116 results about "Electrocardiogram analysis" patented technology

The invention discloses a dynamic electrocardiogram and motion recording and analyzing system, which is used for automatic detection on user activities and electrocardiogram analysis under activity scenes. The system comprises an electrocardiogram and motion sensor unit, a data acquisition, storage and transmission unit and an analysis and software unit, wherein the electrode of a motion sensor and the electrode of an electrocardiogram sensor can be packaged together or used independently; the system records and automatically detects daily physical motions of a user, such as lying, sitting, walking, running, tumbling, sitting up, standing up, sitting down, lying down and the like, and gives corresponding activity intensity; the electrocardiogram is automatically analyzed; and a corresponding mark is given when an abnormal electrocardiogram or abnormal activity is detected, all corresponding original signals and analysis results are stored, and nursing staff are prompted. The system gives heart rate variability of the user under different activity intensities, and changes of the heart rate variability along with activity types, activity intensities and time. The systems gives a method of analyzing changes of heart rate and electrocardiogram forms along with activity intensity and duration, and can be used for aerobic exercise optimization and exercise safety in motion and exercising.

The invention discloses an automatic electrocardiogram recognition system. The system comprises an electrocardiogram acquisition device, a wireless / wired network transmission module, an electrocardiogram collection and time domain feature recognizer, an electrocardiogram dominant wave interphase recognizer, an electrocardiogram QRS wave group similarity recognizer and an electrocardiogram queuing recognizer, the electrocardiogram acquisition device inputs acquired data to the electrocardiogram collection and time domain feature recognizer via the transmission module, the electrocardiogram collection and time domain feature recognizer recognizes to obtain positions of peak points of P waves, QRS waves and T waves on a 12-lead, the electrocardiogram dominant wave interphase recognizer recognizes heart rate to obtain normal and abnormal results of the heart rate, the electrocardiogram QRS wave group similarity recognizer recognizes whether an electrocardiogram probably has premature beat or not, and the electrocardiogram queuing recognizer sequences and outputs. The system performs real-time computer-aided analysis of clinically acquired 12-lead electrocardiograms to automatically recognize arrhythmia and premature beat electrocardiograms, and accordingly efficiency of electrocardiogram analysis is improved while a priority processing means is provided for emergency electrocardiograms.

The system and method provide for electrocardiogram analysis and optimization of patient-customized cardiopulmonary resuscitation and therapy delivery. An external medical device includes a housing and a processor within the housing. The processor can be configured to receive an input signal for a patient receiving chest compressions and to select at least one filter mechanism and to apply the filter mechanism to the signal to at least substantially remove chest compression artifacts from the signal. A real time dynamic analysis of a cardiac rhythm is applied to adjust and integrate CPR prompting of a medical device. Real-time cardiac rhythm quality is facilitated using a rhythm assessment meter.

The embodiment of the invention relates to a static electrocardiogram analysis method and device based on artificial intelligence self-learning. The static electrocardiogram analysis method comprisesthe steps of data preprocessing, heart beat detection, heart beat classification based on a deep learning method, heart beat checking, heart beat waveform characteristic detection, electrocardiogram event measurement and analysis and final automatic report data outputting and achieve a complete and quick static electrocardiogram process. By adopting the static electrocardiogram analysis method, modification information of automatic analysis results can be also recorded, modified data is collected and fed back to a deep learning model for continuous training, and the accuracy rate of an automatic analysis method is constantly improved.

The invention relates to the technical field of electrocardiogram analysis, in particular to an electrocardiosignal classification method and device. The electrocardiosignal classification method includes the steps: a, segmenting extracted electrocardiosignals to obtain standard input data at a training stage; b, building a deep neural network through the standard input data at the training stage and training the deep neural network to obtain an electrocardiosignal classifier; c, converting the acquired original electrocardiosignals into data in a format as same as that of the standard input data at the training stage to obtain standard input data at an application stage, and inputting the standard input data at the application stage to the electrocardiosignal classifier for electrocardiosignal classification. A large number of signal processing steps based on field knowledge are omitted, and adaptive learning can be effectively achieved according to electrocardiogram data acquired by different equipment and different users in different environments.

In an implantable medical device for monitoring glucose concentration in the blood, a blood-glucose concentration analysis is performed using correlations of blood-glucose concentration with measures of metabolic oxygen consumption including oxymetric, and / or temperature. Analysis of electrocardiographic data is used in a parallel method to detect and / or confirm the onset and / or existence and / or extent of hypoglycemia and / or hyperglycemia. Blood-glucose concentration calculation is enhanced by using the combination of the oxygen metabolism analysis and electrocardiographic analysis.

The invention discloses an electrocardiogram data analysis method and system, and relates to the field of medical equipment. The method comprises the following steps: by collecting human body electrocardiogram data by virtue of a plurality of leads, acquiring and saving the electrocardiogram data collected by the plurality of the leads within N hours; selecting one of the plurality of the leads, with the minimum interference, as an analysis lead, and analyzing the electrocardiogram data collected by the analysis lead, so as to obtain electrocardiogram waveforms and an electrocardiogram form report within the N hours; examining the electrocardiogram waveforms which are obtained by analyzing the electrocardiogram data collected by the analysis lead to find out the electrocardiogram waveform with waveform quality nonconforming to requirement as well as a corresponding time period; and replacing the electrocardiogram form report with the waveform quality nonconforming to the requirement with the corresponding electrocardiogram form report of the electrocardiogram data collected by other leads within the time period, so that an electrocardiogram form report with analysis precision improved is obtained. The analysis method and the analysis system disclosed by the invention can improve the precision of a dynamic electrocardiogram analysis result.

The invention provides an electrocardiosignal R peak detection method based on waveform characteristic matching. The method utilizes waveform characteristic matching to identify R peak of electrocardiosignal, the characteristic matching method takes difference vector between points as basic characteristic, the basic characteristic has translational invariance and rotational invariance and can overcome influence of baseline drift of electrocardiosignal signal; meanwhile, logarithm polar coordinate transformation is carried out on the difference vector and partition is carried out to measure similarity of wave form, the measurement is sensitive to the adjacent morphological characteristic, can capture global outline information of wave form and has robustness to wave form ripple; besides, influence of interference signal can be eliminated by setting proper threshold, and further accurate identification and detection on R peak of electrocardiosignal are realized. The invention is applied to related electrocardiogram analyser, accurate identification on R peak of electrocardiosignal can be realized, thus being beneficial to improving detection and analysis capability of electrocardiogram analysis equipment.

The invention relates to the technical field of electrocardiogram analysis, in particular to an electrocardiogram image recognition method and device and a service terminal. The electrocardiogram image recognition method is applied to the service terminal. The service terminal comprises an electrocardiogram deep learning model and at the same time, is used for inputting electrocardiogram images. The electrocardiogram image recognition method comprises the steps that the input electrocardiogram images are divided into a plurality of image segments, features of the plurality of image segments are extracted by the usage of the electrocardiogram deep learning model, according to the extracted features, the electrocardiogram deep learning model is used for recognizing every image segment in the plurality of image segments to obtain the input electrocardiogram image information, and therefore automatic recognition of the input electrocardiogram images is achieved, the data amount is accumulated, and at the same time, the workload of workers is reduced.

The invention provides a heart rate variability analysis method, which comprises the following steps of collecting an electrocardiosignal; performing amplification processing on the collected electrocardiosignal, and outputting the processed electrocardiosignal; receiving the amplified electrocardiosignal; performing denoising processing on the amplified electrocardiosignal; extracting R wave feature parameters in the denoised electrocardiosignal; judging and counting the heart beat type and calculating time domain and frequency domain indexes according to the R wave feature parameters; and outputting an electrocardiogram analysis report according to the heart beat type, the time domain index, the frequency domain index and statistic data, and performing encrypted storage. According to the embodiment of the invention, the weak electrocardiosignal is amplified in the electrocardiosignal collecting process; then, the amplified electrocardiosignal is subjected to noise filtering through the heart rate variability analysis processing; the judgment on each heart beat is realized; and the accuracy and the practicability of the diagnosis are improved.

The invention discloses an electrocardiogram R wave detection method. The method comprises the following steps: filtering an input electrocardiogram signal by a band pass filter, and performing phase compensation; performing differential processing; performing data reduction on a differential signal by adopting linear variation; performing Shannon energy conversion by using a formula d(n)*d(n)*log(d(n)*d(n)); filtering by using an average filter, and performing phase compensation; detecting a maximum point and a minimum point, eliminating a fault R point, and correcting a falsely eliminated point to obtain a position of approximate R wave; and searching the position of true R in a range of periphery of the position of the approximate R wave + / - 25 points. By using the method, the problems of time delay and asystole detection unavailability in the conventional R wave detection method can be solved, and the method can be used for analyzing real-time electrocardiogram to reduce time delay and reduce required memory space, so that the accuracy rate is improved.

The invention discloses a safety protection system for occupying a sudden disease of a driver and aims to solve technical problems that a physiological monitor is inconvenient for a drive to wear, the driver lacks rescue measures when a disease occurs, a vehicle is not well controlled and the like in the prior art. The safety protection system for occupying the sudden disease of the driver comprises a processor, an electrocardiogram sensor, an electrocardiogram analysis module, a wireless voice rescue unit and a global positioning system (GPS) positioning module, wherein the processor is connected with the electrocardiogram sensor, the wireless voice rescue unit and the GPS positioning module, the electrocardiogram analysis module is arranged in the processor, electrodes of the electrocardiogram sensor are arranged on a steering wheel, and the processor is connected with an automobile body controller and an engine control unit through a communication bus on an automobile.

The invention discloses a wearable electrocardiogram monitoring system. The system comprises a wearable electrocardiogram monitor, a mobile phone and a server; the wearable electrocardiogram monitor is used for collecting and preprocessing human body electrocardiogram signals, converting the electrocardiogram signals to digital signals and sending the digital signals to an electrocardiogram monitoring APP of the mobile phone through Bluetooth transmission; the electrocardiogram monitoring APP of the mobile phone receives electrocardiogram data sent by the electrocardiogram monitor through the Bluetooth, stores the electrocardiogram data, conducts filtering processing on the electrocardiogram signals, displays the electrocardiogram signals in a mobile phone screen in real time, transmits the electrocardiogram data to the server through a network, calculates the instantaneous heart rate through electrocardiogram analysis, judges whether the electrocardiogram is abnormal or not and finally calls the stored electrocardiogram data to draw a historical electrocardiogram waveform for viewing; the server receives the electrocardiogram data sent by the APP, analyzes whether the electrocardiogram is abnormal or not in detail and then feeds a result back to the APP. The electrocardiogram monitoring system has the advantages of being low in power dissipation, small in size, long in detection time, easy to use and the like and can be applied to personal heart health monitoring.

A system, method and memory medium for operating on an electrocardiogram (ECG) signal. A multiscale short-time Fourier transform (STFT) is perform on a set of ECG samples {s(n)} to obtain a transform array. For each sufficiently energetic peak in the transform array, a refined window width value and a refined window displacement value is generated by: computing an inner product between the set of samples and each of a plurality of functions, where the plurality of functions are sufficiently close to a coarse approximation function given by the peak location; and solving a linear system Av=c for the unknown vector v, where the vector c is determined by the inner products, where the matrix A is determined by the center times of the plurality of functions. After appropriate selection, the refined window width and refined window displacement may be used to represent ECG waveform features.

The system and method provide for electrocardiogram analysis and optimization of patient-customized cardiopulmonary resuscitation and therapy delivery. An external medical device includes a housing and a processor within the housing. The processor can be configured to receive an input signal for a patient receiving chest compressions and to select at least one filter mechanism and to apply the filter mechanism to the signal to at least substantially remove chest compression artifacts from the signal. A real time dynamic analysis of a cardiac rhythm is applied to adjust and integrate CPR prompting of a medical device. Real-time cardiac rhythm quality is facilitated using a rhythm assessment meter.

A method of analyzing the electrocardiogram ("ECG") using a set of vectors mathematically derived from the heart vector. The entire ECG waveform of one representative heartbeat is analyzed as a time series of vectors taken at selected time intervals. The vector set consists of the heart vector, the vector of deviation, vector of abnormality, delta vector, the delta vector deviation, and the delta vector abnormality. The analysis system can be applied to two or any greater number of ECG leads represented on planar axes, orthogonal spatial axes, or four or more axes in multidimensional space. The normal range of the ECG in this method is delineated by an adaptive multi-dimensional polyhedron in space to which the unknown ECG is compared. This is accomplished by utilizing a computer platform and the software program to support the required mathematical calculations.

The invention discloses an automatic detection and transformation method for loose of electrocardiograph limb electrodes. When one limb electrode or two limb electrodes loose (s), the loosed electrodes need not to be fixed again; the electric potential at a Wilson center end can be automatically adjusted by a system, and an obtained precordial lead electrocardiogram is still normal, so that under the condition, most parts of recorded electrocardiogram lead signals are ensured to be still available. The automatic detection and transformation method for loose of the electrocardiograph limb electrodes has the characteristic that the signals are recorded stably in a long time process; and through automatic adjustment on the electric potential of the Wilson center, the most parts of recorded electrocardiogram lead signals are ensured to be stable and effective in a long-time recording process under the condition that parts of limb electrodes loose, thereby laying a good foundation for subsequent electrocardiogram analysis and processing.

The invention provides a dynamic electrocardiogram analysis intelligent diagnosis system and a method. The dynamic electrocardiogram analysis intelligent diagnosis system comprises a database module, a template module, and an analysis module; the database module is used for storing electrocardio data of a human body detected through multiple leads and basic information of the detected human body; the template module is used for defining multiple case templates according to different symptoms, and every case template has multiple constant parameter values; the analysis module is used for performing intelligent full-leading analysis on the detected electrocardio data, acquiring multiple input variable values and then comparing every input variable value with a constant parameter value corresponding to every case template; if every operation result in one case template is real, a text conclusion is output, and then an electrocardio diagnosis report is generated through the text conclusion. The dynamic electrocardiogram analysis intelligent diagnosis system and the method have the advantages of greatly improving the diagnosis speed, reducing labor intensity of a doctor, improving the accuracy of the diagnosis conclusion, and reducing the omission of the diagnosis conclusion.

The invention discloses a dynamic electrocardiogram analysis method and system based on the network and artificial intelligence. The method comprises the steps that a dynamic electrocardiogram storageand analysis server receives dynamic electrocardiogram data uploaded by a dynamic electrocardiogram original collection data uploading terminal; the dynamic electrocardiogram storage and analysis server performs pre-analysis on the received dynamic electrocardiogram data, and automatically generates a dynamic electrocardiogram analysis report directly through the pre-analysis or automatically generates the dynamic electrocardiogram analysis report after a dynamic electrocardiogram pre-analysis data analysis terminal confirms a pre-analysis result; a dynamic electrocardiogram analysis report display and explanation terminal displays, explains and prints the dynamic electrocardiogram analysis report so as to assist a medical worker in diagnosing a patient and explaining the dynamic electrocardiogram analysis report to the patient. The analysis report generated through the above technical scheme and a provided corresponding data explanation report are used for being viewed by primary hospital physicians, so that the efficiency of explaining and analyzing the report of the physicians is improved.

The present invention relates to a computer-implemented method for electrocardiogram analysis, the method comprising the steps of receiving at least one ECG signal; analyzing the ECG signal to provide features and / or identify at least one episode and / or event, wherein an episode is a segment of the ECG signal defined by a starting time, a duration and a label obtained during the analysis of the ECG signal and an event is a strip of the ECG signal of predefined duration defined by a starting time and a label obtained during the analysis of the ECG signal; and displaying a multiple field display (1) which includes at least a main plot (42), being a global view of a graphic representation of the ECG signal in a first time window; a local view of a graphic representation of the ECG signal in a second time window (51), where the first time window comprises the second time window; an intermediate view of a graphic representation of the ECG signal in a third time window (52), wherein the third time window comprises the second time window and has a duration comprised between the duration of the first time window and the duration of the second time window

The invention discloses an electrocardiogram remote diagnosis system based on an arithmetic server, which at least comprises a source terminal used for sending out electrocardiogram data, and the arithmetic server, wherein the arithmetic server can be arranged in a place which is far away from the data source terminal; the data source terminal is connected with the arithmetic server by a network; electrocardiogram data is sent into the arithmetic server by the data source terminal through the network; and the arithmetic server at least comprises an electrocardiogram analysis algorithm, uses the electrocardiogram analysis algorithm for carrying out automatic analysis and diagnosis for the electrocardiogram data, and returning the diagnosis result to the data source terminal, or other mediums such as a database, a file, email address or short message.

A self-learning dynamic electrocardiography analysis method employing artificial intelligence. The method comprises: pre-processing data, performing cardiac activity feature detection, interference signal detection and cardiac activity classification on the basis of a deep learning method, performing signal quality evaluation and lead combination, examining cardiac activity, performing analytic computations on an electrocardiogram event and parameters, and then automatically outputting report data. The method achieves an automatic analysis method for a quick and comprehensive dynamic electrocardiography process, and recording of modification information of an automatic analysis result, while also collecting and feeding back modification data to a deep learning model for continuous training, thereby continuously improving and enhancing the accuracy of the automatic analysis method. Also disclosed is a self-learning dynamic electrocardiography analysis device employing artificial intelligence.

The invention discloses a method for analyzing abnormal electrocardiogram tension for remote medical care. The method comprises the following steps of firstly, collecting a large amount of standard 12-lead electrocardiogram data in a remote method; then, converting the electrocardiogram into high-dimension tension electrocardiogram data by a short-time Fourier transform; directly using the high-dimension tension electrocardiogram data as a feature, and extracting electrocardiogram features directly being used for classification by an feature extraction and feature dimension reduction algorithm through directly using the tension data as the input. Because the method is based on a TTV (transit timing variable) transform principle, the features based on vector storage can be obtained, and then the vector features are classified by a SVM (support vector machine) classifying method. The method has the advantages that the tension electrocardiogram data are directly used as the input, the structure information of multi-lead electrocardiogram is fully utilized, the defect of non-precise data ton single analysis of the original single-lead electrocardiogram is eliminated, and the effectivity of the electrocardiogram analysis is realized.

The invention discloses a dynamic electrocardiogram analysis method for intelligently selecting leads, and relates to the field of dynamic electrocardiogram analysis. Invalid data of a Holter wearingand picking-off part is automatically cut off through clutter identification, interference caused by unstable wearing is eliminated, a starting point and an ending point for analyzing electrocardiogram data are automatically generated, the time for doctors to manually find and then analyze an effective data starting point and an effective data ending point is saved, and the efficiency is greatly improved. The leads with large errors are low accuracy are screened out through heart beat RR variances of the leads, the optimal analysis lead set is selected in the remaining leads according to the signal amplitude, the analysis accuracy is improved, the situation that the doctors reselect the leads again for analysis is reduced, and the analysis efficiency is improved.

The invention discloses a method for detecting an electrocardiogram QRS wave group. The method comprises the steps of using an extremum method to find peaks and troughs in a QRS wave, according to anextremum point found, and combining an equipotential step potential value and amplitude information to detect each sub-waveform in the QRS wave group so as to determine the time position of the QRS wave group so that QRS wave group forms can be clearly displayed and the heart rate can be calculated; the accurate detection of the QRS wave group is the basis for the automatic diagnosis of an electrocardiogram. After the detection of the QRS wave group is determined, it is possible to calculate the heart rate, that is, the number of heart beats per minute, heart rate variability and other electrocardiogram time interval measurement and amplitude measurement.

The system and method provide for electrocardiogram analysis and optimization of patient-customized cardiopulmonary resuscitation and therapy delivery. An external medical device includes a housing and a processor within the housing. The processor can be configured to receive an input signal for a patient receiving chest compressions and to select at least one filter mechanism and to apply the filter mechanism to the signal to at least substantially remove chest compression artifacts from the signal. A real time dynamic analysis of a cardiac rhythm is applied to adjust and integrate CPR prompting of a medical device. Real-time cardiac rhythm quality is facilitated using a rhythm assessment meter.

The embodiment of the invention relates to an artificial intelligence real-time analysis method and system for electrocardiogram monitoring. The method includes the steps of using electrocardiogram monitoring equipment for conducting electrocardiogram monitoring on a monitored user to obtain real-time electrocardiogram data and determining abnormal data of the real-time electrocardiogram data in real time on the basis of an online artificial intelligence (AI) electrocardiogram analysis model to generate a prewarning data segment; adopting a first cloud server for carrying out identification and judgment processing on the prewarning data segment according to an AI electrocardiogram evaluation model; adding a false alarm filtering mark to the prewarning data segment when this prewarning is determined to be a false alarm, and storing the false alarm filtering mark; carrying out abnormal data judgment on the prewarning data segment when prewarning is determined to be a true alarm, and transmitting an alarm record to a corresponding receiving device according to a transmission priority of alarm data records determined by a judgment level identifier; using the electrocardiogram monitoring equipment for uploading all the real-time electrocardiogram data to a second cloud server, generating dynamic electrocardiogram data of the monitored user, carrying out analysis according to an offline AI electrocardiogram analysis model and outputting report data.

The invention discloses an electrocardiosignal quality identification method. The electrocardiosignal quality identification method comprises the steps of S1, acquiring original electrocardiogram waveform amplitude data; S2, carrying out fragment segmentation on the electrocardiosignal by taking 1 second as a unit; S3, taking out the maximum value and the minimum value of the amplitude of each fragment to form an envelope point, and comparing all the envelope points so as to obtain envelope difference; S4, acquiring the amplitude variance yield of each segmentation section; S5, converting a time domain signal of an electrocardiogram fragment signal into a frequency domain signal, namely a power spectrum signal by utilizing fast Fourier transform, and integrating the amplitude of 1-5 Hz soas to obtain the power; S6, after acquiring a power spectrum signal of the electrocardiogram fragment signal in the step S5, integrating the amplitude of 5-40 Hz and the amplitude of 40-100 Hz separately so as to obtain the corresponding power, and calculating the signal-to-noise ratio of the two kinds of power; and S7, grading the quality of the electrocardiogram waveform according to the parameter envelope difference, the variance yields, the power of the signals with 1-5 Hz and the qualified condition of the signal-to-noise ratio.

The invention discloses a dynamic electrocardiogram and motion recording and analyzing system, which is used for automatic detection on user activities and electrocardiogram analysis under activity scenes. The system comprises an electrocardiogram and motion sensor unit, a data acquisition, storage and transmission unit and an analysis and software unit, wherein the electrode of a motion sensor and the electrode of an electrocardiogram sensor can be packaged together or used independently; the system records and automatically detects daily physical motions of a user, such as lying, sitting, walking, running, tumbling, sitting up, standing up, sitting down, lying down and the like, and gives corresponding activity intensity; the electrocardiogram is automatically analyzed; and a corresponding mark is given when an abnormal electrocardiogram or abnormal activity is detected, all corresponding original signals and analysis results are stored, and nursing staff are prompted. The system gives heart rate variability of the user under different activity intensities, and changes of the heart rate variability along with activity types, activity intensities and time. The systems gives a method of analyzing changes of heart rate and electrocardiogram forms along with activity intensity and duration, and can be used for aerobic exercise optimization and exercise safety in motion and exercising.