub-board information, judging whether the sub-board heartbeat count falls between a minimum critical heartbeat count and a maximum critical heartbeat count; in the case of not falling therebetween, increasing the verification error count and judging whether the verification error count is greater than a fault tolerance threshold; and in the case of the verification error count being greater than the fault tolerance threshold, determining that the sub-board is abnormally running. The heartbeat monitoring of the main board on the sub-board is realized through inter-board communication, which is convenient to implement and low in cost, and has universality.

The invention discloses a row-column addressing area array flexible ultrasonic transducer integrated with electrocardiogram monitoring and a preparation method thereof.An ultrasonic function unit takes a flexible circuit board as a core carrier, integrates independent piezoelectric array elements, a top flexible electrode layer and a flexible acoustic matching layer which are distributed in rows and columns, and is controlled through a row-column addressing electrode array; and the number of the leads is reduced from N2 to 2N. The electrocardio monitoring unit comprises electrocardio sensing electrodes which are integrated together. The package structure covers the non-functional surface to provide protection. The ultrasonic array and the electrocardio sensing electrode are conformally integrated on the same flexible substrate, so that synchronous and homologous monitoring of mechanical movement and electrophysiological activity of the heart is realized. Due to the flexible design, the transducer can be adaptive to the curved surface of the chest of a human body and tolerate deformation caused by cardiac pulsation and respiration, and the accuracy, stability and comfort in wearable long-term dynamic heart monitoring are remarkably improved.

The invention provides a sleep detection model training method and a sleep detection method.The training method comprises the steps that according to the segment signal-to-noise ratios of a plurality of initial respiration signal segments and a plurality of corresponding heart beat signal segments in the sleep period and a preset signal-to-noise ratio threshold value, the heart beat signal segments are selected from the initial respiration signal segments, acquiring a plurality of respiratory signal training fragments with the fragment type of abnormal respiration and the fragment type of normal respiration, and then taking the fragment types, the first signal fluctuation characteristics and the second signal fluctuation characteristics corresponding to the plurality of respiratory signal training fragments as sleep respiratory abnormality fragment training samples; and training a plurality of machine learning models according to the sleep breathing anomaly fragment training samples of the plurality of object individuals so as to obtain a plurality of sleep detection models for detecting sleep breathing anomaly fragments. The proportion of the fragment types corresponding to the training samples is balanced, and the accuracy of the sleep detection model obtained through training can be improved.

The application discloses a kind of multi-channel sensing fusion systems for exposure stress judgment, it is related to sensing fusion technical field, for solving the problem of insufficient accuracy of stress exposure state judgment, by the monitoring equipment corresponding to the working individual, the respiratory rhythm, the heart beat interval, the skin electricity response and the action trajectory such as multi-dimensional physiological and behavioral parameters in the working process are continuously collected, the multi-channel stress state observation basis is constructed, the feature extraction and abnormal discrimination of each channel data are carried out, the state mode is classified modeling using pattern recognition method, combined with cross-channel consistency analysis and causal order constraint, the abnormal response is comprehensively evaluated, when the evaluation result meets the preset stress exposure determination condition, combined with action trajectory characteristics, the stress exposure grade of working individual is graded determination, and according to the determination result, continuous monitoring or event record and information upload operation is selected, realize the automation, real-time judgment of stress exposure state.

The invention discloses an intelligent assessment method and system for coronary stenosis based on chest radiography, and relates to the technical field of health risk assessment, and the method comprises the steps: obtaining chest radiography image data of a target patient; based on the time sequence fluctuation of the calcification focus area in the chest radiograph image data, calculating to obtain a calcification activity index, determining a cardiac pulsation key point in the chest radiograph image data, and based on the displacement change of the cardiac pulsation key point between each image frame, calculating to obtain a collateral circulation compensation index of the calcification focus area; based on the collateral circulation compensation index and the calcification activity index, calculating a dynamic risk factor corresponding to the coronary artery stenosis; and inputting the dynamic risk factor into a preset neural network model for iterative training, and performing prediction processing on the chest radiograph image data based on the trained preset neural network model to obtain a coronary artery stenosis risk assessment result. The technical effect of reducing the clinical misjudgment risk of coronary artery stenosis is achieved.

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.