WO2019161611A1 - 心电信息处理方法和心电工作站 - Google Patents

心电信息处理方法和心电工作站 Download PDF

Info

Publication number
WO2019161611A1
WO2019161611A1 PCT/CN2018/083466 CN2018083466W WO2019161611A1 WO 2019161611 A1 WO2019161611 A1 WO 2019161611A1 CN 2018083466 W CN2018083466 W CN 2018083466W WO 2019161611 A1 WO2019161611 A1 WO 2019161611A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
report
heartbeat
ecg
information
Prior art date
Application number
PCT/CN2018/083466
Other languages
English (en)
French (fr)
Inventor
胡传言
曹君
刘畅
赵子方
张雪
王宝泉
Original Assignee
乐普（北京）医疗器械股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 乐普（北京）医疗器械股份有限公司 filed Critical 乐普（北京）医疗器械股份有限公司
Priority to EP18907191.3A priority Critical patent/EP3698708A4/en
Priority to US16/766,551 priority patent/US11783924B2/en
Publication of WO2019161611A1 publication Critical patent/WO2019161611A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A61B5/0245—Detecting, measuring or recording pulse rate or heart rate by using sensing means generating electric signals, i.e. ECG signals
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/363—Detecting tachycardia or bradycardia
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/364—Detecting abnormal ECG interval, e.g. extrasystoles, ectopic heartbeats
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7271—Specific aspects of physiological measurement analysis
    • A61B5/7282—Event detection, e.g. detecting unique waveforms indicative of a medical condition
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/63—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for local operation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
    • A61B2562/08—Sensors provided with means for identification, e.g. barcodes or memory chips
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
    • A61B5/0004—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by the type of physiological signal transmitted
    • A61B5/0006—ECG or EEG signals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Definitions

  • the present invention relates to the field of data processing technologies, and in particular, to an ECG information processing method and an ECG workstation.
  • the ECG workstation collects the weak ECG signals from the ECG collector and sends them to the computer processing system for amplification, analysis and processing, so as to achieve the purpose of diagnosing heart disease, usually by computer host, monitor, lead wire, ECG. It consists of a signal acquisition box and a printer. It has a window menu and does not require esoteric operation techniques and excessive manual intervention. The clinician or operator can obtain an ECG output report through it.
  • ECG monitoring performed by ECG workstations is a commonly used clinical monitoring method.
  • the ECG signal it monitors is the weak current reflected by the electrical activity of cardiomyocytes on the body surface, recorded by the body surface electrode and the amplified recording system.
  • the ECG data is automatically analyzed.
  • it is susceptible to various signal interferences.
  • Other non-cardiogenic electrical signals such as skeletal muscles, are also recorded during the recording process.
  • EMG signal interference caused by activities and so on. These signals may result in an output of incorrect heartbeat signal detection results.
  • the ECG signal is a manifestation of the process of myocardial electrical activity and can reflect a large amount of information about the state of the heart. When there is a problem in the heart state, the ECG signal will change accordingly. At present, the accuracy of the automatic analysis is far from enough, so that the reference of the output ECG test report is not significant, or it still depends on the subjective judgment of the doctor to form the electrocardiogram. Test Report.
  • the ECG test report of the existing ECG workstation has a single output mode, which cannot meet the different requirements of different users or different use requirements. Therefore, how to effectively improve the automatic analysis level of the electrocardiogram, and intelligently generate and output analytical data and meet the needs of multiple directions are the problems and challenges to be solved by the present invention.
  • the present invention provides an ECG information processing method and an ECG workstation, which can form a report data by performing a complete and rapid automatic analysis of the electrocardiogram data output by the ECG monitoring device; Requested or set output mode and data format output report data, and support update and modification of report data.
  • a first aspect of the embodiments of the present invention provides a method for processing an electrocardiogram information, including:
  • the ECG workstation receives ECG data output by the ECG monitoring device, where the ECG data includes the measured object ID and the detection time information;
  • the report data includes: report conclusion data corresponding to the measured object ID, report table item data, and/or report graphic data;
  • the report data query result list data includes at least one obtained by the query or a measured object ID and detection time information of a plurality of the report data;
  • the method further includes:
  • the electrocardiogram data is single-lead or multi-lead time series data; and the analyzing the electrocardiogram data of the electrocardiogram data to generate report data specifically includes:
  • each of the heartbeat data corresponding to a heartbeat cycle including a corresponding P wave, QRS Wave group, T wave amplitude data and start and end time data;
  • the heartbeat analysis data of the specific heartbeat in the primary classification information result is input to the trained ST segment and the T wave change model to identify the ST segment and the T wave evaluation information;
  • P-wave and T-wave feature detection are performed on the heartbeat analysis data, and detailed feature information of P wave and T wave in each heart beat is determined;
  • the report graphic data is generated based on typical data segments in each of the electrocardiogram event data.
  • performing heartbeat detection processing on the first filtered processed electrocardiogram data further includes:
  • the detection confidence of each QRS complex is determined based on the estimated value of the noise and the maximum amplitude in each QRS complex.
  • the interference recognition two-class classification model obtained by the training performs interference recognition on the heartbeat data, and specifically includes:
  • the heartbeat data is cut and sampled by the first data amount, and the data obtained by the cut sampling is input to the interference recognition two-class model for interference recognition;
  • the interference identification is performed for each of the sampled data segments.
  • the heartbeat analysis data of the specific heartbeat in the result of the primary classification information is input to the trained ST segment and the T wave change model to identify the ST segment and the T wave evaluation information, and specifically includes:
  • the specific heart beat data in the primary classification information is sequentially input into the ST segment and the T wave change model according to the training according to the lead, and the feature extraction of the amplitude and time characterization data is performed on the specific heart beat data of each lead. And analyzing, obtaining ST segment and T wave change information of each lead, and determining ST segment and T wave evaluation information; the ST segment and T wave evaluation information are specifically ST segment and T wave corresponding to the heart beat segment data Changed lead position information.
  • the generating the report graphic data according to the typical data segment in each of the electrocardiogram event data includes:
  • the data segment of each electrocardiogram event is evaluated, and the data segment with the highest signal quality evaluation parameter is selected as a typical data segment in the ECG event.
  • the ECG information processing method provided by the embodiment of the present invention forms a report data by performing complete and rapid automatic analysis on the electrocardiogram data output by the electrocardiogram monitoring device; and can query the report data according to the request or set output mode and data.
  • the format outputs report data and supports updates and modifications to the report data.
  • a second aspect of the embodiments of the present invention provides an ECG workstation, the device comprising a memory and a processor, the memory is for storing a program, and the processor is configured to execute the method in the first aspect and the implementation manners of the first aspect.
  • a third aspect of the embodiments of the present invention provides a computer program product comprising instructions for causing a computer to perform the methods of the first aspect and the implementations of the first aspect when the computer program product is run on a computer.
  • a fourth aspect of the embodiments of the present invention provides a computer readable storage medium.
  • the computer readable storage medium stores a computer program.
  • the computer program is executed by the processor, the first aspect and the method in each implementation manner of the first aspect are implemented. .
  • FIG. 1 is a flowchart of a method for processing ECG information according to an embodiment of the present invention
  • FIG. 2 is a flowchart of a method for processing electrocardiogram data according to an embodiment of the present invention
  • FIG. 3 is a schematic diagram of a two-classification model for interference recognition according to an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a heart beat classification model according to an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of a ST segment and T wave change model according to an embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram of an ECG workstation according to an embodiment of the present invention.
  • 8a-8g are report output modes of dynamic electrocardiogram monitoring data according to an embodiment of the present invention.
  • the ECG workstation sends the collected ECG signals to the computer processing system for amplification, analysis and processing, so as to achieve the purpose of ECG examination and monitoring.
  • the ECG signal is the weak current reflected by the electrical activity of the cardiomyocytes on the body surface, recorded by the body surface electrode and the amplified recording system.
  • the invention is based on the recorded ECG signal, performs complete and rapid automatic analysis to form report data, and establishes an output mode and data format for querying the report data, according to the request or setting, and updating and modifying the report data.
  • the ECG information processing method of the present invention mainly includes the following steps:
  • Step 110 The ECG workstation receives the ECG data output by the ECG monitoring device
  • the ECG monitoring device may specifically be a single-lead or multi-lead ECG monitor, and each ECG detecting device has a unique device ID, so that the measured data can be marked to indicate the data. Which device was obtained.
  • the electrocardiograph is a device that has an electrocardiogram data analysis and processing function and can provide information interaction between users, and can implement functions such as data transmission, user management and data management, and report output management of electrocardiogram data.
  • the ECG monitoring device can be integrated with the ECG monitoring device, or it can be connected by wired or wireless network for data transmission.
  • the wireless network includes wireless but not limited to wireless local area network (WIFI) based on IEEE802.11b standard, Bluetooth, 3G/4G/5G mobile communication network, and Internet of Things.
  • WIFI wireless local area network
  • the ECG monitoring device in this embodiment focuses on the function of ECG signal acquisition, and the output ECG data is processed by the ECG workstation.
  • the ECG monitoring device collects and records the signals generated by the electrophysiological activity of the cardiac cells in a single-lead or multi-lead manner by means of non-invasive electrocardiogram examination, and obtains electrocardiogram data to be sent to the ECG workstation.
  • the electrocardiogram data includes the object ID to be measured, the device ID of the electrocardiogram detecting device, and the detection time information.
  • Step 120 Perform ECG data analysis on the electrocardiogram data, generate report data, and store the data
  • the ECG signal is the embodiment of the myocardial electrical activity process. Therefore, in addition to the heart rate, the ECG signal can also display a large amount of information about the heart state. When there is a problem with the heart state, the ECG signal will change accordingly.
  • the research on the existing ECG signal processing methods in the industry we found that only very limited analysis and alarms were performed on ECG signals. In addition to this, in addition to effective interference identification and elimination of ECG signals to reduce false positives caused by interference signals, we believe that it can be improved from the following points:
  • the classification of heart beats is more detailed, and not only in the three categories of sinus, supraventricular and ventricular, so as to meet the complex and comprehensive analysis requirements of clinical electrocardiographers.
  • the ECG data processing process of the present invention adopts an artificial intelligence self-learning automatic ECG analysis method, which is implemented based on an artificial intelligence convolutional neural network (CNN) model.
  • the CNN model is a supervised learning method in deep learning. It is a multi-layer network (hidden layer) connection structure that simulates a neural network. The input signal passes through each hidden layer in turn, and a series of complicated mathematical processing (Convolution volume) is performed.
  • CNN belongs to the supervised learning method in artificial intelligence.
  • the input signal passes through multiple hidden layer processing to reach the final fully connected layer.
  • the classification result obtained by softmax logistic regression is related to the known classification result (label label).
  • label label There will be an error.
  • a core idea of deep learning is to continually minimize this error through a large number of sample iterations, and then calculate the parameters that connect the hidden layer neurons. This process generally requires constructing a special cost function, using a nonlinearly optimized gradient descent algorithm and a backpropagation algorithm (BP) to quickly and efficiently minimize the entire depth (the number of layers in the hidden layer). ) and breadth (dimension dimension) are all complex parameters in the neural network structure.
  • BP backpropagation algorithm
  • Deep learning inputs the data to be identified into the training model, passes through the first hidden layer, the second hidden layer, the third hidden layer, and finally outputs the recognition result.
  • the wave group feature recognition, the interference recognition, the heart beat classification and the like of the electrocardiogram data are all based on the artificial intelligence self-learning training model to obtain an output result, and the analysis speed is fast and the accuracy is high.
  • the step obtains the characteristic signal of the electrocardiogram data by performing wave group feature recognition on the electrocardiogram data, performs heartbeat classification on the electrocardiogram data according to the characteristic signal, and obtains heartbeat classification information according to the basic rule reference data of the electrocardiogram, according to the heartbeat classification information. Processing generates ECG event data and finally generates report data to achieve. Further, the process may be specifically implemented by the following steps as shown in FIG. 2.
  • Step 1201 The data format of the electrocardiogram data is resampled into a preset standard data format, and the first filtering process is performed on the ECG data of the converted preset standard data format.
  • the format of the ECG data is read and read, and different reading operations are implemented for different devices.
  • the baseline needs to be adjusted and converted into millivolt data according to the gain.
  • the data is converted to a sampling frequency that can be processed by the entire process. Then, high frequency, low frequency noise interference and baseline drift are removed by filtering to improve the accuracy of artificial intelligence analysis.
  • the processed ECG data is saved in a preset standard data format.
  • sampling frequency and transmission data format are solved, and high frequency, low frequency noise interference and baseline drift are removed by digital signal filtering.
  • Digital signal filtering can use high-pass filter, low-pass filter and median filter to eliminate power frequency interference, myoelectric interference and baseline drift interference, and avoid the impact on subsequent analysis.
  • a low-pass, high-pass Butterworth filter can be used for zero-phase shift filtering to remove baseline drift and high-frequency interference, retaining an effective ECG signal; median filtering can be performed using a preset duration of sliding window The median of the data point voltage magnitude replaces the amplitude of the center sequence of the window. It is possible to remove the baseline drift of the low frequency.
  • Step 1202 Perform heartbeat detection processing on the electrocardiogram data after the first filtering process, and identify multiple heartbeat data included in the electrocardiogram data;
  • Each heart beat data corresponds to a heart cycle, including the corresponding P wave, QRS complex, T wave amplitude and start and end time data.
  • the heartbeat detection in this step is composed of two processes, one is a signal processing process, and the characteristic frequency band of the QRS complex is extracted from the electrocardiogram data after the first filtering; the second is to determine the QRS complex by setting a reasonable threshold The time of occurrence.
  • a P wave, a QRS complex, a T wave component, and a noise component are generally included.
  • the QRS complex has a frequency range of 5 to 20 Hz, and the QRS complex signal can be proposed by a bandpass filter within this range.
  • the specific detection process is a process based on peak detection. Threshold judgment is performed for each peak sequence in the signal. When the threshold value is exceeded, the QRS group judgment process is entered, and more features are detected, such as RR interval and shape.
  • the threshold adjustment needs to be dynamically performed according to the change of the data characteristics in the time domain.
  • QRS complex detection mostly adopts the dual amplitude threshold combined with the time threshold.
  • the high threshold has a higher positive rate
  • the lower threshold has a higher sensitivity rate
  • the RR interval exceeds a certain period.
  • the time threshold is detected using a low threshold to reduce missed detection. Since the low threshold is low due to the low threshold, it is susceptible to T wave and myoelectric noise, and it is easy to cause multiple tests. Therefore, high threshold is preferred for detection.
  • Step 1203 Determine a detection confidence level of each heart beat according to the heart beat data
  • the confidence calculation module can provide an estimate of the confidence of the QRS complex detection based on the amplitude of the QRS complex and the amplitude ratio of the noise signal during the RR interval.
  • Step 1204 Perform interference recognition on the heartbeat data according to the interference recognition two-class model, obtain whether the heartbeat data has interference noise, and a probability value for determining the interference noise;
  • the interference phenomenon is easily affected by various effects during the long-term recording process, the acquired heartbeat data is invalid or inaccurate, and cannot correctly reflect the condition of the subject, and also increases the difficulty and workload of the doctor; and the interference data is also The main factor that leads to the inability of intelligent analysis tools to work effectively. Therefore, it is especially important to minimize external signal interference.
  • This step is based on the end-to-end two-category recognition model with deep learning algorithm as the core. It has the characteristics of high precision and strong generalization performance, which can effectively solve the disturbance problem caused by the main interference sources such as electrode stripping, motion interference and static interference. It overcomes the problem that the traditional algorithm has poor recognition effect due to the diversity and irregularity of the interference data.
  • Step A using interference recognition two-class model for heart rate data for interference recognition
  • Step B identifying a data segment in the heartbeat data that the heartbeat interval is greater than or equal to the preset interval determination threshold
  • Step C performing signal abnormality determination on the data segment whose heartbeat interval is greater than or equal to the preset interval determination threshold, and determining whether it is an abnormal signal;
  • the identification of the abnormal signal mainly includes whether the electrode piece is off, low voltage, and the like.
  • Step D if it is not an abnormal signal, determine a starting data point and a ending data point of the sliding sample in the data segment according to the set time value by a preset time width, and start sliding sampling the data segment from the starting data point, Obtaining a plurality of sampled data segments until the data point is terminated;
  • step E interference identification is performed for each sampled data segment.
  • the above steps A-E will be described with a specific example.
  • the heartbeat data of each lead is cut and sampled by the set first data amount, and then input to the interference recognition two-classification model for classification, and a probability value of the interference recognition result and the corresponding result is obtained; for the heartbeat interval If the heartbeat data is greater than or equal to 2 seconds, first determine whether the signal is overflowing, low voltage, and the electrode is off; if not, according to the first data amount, starting from the left heartbeat, continuing to the right continuously without overlapping the first data amount Sliding sampling for identification.
  • the input may be the first data volume heartbeat data of any lead, and then the interference identification two-class model is used for classification, and the direct output is the interference classification result, and the obtained result is fast, the accuracy is high, the stability is good, and the subsequent Analysis provides more effective and quality data.
  • the interference data is often caused by the external disturbance factor, there are mainly the electrode piece falling off, low voltage, static interference and motion interference.
  • the interference data generated by different disturbance sources is different, and the interference data generated by the same disturbance source is different.
  • the diversity is wide, but it is very different from the normal data, it is also possible to ensure the diversity when collecting the interference training data, and take the sliding sampling of the moving window. It is possible to increase the diversity of the interference data so that the model is more robust to the interference data. Even if the future interference data is different from any previous interference, the similarity with the interference is greater than the normal data. The ability of the model to identify interfering data is enhanced.
  • the interference identification two-class model used in this step can be as shown in Figure 3.
  • the network first uses two layers of convolutional layers.
  • the convolution kernel size is 1x5, and each layer is followed by a maximum pool.
  • the number of convolution kernels starts at 128, and the number of convolution kernels doubles each time the largest pooling layer is passed.
  • the convolutional layer is followed by two fully connected layers and a softmax classifier. Since the classification number of the model is 2, softmax has two output units, which in turn correspond to the corresponding categories, and uses cross entropy as the loss function.
  • the sampling rate is 200 Hz
  • the data length is a segment D[300] of 300 ECG voltage values (millivolts)
  • the input data is: InputData(i,j), where i is the ith Lead, j is the jth segment D of the lead i. All the input data is randomly dispersed to start training, which ensures the convergence of the training process. At the same time, it controls the collection of too many samples from the same patient's ECG data, improving the generalization ability of the model and the accuracy of the real scene. After the training converges, using 1 million independent test data for testing, the accuracy rate can reach 99.3%. Another specific test data is shown in Table 1 below.
  • Step 1205 determining the validity of the heartbeat data according to the detection confidence, and, according to the lead parameter and the heartbeat data determining the valid heartbeat data, combining the result of the interference recognition and the time rule to generate the heartbeat time series data, and Generating heartbeat analysis data based on cardiac time series data;
  • each lead heart rate data can be cut using a preset threshold to generate heartbeat analysis data of each lead required for specific analysis.
  • the heartbeat data merging process performed by the lead heartbeat merging module is as follows: according to the refractory period of the reference data of the basic rule of the electrocardiogram, the time characterization data combination of the different lead heartbeat data is obtained, and the heartbeat data with large deviation is discarded.
  • the above-mentioned time characterization data combination voting generates a merged heart beat position, the merged heart beat position is added to the combined cardiac beat time sequence, and the next set of heart beat data to be processed is moved, and the loop execution is performed until all the heart beat data are merged.
  • the ECG activity refractory period may preferably be between 200 milliseconds and 280 milliseconds.
  • the time characterization data combination of the acquired different lead heartbeat data should satisfy the following conditions: Time characterization of the heart beat data Each lead in the data combination contains at most one time characterization data of the heart beat data.
  • the number of leads using the detected heartbeat data is determined as a percentage of the effective number of leads; if the time of the heartbeat data is indicative of the position of the corresponding lead is a low voltage
  • the lead, the interfering segment, and the electrode are considered to be inactive leads for this heartbeat data when the electrode is detached.
  • the time average of the heart beat data can be used to obtain the average value of the data.
  • this method sets a refractory period to avoid false merges.
  • a unified heartbeat time series data is output through the merging operation.
  • This step can simultaneously reduce the multi-detection rate and missed detection rate of the heart beat, and effectively improve the sensitivity and positive predictive rate of heart beat detection.
  • Step 1206 performing signal quality analysis on the heartbeat analysis data, evaluating the signal quality of the heartbeat analysis data, and obtaining signal quality evaluation parameters of the heartbeat analysis data.
  • the signal quality evaluation may not be performed. If the monitoring is dynamic electrocardiogram data, various disturbances will occur during the monitoring process, resulting in relatively more invalid signal generation. In order to avoid the invalid signal affecting the final result calculation, signal quality evaluation is needed to reduce the invalid signal pair. The impact of the final result.
  • the signal-to-noise ratio determines the signal quality evaluation parameters.
  • the specific steps may include:
  • Step A extracting position information and width information of the QRS complex in the heartbeat analysis data
  • Step B extracting a signal of an RR interval between two adjacent QRS group signals
  • Step C filtering the signal of the RR interval, and performing envelope calculation on the filtered signal to obtain an average power of the noise signal of the RR interval; wherein, the average power of the noise signal of the RR interval is between the RRs The mean value of the envelope amplitude during the period.
  • Step D obtaining a signal quality evaluation parameter according to the average power of the noise signal and the power of the QRS group signal;
  • the signal quality evaluation parameter can be represented by the noise level of the RR interval relative to the QRS complex. Specifically, it is calculated based on the power of the QRS complex and the average power of the noise signal.
  • S i is the amplitude of the i-th QRS complex signal
  • N i,t is the amplitude of the t-th sample point in the i-th RR interval interval
  • T is the RR interval length.
  • Step 1207 Perform feature extraction and analysis on the amplitude and time characterization data of the heartbeat analysis data according to the heartbeat classification model, and obtain primary classification information of the heartbeat analysis data;
  • the multi-lead classification method includes two methods: lead voting decision classification method and lead synchronization association classification method.
  • the lead voting decision classification method is based on the heartbeat analysis data of each lead to conduct independent lead classification, and then the result vote is merged to determine the voting result decision method of the classification result; the lead synchronous association classification method uses the heart beat for each lead Analyze data for simultaneous association analysis.
  • the single-lead classification method is to analyze the heartbeat analysis data of the single-lead device, and directly use the corresponding lead model for classification, and there is no voting decision process. The following describes several classification methods described above.
  • Single-lead classification methods include:
  • the single-lead heartbeat data is cut to generate single-lead heartbeat analysis data, and the characteristics of the amplitude and time characterization data of the heartbeat classification model corresponding to the training are input. Extract and analyze to obtain a single-lead classification information.
  • the lead voting decision classification method may specifically include:
  • the first step is to cut the heartbeat data of each lead according to the heartbeat time series data, thereby generating heartbeat analysis data of each lead;
  • the feature extraction and analysis of the amplitude and time characterization data of each lead heartbeat analysis data are performed, and the classification information of each lead is obtained;
  • the classification voting decision calculation is performed according to the classification information of each lead and the reference weight value reference coefficient, and the primary classification information is obtained.
  • the lead weight value reference coefficient is based on the Bayesian statistical analysis of the electrocardiogram data to obtain the voting weight coefficient of each lead for different heart beat classifications.
  • the lead synchronization association classification method may specifically include:
  • each lead heartbeat data is cut to generate heartbeat analysis data of each lead; and then the heartbeat analysis data of each lead is performed according to the trained multi-lead synchronous correlation classification model. Synchronous amplitude and time characterizing the feature extraction and analysis of the data, and obtaining a classification information of the heartbeat analysis data.
  • the synchronous correlation classification method input of the heart beat data is all the lead data of the dynamic electrocardiogram device.
  • the data points of the same position and a certain length on each lead are intercepted and synchronously transmitted to the trained
  • the artificial intelligence deep learning model performs computational analysis, and the output is that each heartbeat position point comprehensively considers all the lead ECG signal characteristics, and the accurate heart beat classification of the heartbeat associated with the heart rhythm characteristics in time.
  • the method fully considers that the different lead data of the electrocardiogram actually measures the information flow transmitted by the cardiac electrical signal in different vector directions of the electrocardiogram, and comprehensively analyzes the multi-dimensional digital features transmitted by the electrocardiogram signal in time and space. Greatly improved the traditional method only relying on a single lead independent analysis, and then the results are summarized into some statistical voting methods and the easy to get the classification error defects, greatly improving the accuracy of heart rate classification.
  • the heartbeat classification model used in this step can be as shown in FIG. 4, and specifically can be an end-to-end multi-label classification model inspired by the model of convolutional neural network AlexNet, VGG16, Inception and the like based on artificial intelligence deep learning.
  • the model's network is a 7-layer convolutional network, with each convolution followed by an activation function.
  • the first layer is a convolutional layer of two different scales, followed by six convolutional layers.
  • the convolution kernels of the seven-layer convolution are 96, 256, 256, 384, 384, 384, 256, respectively. Except for the first-level convolution kernel, which has two scales of 5 and 11, respectively, the other layer has a convolution kernel scale of 5.
  • the third, fifth, sixth, and seven-layer convolutional layers are followed by the pooling layer. Finally followed by two fully connected layers.
  • the heartbeat classification model in this step we used a training set containing 17 million data samples from 300,000 patients for training. These samples are generated by accurately labeling the data according to the requirements of dynamic electrocardiogram analysis and diagnosis.
  • the annotations are mainly for common arrhythmia, conduction block and ST segment and T wave changes, which can meet the model training of different application scenarios.
  • the marked information is saved in a preset standard data format.
  • a small sliding is performed on the classification with less sample size to amplify the data. Specifically, it is based on each heart beat and according to a certain step. (For example, 10-50 data points) move 2 times, which can increase the data by 2 times, and improve the recognition accuracy of the classified samples with less data. After the actual results are verified, the generalization ability has also been improved.
  • the length of the interception of the training data may be 1 second to 10 seconds.
  • the sampling rate is 200 Hz, with a sampling length of 2.5 s, and the obtained data length is a segment D [500] of 500 ECG voltage values (millivolts)
  • the input data is: InputData (i, j), where i is The i-th lead, j is the j-th segment D of the lead i. All the input data is randomly dispersed to start training, which ensures the convergence of the training process. At the same time, it controls the collection of too many samples from the same patient's ECG data, improving the generalization ability of the model, and the accuracy of the real scene.
  • the segment data D corresponding to all the leads is synchronously input, and the lead data of multiple spatial dimensions (different cardiac axis vectors) of each time position is synchronously learned according to the multi-channel analysis method of image analysis, thereby Get a more accurate classification result than the conventional algorithm.
  • Step 1208 inputting, to the ST segment and the T wave change model, the heartbeat analysis data of the specific heartbeat in the primary classification information result, and determining the ST segment and the T wave evaluation information;
  • the ST segment and T wave evaluation information is specifically the lead position information in which the ST segment and the T wave corresponding to the heartbeat analysis data are changed. Because clinical diagnosis requires localization of changes to ST segments and T waves to specific leads.
  • the specific heartbeat data of the primary classification information refers to the heartbeat analysis data including the sinus beat (N) and other heartbeat types that may contain ST changes.
  • the ST segment and T wave change lead positioning module inputs the specific heart beat data of the primary classification information into each lead according to each lead into an artificial intelligence deep learning training model for identifying the ST segment and the T wave change, and performs calculation analysis and output.
  • the results indicate whether the characteristics of the lead segment conform to the conclusions of the ST segment and the T wave change, so that the information of the ST segment and the T wave change occurring in the specific lead, that is, the ST segment and the T wave evaluation information can be determined.
  • the specific method may be: inputting the data of each lead heartbeat analysis of the sinus heartbeat in the primary classification information, inputting the ST segment and the T wave change model, and identifying and analyzing the sinus beat analysis data one by one to determine whether the sinus beat analysis data is There are ST segment and T wave changing characteristics and specific lead position information that occurs, and ST segment and T wave evaluation information is determined.
  • the ST segment and T wave change model used in this step can be as shown in Fig. 5, and can be an end-to-end classification model inspired by models such as artificial neural network deep learning based convolutional neural networks AlexNet and VGG16.
  • the model is a 7-layer network with 7 convolutions, 5 pools, and 2 full connections.
  • the convolution kernel used for convolution is 1x5, and the number of filters for each layer is different.
  • the number of layer 1 convolution filters is 96; the second layer convolution is combined with the third layer convolution, the number of filters is 256; the fourth layer convolution is combined with the fifth layer convolution, and the number of filters is 384; the number of the sixth layer convolution filter is 384; the number of the seventh layer convolution filter is 256; the first, third, fifth, sixth, and seventh layers of the convolution layer are pooled. Then there are two full connections, and finally the results are divided into two categories using the Softmax classifier. In order to increase the nonlinearity of the model and extract the features of higher dimensionality of the data, two convolutional modes are used.
  • the ratio of the training data to the T wave change is about 2:1, which guarantees the good generalization ability of the model in the classification process and does not appear to have a tendency to have more training data.
  • the shape of the heart beat is diverse, the forms of different individuals are not the same. Therefore, in order to better estimate the distribution of each classification, the characteristics can be effectively extracted.
  • the training samples are collected from individuals of different ages, weights, genders, and areas of residence.
  • the ECG data of a single individual in the same time period is often highly similar, in order to avoid over-learning, when acquiring data of a single individual, a small number of samples of different time periods are randomly selected from all the data; The patient's heartbeat morphology has large differences between individuals and high intra-individual similarity. Therefore, when dividing training and test sets, different patients are divided into different data sets to avoid the same individual data appearing in the training set at the same time. With the test set, the resulting model test results are closest to the real application scenario, ensuring the reliability and universality of the model.
  • Step 1209 Perform P wave and T wave feature detection on the heartbeat analysis data according to the heartbeat time series data, and determine detailed feature information of the P wave and the T wave in each heart beat;
  • the detailed feature information includes amplitude, direction, shape, and start and stop time data; in the analysis of the heartbeat signal, the features of the P wave, the T wave, and the QRS wave are also important basis in the analysis of the electrocardiogram.
  • the P-wave, T-wave and QRS complexes are extracted by calculating the position of the segmentation point in the QRS complex and the position of the P- and T-wave segmentation points. . It can be realized by QRS group cut point detection, single lead PT detection algorithm and multi-lead PT detection algorithm.
  • QRS group segmentation point detection According to the QRS group segment power maximum point and the start and end points provided by the QRS complex detection algorithm, the R point, R' point, S point and S' point of the QRS group in a single lead are searched. When there is multi-lead data, the median of each segmentation point is calculated as the last segmentation point position.
  • P-wave and T-wave detection algorithms are relatively low in amplitude relative to QRS complex, and the signal is gentle, which is easy to be submerged in low-frequency noise, which is a difficult point in detection.
  • QRS complex detection the method uses a low-pass filter to perform third filtering on the signal after eliminating the influence of the QRS complex on the low frequency band, so that the relative amplitude of the PT wave is increased.
  • the T wave is then found between the two QRS complexes by peak detection. Because the T wave is a wave group generated by ventricular repolarization, there is a clear lock-time relationship between the T wave and the QRS complex.
  • the midpoint between each QRS complex and the next QRS complex (such as the range between 400ms and 600ms after the first QRS complex) is used as the T-wave detection.
  • the largest peak is selected as the T wave in this interval.
  • the direction and morphological characteristics of the P wave and the T wave are determined based on the peak and position data of the P wave and the T wave.
  • the cutoff frequency of the low pass filtering is set between 10-30 Hz.
  • Multi-lead P-wave and T-wave detection algorithms In the case of multi-lead, since the generation time of each wave in the heart beat is the same, the spatial distribution is different, and the temporal and spatial distribution of noise is different, the traceability algorithm can be used to perform P, Detection of T waves.
  • the signal is first subjected to QRS complex elimination processing and the signal is third filtered using a low pass filter to remove interference.
  • Each individual component in the original waveform is then calculated by an independent component analysis algorithm. Among the separated independent components, according to the distribution characteristics of the peaks and the position of the QRS complex, the corresponding components are selected as the P-wave and T-wave signals, and the direction and morphological characteristics of the P-wave and the T-wave are determined.
  • Step 1210 Perform secondary classification processing on the heartbeat analysis data according to the basic rule of the electrocardiogram, the detailed feature information of the P wave and the T wave, and the ST segment and the T wave evaluation information in one classification information to obtain the heartbeat classification information;
  • the basic rule of ECG reference data is generated by following the basic rules describing the electrophysiological activity of cardiomyocytes and the clinical diagnosis of electrocardiogram in authoritative ECG textbooks, such as the minimum time interval between two heart beats, and the minimum of P and R waves.
  • Interval is used to subdivide the classification information after heartbeat classification; mainly based on the inter-heart rate RR interval and the medical saliency of different heartbeat signals on each lead; the heartbeat review module is based on the electrocardiogram
  • the basic rule reference data combined with the classification and recognition of a plurality of continuous heartbeat analysis data, and the detailed feature information of the P wave and the T wave, the ventricular heart beat classification is divided into finer heart beat classification, including: ventricular premature beat (V) , ventricular escape (VE), accelerated ventricular premature beats (VT), subventricular subtypic breakdown into supraventricular premature beats (S), atrial escape (SE), borderline escape (JE ) and atrial accelerated premature beats (AT) and so on.
  • V ventricular premature beat
  • VE ventricular escape
  • VT accelerated ventricular premature beats
  • S supraventricular premature beats
  • SE atrial escape
  • JE borderline escape
  • AT atrial accelerated premature beats
  • the secondary classification process it is also possible to correct the misclassification identification of the reference data that does not conform to the basic rule of the electrocardiogram occurring in one classification.
  • the subdivided heart beats are classified according to the reference data of the basic rules of the electrocardiogram, and the classification and identification which does not conform to the basic rule of the electrocardiogram are found, and the classification is corrected according to the RR interval and the classification marks before and after.
  • a variety of heartbeat classifications can be output, such as: normal sinus beat (N), complete right bundle branch block (N_CRB), complete left bundle branch block (N_CLB), indoor resistance Hysteresis (N_VB), first degree atrioventricular block (N_B1), pre-excitation (N_PS), premature ventricular contraction (V), ventricular escape (VE), accelerated ventricular premature beat (VT), supraventricular premature beats ( S), atrial escape (SE), borderline escape (JE), accelerated atrial premature beats (AT), atrial flutter (AF), artifacts (A) and other classification results.
  • N normal sinus beat
  • N_CRB complete right bundle branch block
  • N_CLB complete left bundle branch block
  • N_VB indoor resistance Hysteresis
  • N_PS first degree atrioventricular block
  • V premature ventricular contraction
  • VE ventricular escape
  • VT accelerated ventricular premature beat
  • S supraventricular premature beats
  • SE atrial escape
  • JE borderline escape
  • AF accelerated
  • the heart rate parameters of the basic calculation include: RR interval, heart rate, QT time, QTc time and other parameters.
  • the pattern matching is performed according to the basic rule of the electrocardiogram, and the following typical ECG events corresponding to the ECG event data can be obtained, including but not limited to:
  • Second degree type II (2:1) atrioventricular block
  • Step 1211 The heartbeat analysis data is generated according to the heartbeat classification information and the electrocardiogram basic rule reference data, and the electrocardiogram event data is filtered according to the signal quality evaluation parameter, and the report conclusion data and the report item data are obtained; according to each electrocardiogram A typical piece of data in the event data that generates report graph data.
  • the untrustworthy events in the ECG event data are eliminated, various heart rate parameters are calculated, the number of events and the time of occurrence are counted, and the report conclusion data and the report item data are obtained.
  • the heart rate parameter calculation includes calculating an average heart rate, and maximum and minimum heart rate.
  • the maximum and minimum heart rate the fixed-length segment is used as the statistical unit, and the whole process scan and statistical comparison are performed one by one.
  • the length of the clip is generally 8-10 seconds, and can be freely set as needed.
  • the statistical calculation method for the heart rate of the sinus heart rate and the ectopic heart rate is different.
  • the maximum and minimum heart rate for the sinus heart rate in the main electrocardiogram, only the sinus classification heart rate is calculated; for the atrial flutter atrial fibrillation main body ECG, only the atrial flutter atrial fibrillation heartbeat and sinus beats are calculated; Other ectopic beats of atrial fibrillation accounted for the main electrocardiogram, and all types of heart beats were involved in calculations except for artifacts.
  • the quality evaluation is performed according to the signal quality evaluation parameters, and the event fragment with the highest quality of the data signal is selected, and the number of event types included in the segment is analyzed, and the most representative segment is preferentially selected, and the starting position of the segment is preferred.
  • the event heartbeat is guaranteed to be in the middle of the selected segment to generate report graphic data.
  • the selection rule of the electrocardiogram event can be specifically as follows:
  • the segment starting point position is 0.3 second from the first heartbeat distance.
  • the starting position of the segment is 0.37 seconds away from the first heartbeat distance.
  • the interference-free signal ratio reaches the set threshold (preferably at 60%)
  • the threshold is determined in the -95% range, and the segment meets the screening conditions from which the optimal typical data segment is obtained.
  • the report conclusion data, the report table item data, and the report graphic data are associated and stored as report data. Therefore, when the query is invoked, various report data related to the measured object ID can be directly obtained according to the measured object ID.
  • the report data also includes the detection time information of the report data. This information should include at least information on the acquisition time/time period of the ECG data, and may also include the time at which the report data was last updated. This time can also be recorded because it is possible to modify the report data.
  • Step 130 Receive a report data query instruction input by the user, query the corresponding report data according to the user ID of the user, and generate report data query result list data, and display and output;
  • the ECG workstation can provide a human-computer interaction interface to the user, and through the human-computer interaction interface, the user can log in and query the report data.
  • the ECG workstation When the user logs in, the ECG workstation performs permission verification according to the login information of the user, and performs data query authority management according to the user ID corresponding to the user authority information to obtain corresponding report data. Then, the report data is extracted, and the report data query result list data is obtained and output.
  • the report data query result list data includes at least the object ID and the detection time information of the one or more report data obtained by the query.
  • the ECG workstation obtains the ID of the patient in the department according to the authority, and queries and matches all the tested objects according to the ID of the patient.
  • ID the report data of the patient who has the authority to consult the attending doctor, preferably may be the report data within the set time period.
  • the report data is extracted, at least the measured object ID and the detection time information are extracted, and the report data query result list data is generated, and is preferably displayed in a list manner on the human-computer interaction interface of the ECG workstation.
  • the object ID to be measured may specifically be a name or a patient file number.
  • the order in which the lists are displayed may be arranged in the order of the object IDs to be measured, or in the order of the detection time information/in reverse order.
  • the ECG workstation acquires report data of all or the set time period related to the patient ID according to the authority.
  • the report data is extracted, at least the measured object ID and the detection time information are extracted, and the report data query result list data is generated, and displayed in a list manner on the human-computer interaction interface of the electrocardiographer.
  • Step 140 Receive a selection instruction input by a user, and acquire the selected report data according to the selection instruction;
  • the user performs selection input through the human-computer interaction interface to determine the report data to be selected.
  • a single query result may be selected from the report data query result list data to obtain a corresponding report data.
  • report data query result list data may be selected from the report data query result list data to obtain corresponding report data at one time. This simplifies the operation.
  • the user can be operated with authority management.
  • the user category information of the user can be set, for example, for a doctor, a general worker, a patient, etc., and the permissions of different types of users are set to be different.
  • the report data can be queried, modified, downloaded, forwarded, etc., and if it is an ordinary staff member or patient, the report data can only be queried and printed.
  • an output (step 150 described below), a modification (step 160 described below), and the like can be performed on the report data.
  • Step 150 Receive a report output instruction input by the user, determine output mode information and output format information according to the report output instruction, and selectively output the report conclusion data, the report item data, and/or the part of the report graphic data according to the output mode information. Data or all data, and according to the output format information, part or all of the data is converted into a data format to generate report output data.
  • the ECG workstation acquires the selected report data according to the user's selection instruction, and outputs the mode information and the report output format according to the report.
  • the output of the information response reports the output data.
  • the ECG workstation obtains report output mode information and output format information.
  • the report output mode information refers to which format the report is output, and can have different report output modes according to different user rights.
  • the user category information is the user of the patient, and only the set partial data in the report data is output.
  • the report output mode also includes the way the output is presented. Different report output modes are shown in Figures 7a-7c and 8a-8g, respectively, wherein Figures 7a-7c are a report output mode for static ECG monitoring data, and Figures 8a-8g are a dynamic ECG detection data.
  • the report output mode allows the user to input or select the corresponding report output mode information as needed to enable the ECG workstation to output the report data of the corresponding output mode.
  • the output format information of the report may be an output format selected according to different uses, for format conversion of the report data, conversion to the required data format, and output.
  • Specific formats may include: Extensible Markup Language (XML), Standard Communication Protocol (SCP) for ECG Data Recording and Transmission, Portable Document Format (PDF), Joint Photographic Experts Group (JPEG), Medical Digital Imaging and Communications (DICOM) 3.0
  • PDF Portable Document Format
  • JPEG Joint Photographic Experts Group
  • DIOM Medical Digital Imaging and Communications
  • the default report output mode information and output format information are pre-set in the ECG workstation.
  • the ECG workstation can convert the report data into report output data for output according to the default format.
  • the output of the report output data is output on the human-computer interaction interface of the ECG workstation, and the printer integrated or connected to the ECG workstation performs print output.
  • Step 160 Receive report conclusion modification data and/or report table item modification data input by the user; modify the data update report conclusion data according to the report conclusion, and modify the data update report table item data according to the report entry.
  • the report data can also be modified through the ECG workstation. This includes specific changes to the conclusions of the report and modifications to the test data. In practical applications, this function is mainly open to doctors.
  • the report data is first acquired and displayed through the human-computer interaction interface. At this time, the format of the report data is in a readable and writable format.
  • the user After the user determines the content to be modified according to the report data, the user receives the deletion of part of the data in the original report data through the interpersonal interaction interface, and records the newly input data of the user, where the report conclusion data and the report item data may be specifically included in the After receiving the input data update command, the original report data is updated according to the data input by the user. Preferably, a record is generated in the report data, and the time at which the corresponding data is updated and the user ID at which the operation is performed are recorded.
  • FIG. 6 is a schematic structural diagram of an ECG workstation according to an embodiment of the present invention, where the ECG workstation includes: a processor and a memory.
  • the memory can be connected to the processor via a bus.
  • the memory may be a non-volatile memory such as a hard disk drive and a flash memory in which software programs and device drivers are stored.
  • the software program can perform various functions of the above method provided by the embodiments of the present invention; the device driver can be a network and an interface driver.
  • the processor is configured to execute a software program, and when the software program is executed, the method provided by the embodiment of the present invention can be implemented.
  • the embodiment of the present invention further provides a computer readable storage medium.
  • the computer readable storage medium stores a computer program, and when the computer program is executed by the processor, the method provided by the embodiment of the present invention can be implemented.
  • Embodiments of the present invention also provide a computer program product comprising instructions.
  • the processor is caused to perform the above method.
  • the method and device for processing ECG information based on artificial intelligence self-learning provided by the embodiments of the present invention, through data preprocessing, heartbeat feature detection, interference signal detection, signal quality assessment and guidance combined, heart beat classification, heart beat audit The secondary classification, the ECG event classification and the analysis and calculation of the ECG parameters, and finally the automatic analysis method of a complete fast process of automatically outputting the report data.
  • the automatic analysis method of the invention can also record the modification information of the automatic analysis result, and collect the modified data feedback to the deep learning model to continue training, and continuously improve and improve the accuracy of the automatic analysis method.
  • the steps of a method or algorithm described in connection with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both.
  • the software module can be placed in random access memory (RAM), memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or technical field. Any other form of storage medium known.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Cardiology (AREA)
  • Physics & Mathematics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Pathology (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • Physiology (AREA)
  • Signal Processing (AREA)
  • Psychiatry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • General Business, Economics & Management (AREA)
  • Business, Economics & Management (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

一种心电信息处理方法和心电工作站，方法包括：心电工作站接收心电监测设备输出的心电图数据，心电图数据包括被测对象ID和检测时间信息（110）；对心电图数据进行心电数据分析，生成报告数据并进行存储（120）；接收用户输入的报告数据查询指令，根据用户的用户ID查询相应的报告数据，并生成报告数据查询结果列表数据（130）；根据选择指令获取被选择的报告数据（140），根据报告输出指令确定输出模式信息和输出格式信息，并且，根据输出模式信息选择性输出报告结论数据、报告表项数据和/或报告图形数据中的部分数据或全部数据，以及根据输出格式信息，将部分数据或全部数据进行数据格式转换，生成报告输出数据（150）。

Description

心电信息处理方法和心电工作站
本申请要求于2018年2月24日提交中国专利局、申请号为201810157365.3、发明名称为“心电信息处理方法和心电工作站”的中国专利申请的优先权。
技术领域
本发明涉及数据处理技术领域，尤其涉及一种心电信息处理方法和心电工作站。
背景技术
心电工作站是将人体弱小的心电信号由心电采集器采集，送入计算机处理系统放大、分析处理，从而达到诊断心脏疾病的目的，通常由计算机主机、监视器、导联线、心电信号采集盒和打印机等几部分组成，具有视窗菜单，不需要深奥的操作技术和过多的人工干预，临床医生或操作人员即可以通过它获得心电图输出报告。
心电工作站所执行的心电监测是一种常用的临床医疗监测手段。其监测的心电信号是心肌细胞的电活动在体表反映出的微弱电流，通过体表电极和放大记录系统记录下来。
在心电监测中涉及心电图数据自动分析，但由于心电图信号本身的复杂与变异性，很容易受到各种信号干扰，在记录过程中同时还会记录到其他非心源性的电信号，比如骨骼肌活动带来的肌电信号干扰等等。这些信号可能会导致不正确心搏信号检测结果的输出。
此外，心电信号是心肌电活动过程的体现，可以体现出大量的心脏状态 的信息。在心脏状态出现问题的时候，心电信号会出现相应的改变，目前自动分析的准确率远远不够，致使输出的心电图检测报告的参考意义不大，还是依然依赖于医生的主观判断来形成心电图检测报告。
此外，现有心电工作站的心电图检测报告输出方式单一，无法满足不同用户或不同使用需求的差异化要求。因而如何有效提高心电图的自动分析水平，并智能化的生成和输出分析数据以及满足多方位的需求，是本发明所要解决的难题和挑战。
发明内容
本发明为实现上述目的，提出了一种心电信息处理方法和心电工作站，通过对心电监测设备输出的心电图数据进行完整快速的自动分析，形成报告数据；能够对报告数据进行查询，按照请求或设定的输出模式和数据格式输出报告数据，并支持对报告数据的更新和修改。
本发明实施例第一方面提供了一种心电信息处理方法，包括：
心电工作站接收心电监测设备输出的心电图数据，所述心电图数据包括被测对象ID和检测时间信息；
对所述心电图数据进行心电数据分析，生成报告数据并进行存储；所述报告数据包括：所述被测对象ID对应的报告结论数据、报告表项数据和/或报告图形数据；
接收用户输入的报告数据查询指令，根据所述用户的用户ID查询相应的报告数据，并生成报告数据查询结果列表数据，进行显示输出；所述报告数据查询结果列表数据至少包括查询得到的一个或多个所述报告数据的被测对象ID和检测时间信息；
接收用户输入的选择指令，根据所述选择指令获取被选择的报告数据；
接收用户输入的报告输出指令，根据所述报告输出指令确定输出模式信息和输出格式信息，并且，根据所述输出模式信息选择性输出所述报告结论 数据、报告表项数据和/或报告图形数据中的部分数据或全部数据，以及根据所述输出格式信息，将所述部分数据或全部数据进行数据格式转换，生成报告输出数据。
优选的，在所述接收用户输入的选择指令，根据所述选择指令获取被选择的报告数据之后，所述方法还包括：
接收用户输入的报告结论修改数据和/或报告表项修改数据；
根据所述报告结论修改数据更新所述报告结论数据，根据所述报告表项修改数据更新所述报告表项数据。
优选的，所述心电图数据为单导联或多导联的时间序列数据；所述对所述心电图数据进行心电数据分析，生成报告数据具体包括：
将所述心电图数据的数据格式经过重采样转换为预设标准数据格式，并对转换后的预设标准数据格式的心电图数据进行第一滤波处理；
对所述第一滤波处理后的心电图数据进行心搏检测处理，识别所述心电图数据包括的多个心搏数据；每个所述心搏数据对应一个心搏周期，包括相应的P波、QRS波群、T波的幅值数据和起止时间数据；
根据训练得到的干扰识别二分类模型对所述心搏数据进行干扰识别，确定所述心搏数据是否存在干扰噪音，以及用于判断干扰噪音的一个概率值；
根据心搏数据的导联参数和所述心搏数据，基于所述干扰识别的结果和时间规则合并生成心搏时间序列数据；根据所述心搏时间序列数据生成心搏分析数据；
对所述心搏分析数据进行信号质量分析，评估所述心搏分析数据的信号质量，得到所述心搏分析数据的信号质量评价参数；
根据训练得到的心搏分类模型对所述心搏分析数据进行幅值和时间表征数据的特征提取和分析，得到所述心搏分析数据的一次分类信息；
对所述一次分类信息结果中的特定心搏的心搏分析数据输入到训练好的ST段和T波改变模型进行识别，确定ST段和T波评价信息；
根据心搏时间序列数据，对心搏分析数据进行P波和T波特征检测，确定每个心搏中P波和T波的详细特征信息；
对所述心搏分析数据在所述一次分类信息下根据所述心电图基本规律参考数据、P波和T波的详细特征信息以及所述ST段和T波评价信息进行二次分类处理，得到心搏分类信息；
将所述心搏分析数据根据所述心搏分类信息和心电图基本规律参考数据生成心电图事件数据；根据所述信号质量评价参数对心电图事件数据进行筛选，得到所述报告结论数据和报告表项数据；根据每种心电图事件数据中的典型数据片段，生成所述报告图形数据。
进一步优选的，对所述第一滤波处理后的心电图数据进行心搏检测处理还包括：
根据所述QRS波群确定RR间期并计算所述RR间期内噪声的估计值；
根据所述噪声的估计值和每个QRS波群中的最大幅值确定每个QRS波群的检测置信度。
进一步优选的，所述根据训练得到的干扰识别二分类模型对所述心搏数据进行干扰识别，具体包括：
以第一数据量对所述心搏数据进行切割采样，并将切割采样得到的数据输入到干扰识别二分类模型进行干扰识别；
识别心搏数据中，心搏间期大于等于预设间期判定阈值的数据片段；
对所述心搏间期大于等于预设间期判定阈值的数据片段进行信号异常判断，确定是否为异常信号；
如果不是异常信号，则以预设时间宽度，根据设定时值确定所述数据片段中滑动取样的起始数据点和终止数据点，并由所述起始数据点开始对所述数据片段进行滑动取样，至所述终止数据点为止，得到多个取样数据段；
对每个所述取样数据段进行所述干扰识别。
进一步优选的，所述对所述一次分类信息结果中的特定心搏的心搏分析 数据输入到训练好的ST段和T波改变模型进行识别，确定ST段和T波评价信息，具体包括：
将所述一次分类信息中的特定心搏数据，按导联依次输入到根据训练得到的ST段和T波改变模型，对各导联的特定心搏数据进行幅值和时间表征数据的特征提取和分析，得到各导联的ST段和T波改变信息，确定ST段和T波评价信息；所述ST段和T波评价信息具体为所述心搏片段数据对应的ST段和T波发生改变的导联位置信息。
进一步优选的，所述根据每种心电图事件数据中的典型数据片段，生成报告图形数据，具体包括：
根据所述信号质量评价参数，对每种心电图事件的数据片段进行评估，选择信号质量评价参数最高的数据片段为所述心电图事件中的典型数据片段。
本发明实施例提供的心电信息处理方法，通过对心电监测设备输出的心电图数据进行完整快速的自动分析，形成报告数据；能够对报告数据进行查询，按照请求或设定的输出模式和数据格式输出报告数据，并支持对报告数据的更新和修改。
本发明实施例第二方面提供了一种心电工作站，该设备包括存储器和处理器，存储器用于存储程序，处理器用于执行第一方面及第一方面的各实现方式中的方法。
本发明实施例第三方面提供了一种包含指令的计算机程序产品，当计算机程序产品在计算机上运行时，使得计算机执行第一方面及第一方面的各实现方式中的方法。
本发明实施例第四方面提供了一种计算机可读存储介质，计算机可读存储介质上存储有计算机程序，计算机程序被处理器执行时实现第一方面及第一方面的各实现方式中的方法。
附图说明
图1为本发明实施例提供的心电信息处理方法的流程图；
图2为本发明实施例提供的心电图数据的处理方法的流程图；
图3为本发明实施例提供的干扰识别二分类模型的示意图；
图4为本发明实施例提供的心搏分类模型的示意图；
图5为本发明实施例提供的ST段和T波改变模型的示意图；
图6为本发明实施例提供的心电工作站的结构示意图；
图7a-图7c为本发明实施例提供的一种静态心电监测数据的报告输出模式；
图8a-图8g为本发明实施例提供的一种动态心电监测数据的报告输出模式。
具体实施方式
下面通过附图和实施例，对本发明的技术方案做进一步的详细描述。
心电工作站是将采集到的人体弱小的心电信号送入计算机处理系统放大、分析处理，从而达到心电检查、监护的目的。心电信号是心肌细胞的电活动在体表反映出的微弱电流，通过体表电极和放大记录系统记录下来。
本发明就是基于记录的心电信号，进行完整快速的自动分析形成报告数据；并建立了对报告数据进行查询、按请求或设定的输出模式和数据格式输出、以及对报告数据的更新和修改的机制。
下面首先结合图1所示的心电信息处理方法的流程图，对本发明的心电信息处理方法进行详述。
如图1所示，本发明的心电信息处理方法主要包括如下步骤：
步骤110，心电工作站接收心电监测设备输出的心电图数据；
具体的，心电监测设备具体可以是单导联或多导联的心电监测仪，每台心电检测设备都有唯一的设备ID，从而能够对测得的数据进行标记，以表明 该数据是由哪台设备获得的。
心电工作站在本发明中是指具有心电图数据分析处理功能的且能够提供用户进行信息交互的设备，能够实现数据传输、用户管理和数据管理以及心电图数据的报告输出管理等功能。
它与心电监测设备可以集成于一体，也可以是二者通过有线方式或无线网络进行连接进行数据传输。其中无线网络包括无线但不限于基于IEEE802.11b标准的无线局域网(WIFI)，蓝牙，3G/4G/5G移动通信网络，物联网等方式。在本实施例中的心电监测设备，侧重于心电信号采集的功能实现，输出心电图数据由心电工作站进行处理。
心电监测设备通过无创心电图检查的方式对心脏细胞电生理活动产生的信号以单导联或多导联的形式进行采集记录，得到心电图数据发送到心电工作站。心电图数据中包括被测对象ID、心电检测设备的设备ID和检测时间信息。
步骤120，对心电图数据进行心电数据分析，生成报告数据并进行存储；
考虑到在心电信号的记录过程中同时还会记录到其他非心源性的电信号，比如骨骼肌活动带来的肌电信号干扰等等，因此我们认为需要对心电信号进行有效的干扰识别和排除，才能够有效降低因为干扰信号造成的误报。
此外，心电信号是心肌电活动过程的体现，因此心电信号除了可以用来检测心率以外，还可以体现出大量的心脏状态的信息。在心脏状态出现问题的时候，心电信号会出现相应的改变。在对业内现有的心电信号处理方法的研究中我们发现，目前只对心电信号进行了非常有限的分析和报警。对此，除了对心电信号进行有效的干扰识别和排除，以降低因为干扰信号造成的误报之外，我们认为还可以从以下几点进行改进：
第一，在心搏特征提取中需要对P波、T波进行准确识别，可以避免心搏检测的多检和漏检，比如对一些特殊心电图信号，例如心律比较缓慢患者的高大T波，或者T波肥大的信号的多检。
第二，对心搏的分类进行更加细致的划分，而不能仅停留在窦性、室上性和室性这三种分类，从而满足临床心电图医生复杂全面的分析要求。
第三，准确识别房扑房颤和ST-T改变，从而能够有助于提供对ST段和T波改变对心肌缺血分析的帮助。
第四，对心搏和心电事件的准确识别。
在本发明中，我们针对上述几点，通过对心电图数据的分析计算，特别是引入人工智能(AI)技术，对采集的数字信号进行心律失常分析、长间歇停搏，扑动和颤动，传导阻滞，早搏和逸搏，心动过缓，心动过快，ST段改变检测、心电事件的分析与归类，以达到产生准确报警信号的目的，从而有效的进行病人生命体征的监护。
基于上述几点，本发明的心电图数据的处理过程，采用了基于人工智能自学习的心电图自动分析方法，是基于人工智能卷积神经网络(CNN)模型来实现的。CNN模型是深度学习中的监督学习方法，就是一个模拟神经网络的多层次网络(隐藏层hidden layer)连接结构，输入信号依次通过每个隐藏层，在其中进行一系列复杂的数学处理(Convolution卷积、Pooling池化、Regularization正则化、防止过拟合、Dropout暂时丢弃、Activation激活、一般使用Relu激活函数)，逐层自动地抽象出待识别物体的一些特征，然后把这些特征作为输入再传递到高一级的隐藏层进行计算，直到最后几层的全连接层(Full Connection)重构整个信号，使用Softmax函数进行逻辑(logistics)回归，达到多目标的分类。
CNN属于人工智能中的监督学习方法，在训练阶段，输入信号经过多个的隐藏层处理到达最后的全连接层，softmax逻辑回归得到的分类结果，与已知的分类结果(label标签)之间会有一个误差，深度学习的一个核心思想就是通过大量的样本迭代来不断地极小化这个误差，从而计算得到连接各隐藏层神经元的参数。这个过程一般需要构造一个特别的损失函数(cost function)，利用非线性优化的梯度下降算法和误差反向传播算法 (backpropagation algorithm，BP)，快速有效地极小化整个深度(隐藏层的层数)和广度(特征的维数)都十分复杂的神经网络结构中所有连接参数。
深度学习把需要识别的数据输入到训练模型，经过第一隐藏层、第二隐藏层、第三隐藏层，最后是输出识别结果。
在本发明中，对心电图数据进行波群特征识别、干扰识别、心搏分类等都是基于人工智能自学习的训练模型来得到输出结果，分析速度快，准确程度高。
具体的，该步骤通过对心电图数据进行波群特征识别，得到心电图数据的特征信号，根据特征信号对心电图数据进行心搏分类，结合心电图基本规律参考数据得到心搏分类信息，根据心搏分类信息处理生成心电图事件数据，并最终生成报告数据来实现。进一步的，该过程具体可以通过如图2所示的如下步骤来实现。
步骤1201，将心电图数据的数据格式经过重采样转换为预设标准数据格式，并对转换后的预设标准数据格式的心电图数据进行第一滤波处理；
具体的，心电图数据的格式适配读取，对不同的设备有不同的读取实现，读取后，需要调整基线、根据增益转换成毫伏数据。经过数据重采样，把数据转换成全流程能够处理的采样频率。然后通过滤波去除高频，低频的噪音干扰和基线漂移，提高人工智能分析准确率。将处理后的心电图数据以预设标准数据格式保存。
通过本步骤解决不同在使用不同导联，采样频率和传输数据格式的差异，以及通过数字信号滤波去除高频，低频的噪音干扰和基线漂移。
数字信号滤波可以分别采用高通滤波器，低通滤波器和中值滤波，把工频干扰、肌电干扰和基线漂移干扰消除，避免对后续分析的影响。
更具体的，可以采用低通、高通巴特沃斯滤波器进行零相移滤波，以去除基线漂移和高频干扰，保留有效的心电信号；中值滤波则可以利用预设时长的滑动窗口内数据点电压幅值的中位数替代窗口中心序列的幅值。可以去 除低频的基线漂移。
步骤1202，对第一滤波处理后的心电图数据进行心搏检测处理，识别心电图数据包括的多个心搏数据；
每个心搏数据对应一个心搏周期，包括相应的P波、QRS波群、T波的幅值和起止时间数据。本步骤中的心搏检测由两个过程构成，一是信号处理过程，从所述第一滤波处理后的心电图数据中提取QRS波群的特征频段；二是通过设置合理的阈值确定QRS波群的发生时间。在心电图中，一般会包含P波、QRS波群、T波成分以及噪声成分。一般QRS波群的频率范围在5到20Hz之间，可以通过一个在此范围内的带通滤波器提出QRS波群信号。然而P波、T波的频段以及噪声的频段和QRS波群频段有部分重叠，因此通过信号处理的方法并不能完全去除非QRS波群的信号。因此需要通过设置合理的阈值来从信号包络中提取QRS波群位置。具体的检测过程是一种基于峰值检测的过程。针对信号中每一个峰值顺序进行阈值判断，超过阈值时进入QRS波群判断流程，进行更多特征的检测，比如RR间期、形态等。
在心电信息的记录过程中心搏信号的幅度和频率时时刻刻都在变化，并且在疾病状态下，这种特性会表现的更强。在进行阈值设定时，需要根据数据特征在时域的变化情况动态的进行阈值调整。为了提高检测的准确率和阳性率，QRS波群检测大多采用双幅度阈值结合时间阈值的方式进行，高阈值具有更高的阳性率，低阈值具有更高的敏感率，在RR间期超过一定时间阈值，使用低阈值进行检测，减少漏检情况。而低阈值由于阈值较低，容易受到T波、肌电噪声的影响，容易造成多检，因此优先使用高阈值进行检测。
对于不同导联的心搏数据都具有导联参数，用以表征该心搏数据为哪个导联的心搏数据。因此在得到心电图数据的同时也就可以根据其传输来源确定了其导联的信息，将此信息作为心搏数据的导联参数。
步骤1203，根据心搏数据确定每个心搏的检测置信度；
具体的，置信度计算模块在心搏检测的过程中，根据QRS波群的幅度以及 RR间期内噪声信号的幅度比例可以提供针对QRS波群检测置信度的估计值。
步骤1204，根据干扰识别二分类模型对心搏数据进行干扰识别，得到心搏数据是否存在干扰噪音，以及用于判断干扰噪音的一个概率值；
因为在长时间记录过程中易受多种影响出现干扰现象，导致获取的心搏数据无效或不准确，不能正确反映受测者的状况，同时也增加医生诊断难度及工作量；而且干扰数据也是导致智能分析工具无法有效工作的主要因素。因此，将外界信号干扰降到最低显得尤为重要。
本步骤基于以深度学习算法为核心的端到端二分类识别模型，具有精度高，泛化性能强的特点，可有效地解决电极片脱落、运动干扰和静电干扰等主要干扰来源产生的扰动问题，克服了传统算法因干扰数据变化多样无规律而导致的识别效果差的问题。
具体可以通过如下方法来实现：
步骤A，对心搏数据使用干扰识别二分类模型进行干扰识别；
步骤B，识别心搏数据中，心搏间期大于等于预设间期判定阈值的数据片段；
步骤C，对心搏间期大于等于预设间期判定阈值的数据片段进行信号异常判断，确定是否为异常信号；
其中，异常信号的识别主要包括是否为电极片脱落、低电压等情况。
步骤D，如果不是异常信号，则以预设时间宽度，根据设定时值确定数据片段中滑动取样的起始数据点和终止数据点，并由起始数据点开始对数据片段进行滑动取样，至终止数据点为止，得到多个取样数据段；
步骤E，对每个取样数据段进行干扰识别。
以一个具体的例子对上述步骤A-E进行说明。对每个导联的心搏数据以设定的第一数据量进行切割采样，然后分别输入到干扰识别二分类模型进行分类，获得干扰识别结果和对应结果的一个概率值；对心搏间期大于等于2秒的心搏数据，先判断是否是信号溢出，低电压，电极脱落；如果不是上述 情况，就按照第一数据量，从左边心搏开始，向右连续以第一数据量不重叠滑动取样，进行识别。
输入可以是任一导联的第一数据量心搏数据，然后采用干扰识别二分类模型进行分类，直接输出是否为干扰的分类结果，获得结果快，精确度高，稳定性好，可为后续分析提供更有效优质的数据。
因为干扰数据往往是由外界扰动因素的作用而引起的，主要有电极片脱落、低电压、静电干扰和运动干扰等情况，不但不同扰动源产生的干扰数据不同，而且相同扰动源产生的干扰数据也是多种多样；同时考虑到干扰数据虽然多样性布较广，但与正常数据的差异很大，所以在收集干扰的训练数据时也是尽可能的保证多样性，同时采取移动窗口滑动采样，尽可能增加干扰数据的多样性，以使模型对干扰数据更加鲁棒，即使未来的干扰数据不同于以往任何的干扰，但相比于正常数据，其与干扰的相似度也会大于正常数据，从而使模型识别干扰数据的能力增强。
本步骤中采用的干扰识别二分类模型可以如图3所示，网络首先使用2层卷积层，卷积核大小是1x5,每层后加上一个最大值池化。卷积核数目从128开始，每经过一次最大池化层，卷积核数目翻倍。卷积层之后是两个全连接层和一个softmax分类器。由于该模型的分类数为2，所以softmax有两个输出单元，依次对应相应类别，采用交叉熵做为损失函数。
对于该模型的训练，我们采用了来源于30万病人近400万精确标注的数据片段。标注分为两类：正常心电图信号或者是有明显干扰的心电图信号片段。我们通过定制开发的工具进行片段标注，然后以自定义标准数据格式保存干扰片段信息。
在训练过程，使用两台GPU服务器进行几十次轮循训练。在一个具体的例子中，采样率是200Hz，数据长度是300个心电图电压值(毫伏)的一个片段D[300]，输入数据是：InputData(i，j),其中，i是第i个导联，j是导联i第j个片段D。输入数据全部经过随机打散才开始训练，保证了训练过 程收敛，同时，控制从同一个病人的心电图数据中收集太多的样本，提高模型的泛化能力，既真实场景下的准确率。训练收敛后，使用100万独立的测试数据进行测试，准确率可以到达99.3％。另有具体测试数据如下表1。
  干扰 正常
敏感率(Sensitivity) 99.14％ 99.32％
阳性预测率(Positive Predicitivity) 96.44％ 99.84％
表1
步骤1205，根据检测置信度确定心搏数据的有效性，并且，根据确定有效的心搏数据的导联参数和心搏数据，基于干扰识别的结果和时间规则合并生成心搏时间序列数据，并根据心搏时间序列数据生成心搏分析数据；
具体的，由于心电图信号的复杂性以及每个导联可能受到不同程度的干扰影响，依靠单个导联检测心搏会存在多检和漏检的情况，不同导联检测到心搏结果的时间表征数据没有对齐，所以需要对所有导联的心搏数据根据干扰识别结果和时间规则进行合并，生成一个完整的心搏时间序列数据，统一所有导联心搏数据的时间表征数据。其中，时间表征数据用于表示每个数据点在心电图数据信号时间轴上的时间信息。根据这个统一的心搏时间序列数据，在后续的分析计算时，可以使用预先设置好的阀值，对各导联心搏数据进行切割，从而生成具体分析需要的各导联的心搏分析数据。
上述每个导联的心搏数据在合并前，需要根据步骤1203中获得的检测置信度确定心搏数据的有效性。
具体的，导联心搏合并模块执行的心搏数据合并过程如下：根据心电图基本规律参考数据的不应期获取不同导联心搏数据的时间表征数据组合，丢弃其中偏差较大的心搏数据，对上述时间表征数据组合投票产生合并心搏位置，将合并心搏位置加入合并心搏时间序列，移动到下一组待处理的心搏数据，循环执行直至完成所有心搏数据的合并。
其中，心电图活动不应期可以优选在200毫秒至280毫秒之间。获取的不同导联心搏数据的时间表征数据组合应满足以下条件：心搏数据的时间表征 数据组合中每个导联最多包含一个心搏数据的时间表征数据。在对心搏数据的时间表征数据组合进行投票时，使用检出心搏数据的导联数占有效导联数的百分比来决定；若心搏数据的时间表征数据对应导联的位置为低电压段、干扰段以及电极脱落时认为该导联对此心搏数据为无效导联。在计算合并心搏具体位置时，可以采用心搏数据的时间表征数据平均值得到。在合并过程中，本方法设置了一个不应期来避免错误合并。
在本步骤中，通过合并操作输出一个统一的心搏时间序列数据。该步骤同时能够降低心搏的多检率和漏检率，有效的提高心搏检测的敏感度和阳性预测率。
步骤1206，对心搏分析数据进行信号质量分析，评估心搏分析数据的信号质量，得到心搏分析数据的信号质量评价参数。
如果监测的心电图数据是静态心电图数据，那么信号质量会相对较好，有效信号的比例比较高，这种情况下可以不用进行信号质量评估。而如果监测的是动态心电图数据，则在监测过程中会发生各种扰动，导致无效信号的产生会相对较多，为了避免无效信号影响最终的结果计算，需要进行信号质量评估，降低无效信号对最终结果的影响。
具体的，通过提取心搏分析数据中的RR间期信号，对RR间期信号进行第二滤波处理和包络计算，确定噪声信号强度，并计算相对于相应的心搏时间序列数据的最大振幅的信号噪声比，确定信号质量评价参数。其具体步骤可以包括：
步骤A，提取心搏分析数据中QRS波群的位置信息和宽度信息；
步骤B，提取相邻两个QRS波群信号之间的RR间期的信号；
步骤C，对RR间期的信号进行滤波处理，并对滤波处理后的信号进行包络计算，得到RR间期的噪声信号的平均功率；其中，RR间期的噪声信号的平均功率为RR间期内包络幅度的均值。
步骤D，根据噪声信号的平均功率和QRS波群信号的功率得到信号质量评 价参数；
进一步具体的，信号质量评价参数可以由RR间期内相对于QRS波群的噪声水平来表示。具体通过根据QRS波群的功率和噪声信号的平均功率计算得到。
以公式表示为：
Figure PCTCN2018083466-appb-000001
其中，S i为第i个QRS波群信号的幅度，N i,t为第i个RR间期区间内第t个样本点的幅值，T为RR间期长度。
步骤1207，根据心搏分类模型对心搏分析数据进行幅值和时间表征数据的特征提取和分析，得到心搏分析数据的一次分类信息；
具体的，该步骤在步骤1205之后执行。不同心电监测设备在信号测量、采集或者输出的导联数据等方面存在的差异，因此可以根据具体情况，使用简单的单导联分类方法，或者是多导联分类方法。多导联分类方法又包括导联投票决策分类方法和导联同步关联分类方法两种。导联投票决策分类方法是基于各导联的心搏分析数据进行导联独立分类，再把结果投票融合确定分类结果的投票决策方法；导联同步关联分类方法则采用对各导联的心搏分析数据进行同步关联分析的方法。单导联分类方法就是对单导联设备的心搏分析数据，直接使用对应导联模型进行分类，没有投票决策过程。下面对以上所述几种分类方法分别进行说明。
单导联分类方法包括：
根据心搏时间序列数据，将单导联心搏数据进行切割生成单导联的心搏分析数据，并输入到训练得到的对应该导联的心搏分类模型进行幅值和时间表征数据的特征提取和分析，得到单导联的一次分类信息。
导联投票决策分类方法可以具体包括：
第一步、根据心搏时间序列数据，对各导联心搏数据进行切割，从而生成各导联的心搏分析数据；
第二步、根据训练得到的各导联对应的心搏分类模型对各导联的心搏分析数据进行幅值和时间表征数据的特征提取和分析，得到各导联的分类信息；
第三步、根据各导联的分类信息和导联权重值参考系数进行分类投票决策计算，得到所述一次分类信息。具体的，导联权重值参考系数是基于心电数据贝叶斯统计分析得到各导联对不同心搏分类的投票权重系数。
导联同步关联分类方法可以具体包括：
根据心搏时间序列数据，对各导联心搏数据进行切割，从而生成各导联的心搏分析数据；然后根据训练得到的多导联同步关联分类模型对各导联的心搏分析数据进行同步幅值和时间表征数据的特征提取和分析，得到心搏分析数据的一次分类信息。
心搏数据的同步关联分类方法输入是动态心电图设备所有导联数据，按照心搏分析数据统一的心搏位点，截取各导联上相同位置和一定长度的数据点，同步输送给经过训练的人工智能深度学习模型进行计算分析，输出是每个心搏位置点综合考虑了所有导联心电图信号特征，以及心搏在时间上前后关联的心律特征的准确心搏分类。
本方法充分考虑了心电图不同导联数据实际上就是测量了心脏电信号在不同的心电轴向量方向传递的信息流，把心电图信号在时间和空间上传递的多维度数字特征进行综合分析，极大地改进了传统方法仅仅依靠单个导联独立分析，然后把结果汇总进行一些统计学的投票方式而比较容易得出的分类错误的缺陷，极大地提高了心搏分类的准确率。
本步骤中采用的心搏分类模型可以如图4所示，具体可以为基于人工智能深度学习的卷积神经网络AlexNet，VGG16，Inception等模型启发的端对端多标签分类模型。具体的讲，该模型的网络是一个7层的卷积网络，每个卷积之后紧跟一个激活函数。第一层是两个不同尺度的卷积层，之后是六个卷积层。七层卷积的卷积核分别是96,256,256,384,384,384,256。除第一层卷积核有两个尺度分别是5和11外，其他层卷积核尺度为5。第三、五、六、 七层卷积层后是池化层。最后跟着两个全连接层。
本步骤中的心搏分类模型，我们采用了训练集包含30万病人的1700万数据样本进行训练。这些样本是根据动态心电图分析诊断的要求对数据进行准确的标注产生的，标注主要是针对常见心律失常，传导阻滞以及ST段和T波改变，可满足不同应用场景的模型训练。具体以预设标准数据格式保存标注的信息。在训练数据的预处理上，为增加模型的泛化能力，对于样本量较少的分类做了小幅的滑动来扩增数据，具体的说，就是以每个心搏为基础，按照一定步长(比如10-50个数据点)移动2次，这样就可以增加2倍的数据，提高了对这些数据量比较少的分类样本的识别准确率。经过实际结果验证，泛化能力也得到了改善。
在一个实际训练过程使用了两台GPU服务器进行几十次轮循训练，训练收敛后，使用500万独立的测试数据进行测试，准确率可以到达91.92％。
其中，训练数据的截取的长度，可以是1秒到10秒。比如采样率是200Hz，以2.5s为采样长度，取得的数据长度是500个心电图电压值(毫伏)的一个片段D[500]，输入数据是：InputData(i，j),其中，i是第i个导联，j是导联i第j个片段D。输入数据全部经过随机打散才开始训练，保证了训练过程收敛，同时，控制从同一个病人的心电图数据中收集太多的样本，提高模型的泛化能力，既真实场景下的准确率。训练时候，同步输入所有导联对应的片段数据D，按照图像分析的多通道分析方法，对每个时间位置的多个空间维度(不同心电轴向量)的导联数据进行同步学习，从而得到一个比常规算法更准确的分类结果。
步骤1208，对一次分类信息结果中的特定心搏的心搏分析数据输入到ST段和T波改变模型进行识别，确定ST段和T波评价信息；
ST段和T波评价信息具体为心搏分析数据对应的ST段和T波发生改变的导联位置信息。因为临床诊断要求对于ST段和T波的改变定位到具体的导联。
其中，一次分类信息的特定心搏数据是指包含窦性心搏(N)和其它可能包含ST改变的心搏类型的心搏分析数据。
ST段和T波改变导联定位模块将一次分类信息的特定心搏数据，按照每个导联依次输入到一个为识别ST段和T波改变的人工智能深度学习训练模型，进行计算分析，输出的结果说明导联片段的特征是否符合ST段和T波改变的结论，这样就可以确定ST段和T波改变发生的在具体那些导联的信息，即ST段和T波评价信息。具体方法可以是：把一次分类信息中结果是窦性心搏的各导联心搏分析数据，输入给ST段和T波改变模型，对窦性心搏分析数据进行逐一识别判断，以确定窦性心搏分析数据是否存在ST段和T波改变特征以及发生的具体导联位置信息，确定ST段和T波评价信息。
本步骤中采用的ST段和T波改变模型可以如图5所示，具体可以为基于人工智能深度学习的卷积神经网络AlexNet和VGG16等模型启发的端对端分类模型。具体的讲，该模型是一个7层的网络，模型包含了7个卷积，5个池化和2个全连接。卷积使用的卷积核均为1x5，每层卷积的滤波器个数各不相同。第1层卷积滤波器个数为96；第2层卷积和第3层卷积连用，滤波器个数为256；第4层卷积和第5层卷积连用，滤波器个数为384；第6层卷积滤波器个数为384；第7层卷积滤波器个数为256；第1、3、5、6、7层卷积层后是池化。随后是两个全连接，最后还采用Softmax分类器将结果分为两类。为了增加模型的非线性，提取数据更高维度的特征，故采用两个卷积连用的模式。
因为带有ST段和T波改变的心搏在所有心搏中的占比较低，为了兼顾训练数据的多样性及各个类别数据量的均衡性，选取无ST段和T波改变以及有ST段和T波改变的训练数据比例约为2:1，保证了模型在分类过程中良好的泛化能力且不出现对训练数据占比较多一类的倾向性。由于心搏的形态多种多样，不同个体表现的形态不尽相同，因此，为了模型更好估计各分类的分布，能有效提取特征，训练样本从不同年龄，体重，性别和居住地区的个体 收集；另外，因为单个个体在同一时间段内的心电图数据往往是高度相似的，所以为了避免过度学习，在获取单个个体的数据时，从所有数据中随机选取不同时间段的少量样本；最后，由于患者的心搏形态存在个体间差异大，而个体内相似度高的特点，因而在划分训练、测试集时，把不同的患者分到不同的数据集，避免同一个体的数据同时出现在训练集与测试集中，由此，所得模型测试结果最接近真实应用场景，保证了模型的可靠性和普适性。
步骤1209，根据心搏时间序列数据，对心搏分析数据进行P波和T波特征检测，确定每个心搏中P波和T波的详细特征信息；
具体的，详细特征信息包括幅值、方向、形态和起止时间的数据；在对心搏信号的分析中，P波、T波以及QRS波中的各项特征也是心电图分析中的重要依据。
在P波和T波特征检测模块中，通过计算QRS波群中切分点位置，以及P波和T波的切分点位置，来提取P波、T波以及QRS波群中的各项特征。可以分别通过QRS波群切分点检测、单导联PT检测算法和多导联PT检测算法来实现。
QRS波群切分点检测：根据QRS波群检测算法提供的QRS波群段功率最大点以及起止点，寻找单个导联中QRS波群的R点，R’点，S点以及S’点。在存在多导联数据时，计算各个切分点的中位数作为最后的切分点位置。
单导联P波、T波检测算法：P波和T波相对QRS波群幅度低、信号平缓，容易淹没在低频噪声中，是检测中的难点。本方法依据QRS波群检测的结果，在消除QRS波群对低频频段的影响后，使用低通滤波器对信号进行第三滤波，使PT波相对幅度增高。之后通过峰值检测的方法在两个QRS波群之间寻找T波。因为T波是心室复极产生的波群，因此T波和QRS波群之间有明确的锁时关系。以检测到的QRS波群为基准，在每个QRS波群到下一个QRS波群间期取中点(比如限制在第一个QRS波群后400ms到600ms之间的范围)作为T波检测结束点，在此区间内选取最大的峰作为T波。再在剩余的峰值内选择 幅度最大的峰为P波。同时也根据P波和T波的峰值与位置数据，确定P波和T波的方向和形态特征。优选的，低通滤波的截止频率设置为10-30Hz之间。
多导联P波、T波检测算法：在多导联的情况中，由于心搏中各个波的产生时间相同，空间分布不同，而噪声的时间空间分布不同，可以通过溯源算法来进行P、T波的检测。首先对信号进行QRS波群消除处理并使用低通滤波器对信号进行第三滤波以去除干扰。之后通过独立成分分析算法计算原始波形中的各个独立成分。在分离出的各个独立成分中，依据其峰值的分布特征以及QRS波群位置，选取相应的成分作为P波和T波信号，同时确定P波和T波的方向和形态特征。
步骤1210，对心搏分析数据在一次分类信息下根据心电图基本规律参考数据、P波和T波的详细特征信息以及ST段和T波评价信息进行二次分类处理，得到心搏分类信息；
具体的，心电图基本规律参考数据是遵循权威心电图教科书中对心肌细胞电生理活动和心电图临床诊断的基本规则描述生成的，比如两个心搏之间最小的时间间隔，P波与R波的最小间隔等等，用于将心搏分类后的一次分类信息再进行细分；主要根据是心搏间RR间期以及不同心搏信号在各导联上的医学显著性；心搏审核模块依据心电图基本规律参考数据结合一定连续多个心搏分析数据的分类识别，以及P波和T波的详细特征信息将室性心搏分类拆分更细的心搏分类，包括：室性早搏(V)、室性逸搏(VE)、加速性室性早搏(VT)，将室上性类心搏细分为室上性早搏(S)、房性逸搏(SE)、交界性逸搏(JE)和房性加速性早搏(AT)等等。
此外，通过二次分类处理，还可以纠正一次分类中发生的不符合心电图基本规律参考数据的错误分类识别。将细分后的心搏分类按照心电图基本规律参考数据进行模式匹配，找到不符合心电图基本规律参考数据的分类识别，根据RR间期及前后分类标识纠正为合理的分类。
具体的，经过二次分类处理，可以输出多种心搏分类，比如：正常窦性心搏(N)、完全性右束支阻滞(N_CRB)、完全性左束支阻滞(N_CLB)、室内阻滞(N_VB)、一度房室传导阻滞(N_B1)、预激(N_PS)、室性早搏(V)、室性逸搏(VE)、加速性室性早搏(VT)、室上性早搏(S)、房性逸搏(SE)、交界性逸搏(JE)、加速性房性早搏(AT)、房扑房颤(AF)、伪差(A)等分类结果。
通过本步骤，还可以完成基础心率参数的计算。其中基础计算的心率参数包括：RR间期、心率、QT时间、QTc时间等参数。
随后，根据心搏二次分类结果，按照心电图基本规律参考数据进行模式匹配，可以得到分类对应于心电图事件数据的以下这些典型的心电图事件，包括但不限于：
室上性早搏
室上性早搏成对
室上性早搏二联律
室上性早搏三联律
房性逸搏
房性逸搏心律
交界性逸搏
交界性逸搏心律
非阵发性室上性心动过速
最快室上性心动过速
最长室上性心动过速
室上性心动过速
短阵室上性心动过速
心房扑动-心房颤动
室性早搏
室性早搏成对
室性早搏二联律
室性早搏三联律
室性逸搏
室性逸搏心律
加速性室性自主心律
最快室性心动过速
最长室性心动过速
室性心动过速
短阵室性心动过速
二度I型窦房传导阻滞
二度II型窦房传导阻滞
一度房室传导阻滞
二度I型房室传导阻滞
二度II型房室传导阻滞
二度II型(2：1)房室传导阻滞
高度房室传导阻滞
完全性左束支阻滞
完全性右束支阻滞
室内阻滞
预激综合症
ST段和T波改变
最长RR间期
步骤1211，将心搏分析数据根据心搏分类信息和心电图基本规律参考数据生成心电图事件数据；根据信号质量评价参数对心电图事件数据进行筛选，得到报告结论数据和报告表项数据；根据每种心电图事件数据中的典型数据片段，生成报告图形数据。
根据参考信号质量评价参数，剔除心电图事件数据中不可信事件，计算各种心率参数，统计事件的数量和发生时间等，得到报告结论数据和报告表项数据。
具体的，心率参数计算包括计算平均心率、及最大、最小心率等。在计算最大和最小心率时，以固定长度片段为统计单位，逐个心搏进行全程扫描和统计比较。片段的长度一般为8-10秒，也可以根据需要自由设定。计算心率时，针对窦性心率占主体和异位心率占主体采用不同的心搏类型统计计算方法。在计算最大最小心率时：针对窦性心率占主体的心电图，仅计算窦性分类心搏；针对房扑房颤类占主体的心电图，仅计算房扑房颤类心搏及窦性心搏；针对非房扑房颤的其他异位心搏占主体的心电图，除伪差外所有类型心搏均参与计算。
对心电图事件数据，根据信号质量评价参数进行质量评估，选取数据信号质量最高的事件片段，同时分析片段中的包含的事件种类数量，优先选取最具代表性的片段，优选片段的开始位置，尽量保证事件心搏位于所选取片段的中部，生成报告图形数据。
在优选的方案中，心电图事件的选择规则可以具体如下例子所述：
对于一般心电图事件，选取单个片段。当片段第一个心搏心率大于等于100时，片段起始点位置距离第一个心搏距离为0.3秒。当片段第一个心搏心率小于等于45时，片段起始点位置距离第一个心搏距离为0.37秒。
对于有多个片段的心电图事件，需要对多个片段进行质量评估，依据信号质量评价参数计算截取片段的无干扰信号占比，当无干扰信号占比达到设定的阈值(优选的在60％-95％范围中确定阈值)，片段符合筛选条件，从中获得最优典型数据段。
根据被测对象ID，报告结论数据、报告表项数据和报告图形数据相关联，存储为报告数据。因此在查询调用时，可以根据被测对象ID直接获取到该被测对象ID相关的各种报告数据。报告数据中还相应的包括有报告数据的检测 时间信息。这个信息应当至少包括心电图数据的获取时间/时间段的信息，还可以包括报告数据最后更新的时间。因为考虑到可能对报告数据进行修改，所以也可以对该时间进行记录。
步骤130，接收用户输入的报告数据查询指令，根据用户的用户ID查询相应的报告数据，并生成报告数据查询结果列表数据，进行显示输出；
具体的，心电工作站能够向用户提供人机交互界面，通过人机交互界面，用户可以进行登录，并查询报告数据。
在用户登录时，心电工作站根据用户的登录信息进行权限验证，并根据用户权限信息对应的用户ID进行数据查询权限管理，以获取相应的报告数据。然后对报告数据进行数据提取，得到报告数据查询结果列表数据进行输出。报告数据查询结果列表数据至少包括查询得到的一个或多个报告数据的被测对象ID和检测时间信息。
下面以具体的例子来进行说明，此处仅为举例，并不限定其具体实现方式。
比如，用户为某科室主治医生，在其登录心电工作站后，进行患者报告数据查询操作时，心电工作站根据其权限获取该科室的患者的ID，根据患者的ID去查询匹配所有被测对象ID，得到该主治医生有权限查阅的患者的报告数据，优选的可以是设定时间段内的报告数据。然后对报告数据进行数据提取，至少提取其中的被测对象ID和检测时间信息，生成报告数据查询结果列表数据，优选的以列表方式在心电工作站的人机交互界面进行显示。其中,被测对象ID具体可以是姓名或患者档案号等。列表的展示顺序可以按照被测对象ID顺序排列，或者按照检测时间信息顺序/逆序排列。
又如，用户为某患者，在其登录心电工作站后，进行患者报告数据查询操作时，心电工作站根据其权限获取该患者ID相关的所有或设定时间段内的报告数据。同样的，对报告数据进行数据提取，至少提取其中的被测对象ID和检测时间信息，生成报告数据查询结果列表数据，并以列表方式在心电工 作站的人机交互界面进行显示。
步骤140，接收用户输入的选择指令，根据选择指令获取被选择的报告数据；
具体的，用户通过人机交互界面进行选择输入，从而确定索要选择的报告数据。
基于不同的操作目的，支持对报告数据的单个处理操作或批处理操作。
比如需要对报告数据进行输出查看、编辑、修改等操作，可以从报告数据查询结果列表数据选择单个查询结果以获取相应的一个报告数据。
如果是对报告数据进行打印、传送、下载等操作时，可以从报告数据查询结果列表数据同时选择多个查询结果以一次性的获取相应的多个报告数据。这样可以简化操作。
通过心电工作站，可以对用户进行操作权限管理，比如可以设定用户的用户类别信息，例如为医生、普通工作人员、患者等，对于不同类别用户的权限设定为不同。比如用户类别信息为医生，则可以对报告数据进行查询、修改、下载、转发等操作，如果为普通工作人员或患者，只能对报告数据进行查询和打印。
在选择报告数据之后，可以对报告数据执行输出(下述步骤150)、修改(下述步骤160)等操作。
步骤150，接收用户输入的报告输出指令，根据报告输出指令确定输出模式信息和输出格式信息，并且，根据输出模式信息选择性输出报告结论数据、报告表项数据和/或报告图形数据中的部分数据或全部数据，以及根据输出格式信息，将部分数据或全部数据进行数据格式转换，生成报告输出数据。
具体的，当用户在报告数据查询结果列表数据中选择报告数据并请求对报告数据执行输出时，心电工作站根据用户的选择指令获取被选择的报告数据，并根据报告输出模式信息和报告输出格式信息响应的生成报告输出数据。
同时，心电工作站获取报告输出模式信息和输出格式信息。报告输出模 式信息是指报告以哪种格式输出，可以根据用户权限的不同对应有不同的报告输出模式，比如用户类别信息为患者的用户，仅输出报告数据中的设定的部分数据。报告输出模式还包括输出的数据展示方式。在图7a-7c和图8a-8g中分别展示了不同的报告输出模式，其中图7a-7c为一种静态心电监测数据的报告输出模式，图8a-8g为一种动态心电检测数据的报告输出模式，用户可以根据需要，输入或选择相应的报告输出模式信息，以使心电工作站输出相应输出模式的报告数据。
报告的输出格式信息可以是根据不同用途而进行选择的输出格式，用以对报告数据进行格式转换，转换为所需要的数据格式再进行输出。具体格式可以包括：可扩展标记语言(XML)、心电图数据记录与传输的标准通信协议(SCP)、便携式文档格式(PDF)、联合图像专家组(JPEG)、医学数字成像和通信(DICOM)3.0、HL7组织制定的心电图数据注释格式(HI7)等多种格式。
心电工作站中预设有默认的报告输出模式信息和输出格式信息，在用户不进行指定时，心电工作站可以按照默认格式进行将报告数据转换为报告输出数据进行输出。
报告输出数据的输出包括在心电工作站的人机交互界面上输出，在心电工作站中集成的或连接的打印机进行打印输出等。
步骤160，接收用户输入的报告结论修改数据和/或报告表项修改数据；根据报告结论修改数据更新报告结论数据，根据报告表项修改数据更新报告表项数据。
具体的，在用户具有报告数据修改权限时，还可以通过心电工作站进行报告数据的修改。其中具体包括对报告结论的修改，以及对于测试数据的修改。在实际应用中，这一功能主要对医生开放。
在获取被选择的报告数据之后，如果心电工作站接收到报告结论修改数据和/或报告表项修改数据，首先获取报告数据，并通过人机交互界面进行显 示。此时，报告数据的格式为可读写格式。
在用户根据报告数据确定需要修改的内容后，通过人际交互界面接收用户对原报告数据中部分数据的删除，并记录用户新输入的数据，这里具体可以包括报告结论数据和报告表项数据，在接收到输入完毕的数据更新指令后，根据用户输入的数据，对原报告数据进行更新。优选的，在报告数据中生成一条记录，记录相应的数据更新的时间和进行这一操作的用户ID。
图6为本发明实施例提供的一种心电工作站的结构示意图，该心电工作站包括：处理器和存储器。存储器可通过总线与处理器连接。存储器可以是非易失存储器，例如硬盘驱动器和闪存，存储器中存储有软件程序和设备驱动程序。软件程序能够执行本发明实施例提供的上述方法的各种功能；设备驱动程序可以是网络和接口驱动程序。处理器用于执行软件程序，该软件程序被执行时，能够实现本发明实施例提供的方法。
需要说明的是，本发明实施例还提供了一种计算机可读存储介质。该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器执行时，能够实现本发明实施例提供的方法。
本发明实施例还提供了一种包含指令的计算机程序产品。当该计算机程序产品在计算机上运行时，使得处理器执行上述方法。
本发明实施例提供的基于人工智能自学习的心电信息处理方法及设备，通过数据的预处理，心搏特征检测，干扰信号检测，信号质量评估与导联合并，心搏分类，心搏审核的二次分类，心电图事件分类和心电图参数的分析计算，最终自动输出报告数据的一个完整快速流程的自动化分析方法。本发明的自动分析方法，还可以记录对自动分析结果的修改信息，并收集这些修改的数据反馈给深度学习模型继续训练，不断地改进和提升自动分析方法的准确率。
专业人员应该还可以进一步意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来 实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
结合本文中所公开的实施例描述的方法或算法的步骤可以用硬件、处理器执行的软件模块，或者二者的结合来实施。软件模块可以置于随机存储器(RAM)、内存、只读存储器(ROM)、电可编程ROM、电可擦除可编程ROM、寄存器、硬盘、可移动磁盘、CD-ROM、或技术领域内所公知的任意其它形式的存储介质中。
以上所述的具体实施方式，对本发明的目的、技术方案和有益效果进行了进一步详细说明，所应理解的是，以上所述仅为本发明的具体实施方式而已，并不用于限定本发明的保护范围，凡在本发明的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种心电信息处理方法，其特征在于，所述方法包括：
    心电工作站接收心电监测设备输出的心电图数据，所述心电图数据包括被测对象ID和检测时间信息；
    对所述心电图数据进行心电数据分析，生成报告数据并进行存储；所述报告数据包括：所述被测对象ID对应的报告结论数据、报告表项数据和/或报告图形数据；
    接收用户输入的报告数据查询指令，根据所述用户的用户ID查询相应的报告数据，并生成报告数据查询结果列表数据，进行显示输出；所述报告数据查询结果列表数据至少包括查询得到的一个或多个所述报告数据的被测对象ID和检测时间信息；
    接收用户输入的选择指令，根据所述选择指令获取被选择的报告数据；
    接收用户输入的报告输出指令，根据所述报告输出指令确定输出模式信息和输出格式信息，并且，根据所述输出模式信息选择性输出所述报告结论数据、报告表项数据和/或报告图形数据中的部分数据或全部数据，以及根据所述输出格式信息，将所述部分数据或全部数据进行数据格式转换，生成报告输出数据。
  2. 根据权利要求1所述的心电信息处理方法，其特征在于，在所述接收用户输入的选择指令，根据所述选择指令获取被选择的报告数据之后，所述方法还包括：
    接收用户输入的报告结论修改数据和/或报告表项修改数据；
    根据所述报告结论修改数据更新所述报告结论数据，根据所述报告表项修改数据更新所述报告表项数据。
  3. 根据权利要求1所述的心电信息处理方法，其特征在于，所述心电图数据为单导联或多导联的时间序列数据；所述对所述心电图数据进行心电数据分析，生成报告数据具体包括：
    将所述心电图数据的数据格式经过重采样转换为预设标准数据格式，并对转换后的预设标准数据格式的心电图数据进行第一滤波处理；
    对所述第一滤波处理后的心电图数据进行心搏检测处理，识别所述心电图数据包括的多个心搏数据；每个所述心搏数据对应一个心搏周期，包括相应的P波、QRS波群、T波的幅值数据和起止时间数据；
    根据训练得到的干扰识别二分类模型对所述心搏数据进行干扰识别，确定所述心搏数据是否存在干扰噪音，以及用于判断干扰噪音的一个概率值；
    根据心搏数据的导联参数和所述心搏数据，基于所述干扰识别的结果和时间规则合并生成心搏时间序列数据；根据所述心搏时间序列数据生成心搏分析数据；
    对所述心搏分析数据进行信号质量分析，评估所述心搏分析数据的信号质量，得到所述心搏分析数据的信号质量评价参数；
    根据训练得到的心搏分类模型对所述心搏分析数据进行幅值和时间表征数据的特征提取和分析，得到所述心搏分析数据的一次分类信息；
    对所述一次分类信息结果中的特定心搏的心搏分析数据输入到训练好的ST段和T波改变模型进行识别，确定ST段和T波评价信息；
    根据心搏时间序列数据，对心搏分析数据进行P波和T波特征检测，确定每个心搏中P波和T波的详细特征信息；
    对所述心搏分析数据在所述一次分类信息下根据所述心电图基本规律参考数据、P波和T波的详细特征信息以及所述ST段和T波评价信息进行二次分类处理，得到心搏分类信息；
    将所述心搏分析数据根据所述心搏分类信息和心电图基本规律参考数据生成心电图事件数据；根据所述信号质量评价参数对心电图事件数据进行筛选，得到所述报告结论数据和报告表项数据；根据每种心电图事件数据中的典型数据片段，生成所述报告图形数据。
  4. 根据权利要求3所述的心电信息处理方法，其特征在于，对所述第一 滤波处理后的心电图数据进行心搏检测处理还包括：
    根据所述QRS波群确定RR间期并计算所述RR间期内噪声的估计值；
    根据所述噪声的估计值和每个QRS波群中的最大幅值确定每个QRS波群的检测置信度。
  5. 根据权利要求3所述的心电信息处理方法，其特征在于，所述根据训练得到的干扰识别二分类模型对所述心搏数据进行干扰识别，具体包括：
    以第一数据量对所述心搏数据进行切割采样，并将切割采样得到的数据输入到干扰识别二分类模型进行干扰识别；
    识别心搏数据中，心搏间期大于等于预设间期判定阈值的数据片段；
    对所述心搏间期大于等于预设间期判定阈值的数据片段进行信号异常判断，确定是否为异常信号；
    如果不是异常信号，则以预设时间宽度，根据设定时值确定所述数据片段中滑动取样的起始数据点和终止数据点，并由所述起始数据点开始对所述数据片段进行滑动取样，至所述终止数据点为止，得到多个取样数据段；
    对每个所述取样数据段进行所述干扰识别。
  6. 根据权利要求3所述的心电信息处理方法，其特征在于，所述对所述一次分类信息结果中的特定心搏的心搏分析数据输入到训练好的ST段和T波改变模型进行识别，确定ST段和T波评价信息，具体包括：
    将所述一次分类信息中的特定心搏数据，按导联依次输入到根据训练得到的ST段和T波改变模型，对各导联的特定心搏数据进行幅值和时间表征数据的特征提取和分析，得到各导联的ST段和T波改变信息，确定ST段和T波评价信息；所述ST段和T波评价信息具体为所述心搏片段数据对应的ST段和T波发生改变的导联位置信息。
  7. 根据权利要求3所述的心电信息处理方法，其特征在于，所述根据每种心电图事件数据中的典型数据片段，生成报告图形数据，具体包括：
    根据所述信号质量评价参数，对每种心电图事件的数据片段进行评估， 选择信号质量评价参数最高的数据片段为所述心电图事件中的典型数据片段。
  8. 一种心电工作站，包括存储器和处理器，其特征在于，所述存储器用于存储程序，所述处理器用于执行如权利要求1至7任一项所述的方法。
  9. 一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行如权利要求1至7任一项所述的方法。
  10. 一种计算机可读存储介质，包括指令，当所述指令在计算机上运行时，使所述计算机执行根据权利要求1至7任一项所述的方法。
PCT/CN2018/083466 2018-02-24 2018-04-18 心电信息处理方法和心电工作站 WO2019161611A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP18907191.3A EP3698708A4 (en) 2018-02-24 2018-04-18 ECG INFORMATION PROCESSING AND ECG WORKSTATION
US16/766,551 US11783924B2 (en) 2018-02-24 2018-04-18 ECG information processing method and ECG workstation

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810157365.3 2018-02-24
CN201810157365.3A CN109411042B (zh) 2018-02-24 2018-02-24 心电信息处理方法和心电工作站

Publications (1)

Publication Number Publication Date
WO2019161611A1 true WO2019161611A1 (zh) 2019-08-29

Family

ID=65464010

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/083466 WO2019161611A1 (zh) 2018-02-24 2018-04-18 心电信息处理方法和心电工作站

Country Status (4)

Country Link
US (1) US11783924B2 (zh)
EP (1) EP3698708A4 (zh)
CN (1) CN109411042B (zh)
WO (1) WO2019161611A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112885459A (zh) * 2021-02-09 2021-06-01 清华珠三角研究院 一种心室肥大的预测系统、装置及存储介质
CN114448843A (zh) * 2021-12-23 2022-05-06 天翼云科技有限公司 一种自适应的心跳检测方法及装置、电子设备
CN116594627A (zh) * 2023-05-18 2023-08-15 湖北大学 一种基于多标签学习的群体软件开发中服务匹配方法

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110859613B (zh) * 2019-11-20 2022-07-22 深圳市健云互联科技有限公司 心电数据处理装置、计算机设备及存储介质
CN111000552B (zh) * 2019-12-23 2021-10-01 深圳市凯沃尔电子有限公司 一种智能心电图机
CN111297351A (zh) * 2020-02-13 2020-06-19 苏州百慧华业精密仪器有限公司 一种动态心电图中的运动伪差识别方法及装置
CN112270212B (zh) * 2020-10-10 2023-12-08 深圳市凯沃尔电子有限公司 基于多导联心电信号生成心搏标签数据序列的方法和装置
CN112286937A (zh) * 2020-11-04 2021-01-29 重庆医科大学附属儿童医院 一种脑电图报告生成查询方法及系统
CN112244855B (zh) * 2020-11-13 2022-08-26 上海乐普云智科技股份有限公司 一种面向心电数据的数据处理系统
TWI758039B (zh) * 2020-12-29 2022-03-11 財團法人國家衛生研究院 選擇心電圖的特徵的電子裝置和方法
TWI833462B (zh) * 2022-11-22 2024-02-21 國立勤益科技大學 一種動態心電圖st改變事件自動偵測方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010032099A1 (en) * 1999-12-18 2001-10-18 Joao Raymond Anthony Apparatus and method for processing and/or for providing healthcare information and/or healthcare-related information
CN204813800U (zh) * 2015-06-01 2015-12-02 陈耶锋 一种全自动健康智能干预系统
CN105286909A (zh) * 2015-11-04 2016-02-03 杜晓松 一种可穿戴心音和心电特征信息采集及监控系统
CN105320974A (zh) * 2014-06-25 2016-02-10 朱建军 医学信息采集应用系统及方法
CN106529182A (zh) * 2016-11-15 2017-03-22 黄劲涛 一种云医院

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6463320B1 (en) * 1999-12-22 2002-10-08 Ge Medical Systems Information Technologies, Inc. Clinical research workstation
EP1110502A3 (en) * 1999-12-22 2003-03-26 GE Marquette Medical Systems, Inc. Clinical research workstation
IL155955A0 (en) * 2003-05-15 2003-12-23 Widemed Ltd Adaptive prediction of changes of physiological/pathological states using processing of biomedical signal
JP2006296888A (ja) * 2005-04-22 2006-11-02 Fukuda Denshi Co Ltd 生体情報出力装置及び方法並びに生体情報レポート
KR101002020B1 (ko) * 2008-03-27 2010-12-16 계명대학교 산학협력단 실시간 심전도 모니터링 시스템 및 방법, 패치형 심전도측정장치, 통신장치
EP2534597B1 (en) * 2010-03-15 2018-10-17 Singapore Health Services Pte Ltd Method of predicting the survivability of a patient
CN102028459B (zh) * 2010-12-02 2013-01-02 广东宝莱特医用科技股份有限公司 一种心电图机通道起搏信号检测方法
US8684942B2 (en) * 2011-05-25 2014-04-01 Siemens Medical Solutions Usa, Inc. System for cardiac impairment detection based on signal regularity
BR112014008597A2 (pt) * 2011-10-12 2017-04-18 Koninklijke Philips Nv sistema e método para determinação dos pontos q e j de um eletrocardiograma (ecg); um ou mais processadores; e mídia executável por computador não transitória
US20160045117A1 (en) * 2014-08-14 2016-02-18 Nehemiah T. Liu Peak Detection System and Method for Calculation of Signal-Derived Metrics
JP2016043041A (ja) * 2014-08-22 2016-04-04 セイコーエプソン株式会社 生体情報検出装置及び生体情報検出方法
US10980483B2 (en) * 2015-11-20 2021-04-20 PhysioWave, Inc. Remote physiologic parameter determination methods and platform apparatuses
CN106027566B (zh) * 2016-07-13 2018-10-30 上海数创医疗科技有限公司 基于sip传输协议的移动心电采集及诊断系统
CN106815570B (zh) * 2016-12-30 2020-10-27 广东技术师范大学 一种基于动态模式识别的心电信号st-t段识别方法
CN107714023B (zh) * 2017-11-27 2020-09-01 上海优加利健康管理有限公司 基于人工智能自学习的静态心电图分析方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010032099A1 (en) * 1999-12-18 2001-10-18 Joao Raymond Anthony Apparatus and method for processing and/or for providing healthcare information and/or healthcare-related information
CN105320974A (zh) * 2014-06-25 2016-02-10 朱建军 医学信息采集应用系统及方法
CN204813800U (zh) * 2015-06-01 2015-12-02 陈耶锋 一种全自动健康智能干预系统
CN105286909A (zh) * 2015-11-04 2016-02-03 杜晓松 一种可穿戴心音和心电特征信息采集及监控系统
CN106529182A (zh) * 2016-11-15 2017-03-22 黄劲涛 一种云医院

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112885459A (zh) * 2021-02-09 2021-06-01 清华珠三角研究院 一种心室肥大的预测系统、装置及存储介质
CN114448843A (zh) * 2021-12-23 2022-05-06 天翼云科技有限公司 一种自适应的心跳检测方法及装置、电子设备
CN116594627A (zh) * 2023-05-18 2023-08-15 湖北大学 一种基于多标签学习的群体软件开发中服务匹配方法
CN116594627B (zh) * 2023-05-18 2023-12-12 湖北大学 一种基于多标签学习的群体软件开发中服务匹配方法

Also Published As

Publication number Publication date
US11783924B2 (en) 2023-10-10
CN109411042A (zh) 2019-03-01
US20210280281A1 (en) 2021-09-09
EP3698708A4 (en) 2021-12-08
CN109411042B (zh) 2021-06-25
EP3698708A1 (en) 2020-08-26

Similar Documents

Publication Publication Date Title
WO2019161610A1 (zh) 心电信息处理方法和心电工作站系统
US11529103B2 (en) Artificial intelligence self-learning-based automatic electrocardiography analysis method and apparatus
WO2019161611A1 (zh) 心电信息处理方法和心电工作站
US11517212B2 (en) Electrocardiogram information dynamic monitoring method and dynamic monitoring system
CN107951485B (zh) 基于人工智能自学习的动态心电图分析方法和装置
US11344243B2 (en) Artificial intelligence self-learning-based static electrocardiography analysis method and apparatus
CN108186011B (zh) 房颤检测方法、装置及可读存储介质
CN106815570B (zh) 一种基于动态模式识别的心电信号st-t段识别方法
Shi et al. Inter-patient heartbeat classification based on region feature extraction and ensemble classifier
CN113095302B (zh) 用于心律失常分类的深度模型、利用该模型的方法及装置
Sumathi et al. A wavelet transform based feature extraction and classification of cardiac disorder
Fang et al. Dual-channel neural network for atrial fibrillation detection from a single lead ECG wave
Papadogiorgaki et al. Heart rate classification using ECG signal processing and machine learning methods
Tsai et al. Beat-by-beat Classification of ECG Signals with Machine Learning Algorithm for Cardiac Episodes
US20220262516A1 (en) Atrial Fibrillation Prediction Model And Prediction System Thereof
Gu et al. A Novel Diagnostic Algorithm for Heart Disease in ECG Monitoring System
Hsieh et al. 12-lead ECG signal processing and atrial fibrillation prediction in clinical practice
Jenitta et al. A Comprehensive Survey on ECG Signal Graph Interpretation
Ashokan et al. Comparing Tree-Based Ensemble Machine Learning Models and Convolutional Neural Network for Automatic Classification of Heart Abnormalities from ECG Images

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2018907191

Country of ref document: EP

Effective date: 20200518

NENP Non-entry into the national phase

Ref country code: DE