WO2019161609A1 - 多参数监护数据分析方法和多参数监护仪 - Google Patents

多参数监护数据分析方法和多参数监护仪 Download PDF

Info

Publication number
WO2019161609A1
WO2019161609A1 PCT/CN2018/083463 CN2018083463W WO2019161609A1 WO 2019161609 A1 WO2019161609 A1 WO 2019161609A1 CN 2018083463 W CN2018083463 W CN 2018083463W WO 2019161609 A1 WO2019161609 A1 WO 2019161609A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
information
heartbeat
electrocardiogram
ecg
Prior art date
Application number
PCT/CN2018/083463
Other languages
English (en)
French (fr)
Inventor
赵子方
刘畅
曹君
李喆
臧凯丰
汪嘉雨
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
Publication of WO2019161609A1 publication Critical patent/WO2019161609A1/zh

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/02Detecting, 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
    • A61B5/0205Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • A61B5/02055Simultaneously evaluating both cardiovascular condition and temperature
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/74Details of notification to user or communication with user or patient ; user input means
    • A61B5/746Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/01Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/02Detecting, 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
    • A61B5/021Measuring pressure in heart or blood vessels
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/02Detecting, 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
    • A61B5/021Measuring pressure in heart or blood vessels
    • A61B5/022Measuring pressure in heart or blood vessels by applying pressure to close blood vessels, e.g. against the skin; Ophthalmodynamometers
    • A61B5/0225Measuring pressure in heart or blood vessels by applying pressure to close blood vessels, e.g. against the skin; Ophthalmodynamometers the pressure being controlled by electric signals, e.g. derived from Korotkoff sounds
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/02Detecting, 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
    • A61B5/024Detecting, measuring or recording pulse rate or heart rate
    • A61B5/0245Detecting, measuring or recording pulse rate or heart rate by using sensing means generating electric signals, i.e. ECG signals
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/08Detecting, measuring or recording devices for evaluating the respiratory organs
    • A61B5/0816Measuring devices for examining respiratory frequency
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/145Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
    • A61B5/1455Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
    • A61B5/14551Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/24Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316Modalities, i.e. specific diagnostic methods
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/24Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316Modalities, i.e. specific diagnostic methods
    • A61B5/318Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/24Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316Modalities, i.e. specific diagnostic methods
    • A61B5/318Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346Analysis of electrocardiograms
    • A61B5/349Detecting specific parameters of the electrocardiograph cycle
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/24Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316Modalities, i.e. specific diagnostic methods
    • A61B5/318Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346Analysis of electrocardiograms
    • A61B5/349Detecting specific parameters of the electrocardiograph cycle
    • A61B5/363Detecting tachycardia or bradycardia
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/24Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316Modalities, i.e. specific diagnostic methods
    • A61B5/318Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346Analysis of electrocardiograms
    • A61B5/349Detecting specific parameters of the electrocardiograph cycle
    • A61B5/364Detecting abnormal ECG interval, e.g. extrasystoles, ectopic heartbeats
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7203Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis
    • A61B5/725Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis
    • A61B5/7264Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis
    • A61B5/7264Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7271Specific aspects of physiological measurement analysis
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7271Specific aspects of physiological measurement analysis
    • A61B5/7282Event detection, e.g. detecting unique waveforms indicative of a medical condition
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70ICT 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 a multi-parameter monitoring data analysis method and a multi-parameter monitor.
  • a multi-parameter monitor is a commonly used clinical medical device.
  • This monitoring device features multiple sets of sensors that can simultaneously monitor vital signs such as ECG, blood pressure, blood oxygen, pulse, respiration, and body temperature.
  • vital signs such as ECG, blood pressure, blood oxygen, pulse, respiration, and body temperature.
  • the multi-parameter monitor can become an important reference for the doctor to monitor the patient, so that the doctor can find the patient's problems in time and deal with it in time, thus ensuring the patient's life safety.
  • the clinical application of the monitor can be found in: surgery, post-operative, trauma care, coronary heart disease, critically ill patients, neonates, premature infants, hyperbaric oxygen chambers, delivery rooms, etc.
  • the threshold setting method to trigger the alarm event. For example, when the heart rate is too fast, an alarm is issued or when the heart rate is too slow.
  • the method of setting the threshold is simple and intuitive, the accuracy is relatively poor, because the electrocardiographic signal is a weak current reflected by the electrical activity of the cardiomyocytes on the body surface, and is recorded by the body surface electrode and the amplified recording system.
  • Other non-cardiogenic electrical signals such as EMG signal interference caused by skeletal muscle activity, are also recorded during the recording process. These signals can cause incorrect heartbeat signal detection, which can trigger an alarm.
  • 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, and sometimes it is not necessarily reflected in the heart rate.
  • the current multi-parameter monitoring device can only perform very limited analysis and alarm on the ECG signal, which also leads to a large number of missed events, and the patient's life and health cannot be effectively protected.
  • a first aspect of the embodiments of the present invention provides a multi-parameter monitoring data analysis method, including:
  • the vital sign monitoring data has time attribute information
  • the physical monitoring data includes: electrocardiogram data, pulse data, blood pressure data, respiratory data, Blood oxygen saturation data and body temperature data;
  • Performing wave group feature recognition on the electrocardiogram data obtaining a characteristic signal of the electrocardiogram data, performing heartbeat classification on the electrocardiogram data according to the characteristic signal, obtaining heartbeat classification information according to the basic rule reference data of the electrocardiogram, and generating an electrocardiogram Event data
  • the first alarm information includes the ECG abnormal event information and alarm time information; the ECG abnormal event information has corresponding item information;
  • the pulse data, blood pressure data, respiratory data, blood oxygen saturation data, and body temperature data have abnormal data exceeding a corresponding set threshold, and generating other abnormal event information according to the abnormal data;
  • the set threshold is exceeded, the second alarm information is output; the second alarm information includes the other abnormal event information and alarm time information; and the other abnormal event information has corresponding item information.
  • the method further includes:
  • the vital sign monitoring data is aggregated according to time attribute information of the vital sign monitoring data, and time series data of the vital sign monitoring data is generated and stored.
  • the method further includes:
  • the ECG data in the preset time period before and after the corresponding time of the ECG data is acquired according to the time attribute information, and the abnormal event record data is generated;
  • the method further includes:
  • the method further comprises:
  • the abnormal event record data is analyzed and processed, and abnormal event report data is generated and output.
  • the method further includes:
  • the alarm event data includes item information of the vital sign monitoring data and the corresponding ECG abnormal event information and/or other abnormal event information.
  • performing the wave group feature recognition on the electrocardiogram data, obtaining a characteristic signal of the electrocardiogram data, performing heart beat classification on the electrocardiogram data according to the feature signal, and obtaining a heart beat classification according to the basic rule reference data of the electrocardiogram Information and generate ECG event data specifically include:
  • each of the heartbeat data corresponding to one heart cycle, including a corresponding P wave, QRS Wave group, T wave amplitude and start and end time data;
  • the heartbeat analysis data of the specific heartbeat in the primary classification information result is input to the ST segment and the T wave change model for identification, and the ST segment and T wave evaluation information is determined;
  • the detailed feature information includes amplitude, direction, Form and start and end time data
  • the heartbeat classification information is analyzed and matched to generate the ECG event data.
  • the method before performing the physical monitoring data collection on the measured object to obtain the vital sign monitoring data of the measured object, the method further includes:
  • the set threshold is determined based on the monitoring reference data.
  • the multi-parameter monitoring data analysis method realizes the data analysis and alarm flow of the multi-parameter monitoring based on artificial intelligence, and can automatically, quickly and completely analyze the measured measurement data, and the abnormal electrocardiogram
  • the state and other vital signs parameters give early warning, and reduce the false alarm phenomenon caused by interference.
  • the alarm accuracy is high, and the types of abnormalities that can be detected, especially the types of abnormal electrocardiogram, have good application prospects.
  • a second aspect of the embodiments of the present invention provides a multi-parameter monitor, 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 analyzing multi-parameter monitoring data 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 a multi-parameter monitor according to an embodiment of the present invention.
  • the present invention relates to a multi-parameter monitoring data analysis method for clinical monitoring, and a multi-parameter monitor for performing the method.
  • the multi-parameter monitor is a clinical medical monitoring device. This kind of monitoring device is characterized by multiple sets of sensors, which can simultaneously monitor vital signs such as ECG, blood pressure, blood oxygen, pulse, respiration, body temperature, etc., and process the data transmitted from each sensor in real time, and the abnormality occurs in the corresponding indicators. When the alarm signal is given, the doctor and nurse can handle the condition in time.
  • ECG ECG signal obtained through the sensor
  • the algorithm calculation can extract the effective information among them.
  • the processing process is more complicated and difficult, and it is also a link that is prone to detection errors.
  • 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.
  • Other non-cardiogenic electrical signals such as EMG signal interference caused by skeletal muscle activity, are also recorded during the recording process. Therefore, we believe that it is necessary to effectively identify and eliminate the ECG signals in order to effectively reduce false alarms caused by interference signals.
  • 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 existing monitoring equipment can only perform very limited analysis and alarm on the ECG signal.
  • the existing monitoring equipment can only perform very limited analysis and alarm on the ECG signal.
  • 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 arrhythmia analysis, long interval pause, flutter and flutter are performed on the collected digital signals, Conduction block, premature beat and escape, bradycardia, tachycardia, ST segment change detection, ECG event analysis and classification, in order to achieve the purpose of generating accurate alarm signals, so as to effectively monitor the patient's vital signs.
  • AI artificial intelligence
  • the present invention provides a multi-parameter monitoring data analysis method, the method step flow is shown in Figure 1, the method mainly includes the following steps:
  • Step 110 Perform physical sign monitoring data collection on the measured object to obtain physical condition monitoring data of the measured object;
  • the object to be measured refers to a living body that is monitored by a multi-parameter monitor, wherein the most conventional object to be measured refers to a person.
  • the monitor has a vital sign signal collecting device such as an electrode, a probe, a cuff, and the like, which is in contact with the object to be measured, and collects a vital sign signal of the measured object through the sign signal collecting device, and obtains the vital sign monitoring data through digital processing.
  • the vital signs monitoring data may specifically include: electrocardiogram data, pulse data, blood pressure data, respiratory data, blood oxygen saturation data, and body temperature data.
  • the vitality monitoring data has time attribute information, and each data point has a corresponding data collection time, which is time attribute information. At the same time as data acquisition, this data acquisition time is also recorded and stored as time attribute information of the vitals monitoring data.
  • ECG data The signals generated by the electrocardiographic activity of the ECG signal acquisition team of the non-invasive ECG were recorded in single-lead or multi-lead form.
  • Pulse data The pulse is a phenomenon in which the arteries periodically pulsate with the contraction of the heart.
  • the pulse includes changes in various physical quantities such as intravascular pressure, volume, displacement, and wall tension.
  • the sensor consists of two parts, a light source and a photoelectric transducer, which can be clamped on the fingertip or auricle of the subject.
  • the light source selects a wavelength that is selective for oxyhemoglobin in the arterial blood, such as a light-emitting diode having a spectrum of 700-900 nm.
  • the light passes through the perivascular blood vessels of the human body. When the volume of arterial congestion changes, the light transmittance of the light is changed.
  • the photoelectric transducer transmits the light transmitted or reflected by the tissue, and is converted into an electrical signal to be amplified and output by the amplifier. This reflects the volume change of the arterial blood vessels.
  • the pulse is a signal that periodically changes with the pulsation of the heart, and the volume of the arterial vessel also changes periodically.
  • the period of signal change of the photoelectric transducer is the pulse rate, that is, the pulse data.
  • Blood pressure data The highest pressure reached during systole is called systolic blood pressure, which pushes blood into the aorta and maintains systemic circulation.
  • the lowest pressure reached when the heart expands is called diastolic blood pressure, which allows blood to flow back into the right atrium.
  • the integral of the blood pressure waveform over one week divided by the cardiac period T is called the average pressure.
  • There are many ways to measure blood pressure data which can be divided into invasive measurements and non-invasive measurements. In the multi-parameter monitor, we prefer two types of non-invasive measurement methods, the Korotkoff method and the vibration measurement method.
  • the Korotkoff method is to detect the Korotkoff sound (pulse sound) under the cuff to measure blood pressure.
  • the Korotkoff sound non-invasive blood pressure monitoring system includes a cuff inflation system, a cuff, a Korotkoff sound sensor, an audio amplification and an automatic gain adjustment circuit. , A / D converter, microprocessor and display parts.
  • the vibration measurement method is to detect the oscillating wave of the gas in the sleeve, the oscillation wave originates from the pulsation of the blood vessel wall, and the blood pressure data can be measured by measuring the relevant points of the oscillation wave, including systolic blood pressure (PS), diastolic blood pressure (PD) and average pressure (PM). ).
  • PS systolic blood pressure
  • PD diastolic blood pressure
  • PM average pressure
  • the method of obtaining the pulse vibration wave by the vibration measuring method can obtain the blood pressure data by measuring the pulse vibration wave by means of the microphone and the pressure sensor.
  • blood pressure data can also be obtained by invasive measurement.
  • ICU intensive care unit
  • some patients in the intensive care unit (ICU) ward can be monitored by directly intubating the artery and connecting the other end of the cannula to a sterilized fluid-filled pressure detection system to achieve real-time blood pressure data. collection.
  • the advantages of this invasive monitoring method include: real-time display of blood pressure, and display of continuous blood pressure changes; accurate readings in hypotensive states; long-term patient comfort is improved, avoiding non-invasive measurements
  • the wound caused by long-term inflation and deflation; more information can be extracted, including the vascular volume can be derived from the shape of the blood pressure waveform.
  • Respiratory measurements are an important part of the kinetic energy test.
  • the monitor measures the respiratory rate (times/minute) by measuring the respiratory wave, which is the respiratory data.
  • the measurement of the respiratory rate can directly measure the temperature change of the respiratory airflow through the thermistor, and the change is converted into a voltage signal through the bridge circuit; the impedance method can also be used to measure the respiratory frequency, because the chest wall muscles are alternating when breathing The thoracic shape is alternately deformed, and the electrical impedance of the body tissue also alternates.
  • the measurement of the respiratory impedance value can be performed by various methods such as a bridge method, a modulation method, a constant voltage source method, and a constant current source method.
  • the respiratory impedance electrode can also be used with the ECG electrode to detect changes in respiratory impedance and respiratory rate simultaneously when detecting ECG signals.
  • Blood oxygen saturation is an important parameter to measure the ability of human blood to carry oxygen.
  • the oxygen saturation can be measured by transmission (or reflection) dual-wavelength (red R and infrared IR) photodetection techniques to detect the ratio of alternating components caused by the absorption of red and infrared light through arterial blood.
  • the non-pulsating tissue skin, muscle, venous blood, etc.
  • the blood oxygen saturation value SpO2 that is, blood oxygen saturation data
  • the pulse data can be simultaneously determined according to the period of the detected signal.
  • Body temperature is an important indicator of life status.
  • the body temperature is measured using a thermistor with a negative temperature coefficient as the temperature sensor, and a bridge is used as the detection circuit.
  • a bridge is used as the detection circuit.
  • Body surface probes and body cavity probes can also be used to monitor body surface and cavity temperature, respectively.
  • infrared non-contact temperature measurement technology can also be used to monitor the question data. In the monitor, we set the temperature measurement accuracy to 0.1 °C in order to have a faster temperature response.
  • the multi-parameter monitor to perform the physical monitoring data collection of the measured object by the above method, and obtain the vital sign monitoring data of the measured object.
  • the corresponding data identification and abnormality judgment can be performed according to the physical monitoring data, and corresponding alarms are generated for different abnormalities, thereby effectively monitoring the function.
  • the monitoring of ECG is more complicated than the monitoring of other vital signs such as blood pressure, blood oxygen, pulse, respiration, body temperature, etc. Therefore, in the present invention, the electrocardiogram data is different from other physical monitoring data.
  • the processing method specifically adopts the automatic analysis method of electrocardiogram based on artificial intelligence self-learning to identify, process and abnormally judge the electrocardiogram data.
  • steps 120-140 are processes for ECG data
  • steps 150 and 160 are processes for other vitality monitoring data such as pulse data, blood pressure data, respiratory data, blood oxygen saturation data, and body temperature data.
  • the two processes can be executed synchronously without the limitation of sequential execution.
  • Step 120 performing cluster feature recognition on the electrocardiogram data, obtaining a characteristic signal of the electrocardiogram data, performing heartbeat classification on the electrocardiogram data according to the characteristic signal, obtaining heartbeat classification information according to the basic rule reference data of the electrocardiogram, and generating ECG event data;
  • 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 heartbeat 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 ECG data is identified by the wave group feature, the characteristic signal of the electrocardiogram data is obtained, the heartbeat data is classified according to the characteristic signal, and the heartbeat classification information is obtained by combining the basic rule reference data of the electrocardiogram, and the ECG event data is generated specifically.
  • the following steps are implemented as shown in FIG. 2. This process is real-time, so the processing results can be obtained quickly and in real time.
  • Step 121 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. The low frequency baseline drift can be removed.
  • Step 122 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.
  • Multi-parameter monitors are often recorded for long periods of time, and the amplitude and frequency of the beat signal in the process center are constantly changing, and in the disease state, this characteristic will be more powerful.
  • the threshold is set, 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, and 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 123 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 124 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 multi-parameter monitor is susceptible to interference due to various influences 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 interference data is also a major factor that causes 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 125 determining 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 of each of the above leads needs to determine the validity of the heartbeat data according to the detection confidence obtained in step 123 before merging.
  • 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 acquired time characterization data combination of the different lead heartbeat data should satisfy the following condition: the time characterization data of the heartbeat data combination contains at least one time characterization data of the heartbeat 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 126 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 seventh layers of the convolutional layer 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 127 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 128 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 129 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 under one primary classification information to obtain the heartbeat classification information;
  • the heartbeat classification information is analyzed and matched to generate ECG event data.
  • 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 130 Determine corresponding ECG event information according to the ECG event data, and determine whether the ECG event information is a preset ECG abnormal event information;
  • the ECG event information corresponding to different ECG events may be determined, such as event information corresponding to the ECG event, or event information further summarized based on the ECG event, for example, various conduction blocks Events are classified as anomalous events under the information of conduction block events.
  • the preset ECG abnormal event information is stored in the multi-parameter monitor, and the preset ECG abnormal event information is the corresponding event information of the ECG event that needs to generate an alarm, that is, an abnormal electrocardiogram that needs to generate an alarm. Event information for the event. These information can be stored locally in the multi-parameter monitor or stored in the memory of the multi-parameter monitor or in the network's memory, which can be obtained by the multi-parameter monitor.
  • step 140 is performed.
  • ECG event data determines that the corresponding ECG event information is not the preset ECG abnormal event information, it indicates that there is no abnormal ECG condition that needs to generate an alarm, and the monitoring of Step 110 is continued.
  • Step 140 outputting first alarm information
  • the ECG event data determines that the corresponding ECG event information is preset ECG abnormal event information
  • the first alarm information is generated and output.
  • the first alarm information refers to the alarm information of the abnormality of the electrocardiogram, including the information of the abnormality of the electrocardiogram and the information of the alarm time. Therefore, the first alarm information is generated based on the ECG abnormal event information and the alarm time information.
  • the alarm time information may further be information about the time when the electrocardiographic abnormal event occurs, that is, the time information obtained from the time attribute information, or may be the information that the ECG event information is determined to be the preset ECG abnormal event information after processing the electrocardiogram data. System time information.
  • the ECG abnormal event information has corresponding project information, that is, an ECG project, which can indicate that the abnormal event is an ECG event.
  • the types of alarms that can generate alarm information output according to the present invention include, but are not limited to:
  • the above process realizes the data analysis processing of the electrocardiogram data to the abnormal alarm output.
  • the output of the first alarm information may be output locally on the display of the multi-parameter monitor, or may be locally printed and output by the multi-parameter monitor, and may also be transmitted to the receiving end through a network, such as a workstation or a server (specifically, such as a mobile device) ) to meet different usage needs.
  • a network such as a workstation or a server (specifically, such as a mobile device)
  • Step 150 Determine whether one or more of pulse data, blood pressure data, respiratory data, blood oxygen saturation data, and body temperature data have abnormal data exceeding a corresponding set threshold;
  • step 150 and steps 120-140 may be performed in parallel or in any order, and there is no strict sequence between the two.
  • a corresponding parameter threshold may be set.
  • the parameter threshold of each parameter can have different sets of parameter thresholds, which can be selected according to the actual situation of the monitored person.
  • the monitoring reference data may be determined in advance according to the measured object before monitoring, and then the corresponding set threshold is determined based on the monitoring reference data.
  • the setting of the threshold value of the pulse data and respiratory data of the newborn is higher than that of the ordinary adult.
  • the appropriate parameter threshold can be selected according to the needs, so that the multi-parameter monitor can be very good. Match the monitored person to achieve effective monitoring and accurate alarm.
  • step 160 is performed; otherwise, step 110 is continued to continue the physical sign detection.
  • Step 160 Generate other abnormal event information according to the abnormal data, and output second alarm information
  • other abnormal event information is generated according to the specific excess item.
  • the other abnormal event information has corresponding item information, which is used to indicate which item has abnormal data.
  • the second alarm information refers to the alarm information of the above other abnormal events except the abnormality of the electrocardiogram, including other abnormal event information and alarm time information. Therefore, the second alarm information is generated based on other abnormal event information and alarm time information.
  • the alarm time information may further be information about the time when other abnormal events occur, that is, the time information obtained from the time attribute information, or may be determined by processing other vital signs data other than the electrocardiogram data to determine other abnormalities in the monitoring data. Information about the system time of the event.
  • the output of the second alarm information can be output locally on the display of the multi-parameter monitor, or printed locally by the multi-parameter monitor, and can also be transmitted to the receiving end through a network, such as a workstation or a server (specifically, such as moving Equipment) to meet different usage needs.
  • a network such as a workstation or a server (specifically, such as moving Equipment) to meet different usage needs.
  • the multi-parameter monitoring data analysis method of the present invention can also record data before and after the occurrence of an abnormal event, so that the abnormality analysis can be conveniently performed.
  • the multi-parameter monitoring data analysis method of the present invention can also summarize the vital sign monitoring data based on the time attribute information of the vital sign monitoring data, generate time series data of the vital sign monitoring data, and store it.
  • the ECG data in the preset time period before and after the abnormal event occurrence time is acquired according to the time attribute information corresponding to the abnormal event information, and the abnormal event record data is generated.
  • the association information of the abnormal event record data and the first alarm information is generated and stored.
  • the length of the preset time period can be set as needed, and is preferably 36 seconds in this embodiment.
  • the record of the first alarm information is displayed in the event list column on the user interface of the multi-parameter monitor.
  • the multi-parameter monitor receives Go to the first alarm information review command; at this time, according to the clicked record corresponding to the first alarm information, and according to the abnormal event record data and the first alarm information associated information query to obtain the first alarm information associated with the abnormal event record data.
  • abnormal event record data can also be analyzed and processed, and abnormal event report data is generated and output.
  • the report data output abnormal event and the detailed description of the abnormal event may include, but are not limited to, each abnormal parameter, the occurrence time, the analysis result based on the abnormal parameter, and the like, and the data may be played in a graphical manner, such as electrocardiogram data. Graphical playback and so on.
  • the parameters before and after the generation of the second alarm information may be recorded in the same manner for convenient analysis and judgment, and details are not described herein again.
  • the alarm event data includes the item information of the vital sign monitoring data and the corresponding ECG abnormal event information and/or other abnormal event information.
  • FIG. 6 is a schematic structural diagram of a multi-parameter monitor 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 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 data monitor also preferably includes an output device, specifically a display, a printer or a network interface device, for displaying, outputting, transmitting, etc. data.
  • an output device specifically a display, a printer or a network interface device, for displaying, outputting, transmitting, etc. data.
  • 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 multi-parameter monitoring data analysis method and the multi-parameter monitor provided by the embodiments of the invention can automatically, quickly and completely analyze the physical data such as electrocardiogram, blood pressure, blood oxygen, pulse, respiration and body temperature monitored by the multi-parameter monitor. It provides early warning of abnormal ECG status, abnormal parameters of other physical signs, and the combination of the two, and can reduce the false positive phenomenon caused by interference.
  • the alarm accuracy is high, and the types of abnormalities that can be detected are especially the types of abnormalities of the electrocardiogram, and the ECG data can be dynamically played back and output according to the instructions.
  • the multi-parameter monitoring data analysis method and the related multi-parameter monitor of the invention have wide application range and good application prospect.
  • 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)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Surgery (AREA)
  • Medical Informatics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Cardiology (AREA)
  • Physiology (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Psychiatry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Pulmonology (AREA)
  • Vascular Medicine (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Optics & Photonics (AREA)
  • Fuzzy Systems (AREA)
  • Ophthalmology & Optometry (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

一种多参数监护数据分析方法和监护仪。方法包括:对被测对象进行体征监护数据采集,得到被测对象的体征监护数据(110);对采集到的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并生成心电图事件信息(120);确定心电图事件信息是否为预设的心电异常事件信息(130);当为心电异常事件信息时输出第一报警信息(140);以及确定脉搏数据、血压数据、呼吸数据、血氧饱和度数据和体温数据中的一个或多个是否存在超出相应的设定阈值的异常数据(150),并根据异常数据生成其它异常事件信息;当超出设定阈值时,输出第二报警信息(160)。

Description

多参数监护数据分析方法和多参数监护仪
本申请要求于2018年2月24日提交中国专利局、申请号为201810157159.2、发明名称为“多参数监护数据分析方法和多参数监护仪”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,尤其涉及一种多参数监护数据分析方法和多参数监护仪。
背景技术
多参数监护仪是一种常用的临床医疗设备。这种监护设备的特点是具有多组传感器,可以同时监测心电、血压、血氧、脉搏、呼吸、体温等生命体征指标。在病房监护中,多参数监护仪可以成为医生的对病人监护的重要参考,使医生能及时发现病人出现的问题并及时进行处理,从而保证了病人的生命安全。监护仪临床应用可见于:手术中、手术后、外伤护理、冠心病、危重病人、新生儿、早产儿、高压氧舱、分娩室等。
目前市场上大多数多参数监控仪采用设置阈值的方式进行报警事件的触发。比如在心率过快的时候进行报警或是在心率过缓的时候进行报警。这种设置阈值的方法虽然简单直观,但准确性比较差,因为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,从而触发警报。这些频繁发生的误报,久而久之导致病人和医护人员放松对警报事件 的警惕,而在真正的需要临床处理的事件出现时病人得不到有效的关注和处理。同时,医生和护士会花费大量的精力在处理误报事件上,浪费医院的医疗资源。根据美国心脏协会的数据,在发生心脏骤停的住院患者中,只有不到四分之一可以存活下来。
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,很多时候不一定体现在心率上。目前的多参数监护设备只能对心电信号进行非常有限的分析和报警,这也导致有大量的漏报事件发生,病人的生命健康不能得到有效的保护。
发明内容
本发明的目的是提供一种为解决现有技术缺陷而提出的多参数监护数据分析方法和多参数监护仪。
本发明实施例第一方面提供了一种多参数监护数据分析方法,包括:
对被测对象进行体征监护数据采集,得到所述被测对象的体征监护数据;所述体征监护数据具有时间属性信息,所述体征监护数据包括:心电图数据、脉搏数据、血压数据、呼吸数据、血氧饱和度数据和体温数据;
对所述心电图数据进行波群特征识别,得到所述心电图数据的特征信号,根据所述特征信号对所述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,并生成心电图事件数据;
根据所述心电图事件数据确定对应的心电图事件信息,并确定所述心电图事件信息是否为预设的心电异常事件信息;当为预设的心电异常事件信息时,输出第一报警信息;所述第一报警信息包括所述心电异常事件信息和报警时间信息;所述心电异常事件信息具有对应的项目信息;以及
确定所述脉搏数据、血压数据、呼吸数据、血氧饱和度数据和体温数据中的一个或多个是否存在超出相应的设定阈值的异常数据,并根据所述异常 数据生成其他异常事件信息;当超出所述设定阈值时,输出第二报警信息;所述第二报警信息包括所述其他异常事件信息和报警时间信息;所述其他异常事件信息具有对应的项目信息。
优选的,所述方法还包括:
根据所述体征监护数据的时间属性信息对所述体征监护数据进行汇总,生成所述体征监护数据的时间序列数据,并进行存储。
优选的,所述方法还包括:
当为预设的心电异常事件信息时,根据所述时间属性信息获取所述心电图数据对应时间的前后预设时段内的心电图数据,生成异常事件记录数据;
生成所述异常事件记录数据与所述第一报警信息的关联信息。
进一步优选的,在所述输出第一报警信息之后,所述方法还包括:
接收对所述第一报警信息的查阅指令;
根据所述关联信息获取所述异常事件记录数据并进行输出。
进一步优选的,所述方法还包括:
对所述异常事件记录数据进行分析处理,生成并输出异常事件报告数据。
优选的,所述方法还包括:
根据所述第一报警信息和第二报警信息生成报警事件数据;
根据所述报警时间信息,对所述报警事件数据进行输出显示;其中,所述报警事件数据包括体征监护数据的项目信息以及所对应的心电异常事件信息和/或其他异常事件信息。
优选的,所述对所述心电图数据进行波群特征识别,得到所述心电图数据的特征信号,根据所述特征信号对所述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,并生成心电图事件数据具体包括:
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波的幅值和起止时间数据;
根据所述心搏数据确定每个心搏的检测置信度;
根据干扰识别二分类模型对所述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;
根据所述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;
根据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;
根据所述心搏时间序列数据,对所述心搏分析数据进行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,详细特征信息包括幅值、方向、形态和起止时间的数据;
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、所述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;
对所述心搏分类信息进行分析匹配,生成所述心电图事件数据。
优选的,在对被测对象进行体征监护数据采集,得到所述被测对象的体征监护数据之前,所述方法还包括:
根据所述被测对象确定监测基准数据;
根据所述监测基准数据确定所述设定阈值。
本发明实施例提供的多参数监护数据分析方法,实现了基于人工智能的多参数监护的数据分析和报警流程,能够对监测得到的测量数据进行自动、快速、完整的分析,对异常的心电状态和其他生命体征参数给出预警,并减少 干扰带来的误报现象,报警准确度高,可检测的异常种类特别是心电异常的种类多,具有良好的应用前景。
本发明实施例第二方面提供了一种多参数监护仪,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多参数监护数据分析方法流程图;
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多参数监护仪的结构示意图。
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。
本发明涉及用于临床监护的多参数监护数据分析方法,以及执行该方法的多参数监护仪。多参数监护仪是一种临床医疗监护设备。这种监护设备的特点是具有多组传感器,可以同时监测心电、血压、血氧、脉搏、呼吸、体温等生命体征指标,通过实时处理从各个传感器传入的数据,在相应指标出现 异常的时候给出报警信号,使医生护士可以及时对病情进行处理。
多参数监护仪检测的心电、血压、血氧、脉搏、呼吸、体温等生命体征指标中,心电的监测是不同于其他各项参数的,通过传感器得到的心电信号需要通过一系列复杂的算法计算才能提取出其中的有效信息,相对其他信号而言处理过程比较复杂困难,也是容易出现检测错误的环节。
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。在对业内现有的多参数监护设备进行研究的过程中我们发现,现有的监护设备只能对心电信号进行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。
为此,本发明提出了一种多参数监护数据分析方法,其方法步骤流程如图1所示,该方法主要包括如下步骤:
步骤110,对被测对象进行体征监护数据采集,得到被测对象的体征监护数据;
具体的,被测对象是指由多参数监护仪进行床旁监护的生命体,其中,最常规的被测对象是指人。
监护仪具有与被测对象相接触的电极、探头、袖带等体征信号采集装置,通过体征信号采集装置采集被测对象的体征信号,并通过数字化处理得到体征监护数据。体征监护数据可以具体包括:心电图数据、脉搏数据、血压数据、呼吸数据、血氧饱和度数据和体温数据等。体征监护数据具有时间属性信息,每个数据点都有对应的数据采集时间,这个时间即是时间属性信息。在进行数据采集的同时,这个数据采集时间也被记录下来,并作为体征监护数据的时间属性信息进行存储。
为更好地理解本发明的意图和实现方式,下面对各类体征监护数据的采集方法和原理进行简要介绍说明:
心电图数据:通过无创心电图检查的心电信号采集记录仪队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。
脉搏数据:脉搏是动脉血管随心脏舒缩而周期性搏动的现象,脉搏包含血管内压、容积、位移和管壁张力等多种物理量的变化。我们优选的采用光电容积式脉搏测量,传感器由光源和光电变换器两部分组成,可夹在被测者的指尖或耳廓上。光源选择对动脉血中氧合血红蛋白有选择性的波长,比如采用光谱在700-900nm的发光二极管。这束光透过人体外周血管,当动脉充血容积变化时,改变了这束光的透光率,由光电变换器接收经组织透射或反射的光,转变为电信号送放大器放大和输出,由此反映动脉血管的容积变化。 脉搏是随心脏的搏动而周期性变化的信号,动脉血管容积也周期性地变化,光电变换器的信号变化周期就是脉搏率,即脉搏数据。
血压数据:心脏收缩时所达到的最高压力称为收缩压,它把血液推进到主动脉,并维持全身循环。心脏扩张时所达到的最低压力称为舒张压,它使血液能回流到右心房。血压波形在一周内的积分除以心周期T称为平均压。血压数据的测量有多种方法可实现,具体可分为有创测量和无创测量。在多参数监护仪中我们优选采用柯氏音法和测振法两类无创测量方法。柯氏音法是检测袖带下的柯氏音(脉搏声)来测定血压的,柯氏音无创血压监护系统包括袖带充气系统、袖带、柯氏音传感器、音频放大及自动增益调整电路、A/D转换器、微处理器及显示部分等。测振法是检测气袖内气体的振荡波,振荡波源于血管壁的搏动,测量振荡波的相关点就可测定血压数据,包括收缩压(PS),舒张压(PD)和平均压(PM)。测振法获得脉搏振动波的方法可借助微音器和压力传感器,通过测量得到脉搏振动波即得到血压数据。对于一些特殊的应用场景下,也可以通过有创测量的方式来获得血压数据。比如对于重症加强护理组(ICU)病房的一些病人进行监测,就可通过直接在动脉进行插管,将插管的另一端连接到消毒过的注满液体的压力检测系统中实现血压数据的实时采集。这种有创监测方法的优点包括:可以实时的显示出血压大小,并可以显示连续的血压变化波形;在低血压状态可以有准确的读数;长期记录的病人舒适度得到提升,避免无创测量中长期充气放气导致的创伤;可以提取出更多的信息,包括从血压波形的形态上可以推算出血管容量等。
呼吸数据:呼吸测量是肺动能检查的重要部分。监护仪通过测量呼吸波来测定呼吸频率(次/分钟),即得到呼吸数据。呼吸频率的测量可通过热敏电阻直接测量呼吸气流的温度变化,经过电桥电路将这一变化变换成电压信号;也可采用阻抗法来测量呼吸频率,因为呼吸运动时,胸壁肌肉交变张驰,胸廓交替变形,肌体组织的电阻抗也随之交替变化。测量呼吸阻抗值的变化可采用电桥法、调制法、恒压源法和恒流源法等多种方式。在监护仪中,呼吸 阻抗电极亦可与心电电极合用,检测心电信号时可同时检测呼吸阻抗变化和呼吸频率。
血氧饱和度数据:血氧饱和度是衡量人体血液携带氧的能力的重要参数。血氧饱和度的测量可以采用透射法(或反射法)双波长(红光R和红外光IR)光电检测技术,检测红光和红外光通过动脉血的光吸收引起的交变成分之比和非脉动组织(表皮、肌肉、静脉血等)引起光吸收的稳定分量(直流)值,通过计算可得到血氧饱和度值SpO2,即血氧饱和度数据。由于光电信号的脉动规律与心脏搏动的规律一致,所以根据检出信号的周期亦可同时确定脉搏数据。
体温数据:体温是了解生命状态的重要指标。体温的测量采用负温度系数的热敏电阻作为温度传感器,采用电桥作为检测电路。我们在具体的应用中可以采用集成化测温电路进行测量得到体温数据。亦可使用两道以上的测温电路,测量两个不同部位的温差对测量值进行修正。还可以采用体表探头和体腔探头,分别监护体表和腔内温度。在一些特殊的应用中,为了避免交叉传染,亦可以采用红外非接触测温技术来进行提问数据的监测。在监护仪中,我们设定测温精度在0.1℃,以便有较快的测温响应。
在本发明中,我们可以通过上述方法,使用多参数监护仪对被测对象进行体征监护数据采集,得到被测对象的体征监护数据。
在得到体征监护数据之后,就可以根据体征监护数据进行相应的数据识别和异常判断,并针对不同的异常,产生相应的报警,起到有效的监护作用。
在前面已经提到,心电的监测相对于其他血压、血氧、脉搏、呼吸、体温等生命体征指标的监测更为复杂,因此在本发明中对于心电图数据采用了不同于其他体征监护数据的处理方法,具体采用基于人工智能自学习的心电图自动分析方法进行心电图数据的识别、处理和异常判断。
如下步骤120-步骤140是针对心电图数据的处理过程,步骤150和步骤160是针对脉搏数据、血压数据、呼吸数据、血氧饱和度数据和体温数据等其 他体征监护数据的处理过程。两个处理过程可以同步执行,没有先后执行顺序的限制。
步骤120,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,并生成心电图事件数据;
具体的,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,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,并生成心电图事件数据具体可以通过如图2所示的如下步骤来实现。该处理过程是实时的,因此可以迅速实时的获得处理结果。
步骤121,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122,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。
多参数监护仪往往是进行长时间记录,其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123,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124,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;
因为多参数监护仪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125,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123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126,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,不同动态心电图设备在信号测量、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127,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128,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129,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;以及对心搏分类信息进行分析匹配,生成心电图事件数据。
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130,根据心电图事件数据确定对应的心电图事件信息,并确定心电图事件信息是否为预设的心电异常事件信息;
具体的,根据心电图事件数据,可以确定对应不同心电图事件的心电图事件信息,比如可以是对应上述心电图事件的事件信息,也可以是基于上述心电图事件进一步汇总的事件信息,例如将各种传导阻滞事件归类为传导阻滞事件信息下的异常事件。
在多参数监护仪中存储有预设的心电异常事件信息,预设的心电异常事件 信息,即为需要产生报警的心电图事件的对应的事件信息,也就是需要产生报警的非正常的心电图事件的事件信息。这些信息经过预设设定,可以存储在多参数监护仪本地,也可以存储在多参数监护仪接入的系统或者网络的存储器中,可以被多参数监护仪获取得到。
当心电图事件数据确定对应的心电图事件信息为预设的心电异常事件信息时,执行步骤140。
如果心电图事件数据确定对应的心电图事件信息不是预设的心电异常事件信息,则说明没有需要产生报警的异常心电状况发生,继续持续进行步骤110的监测。
步骤140,输出第一报警信息;
具体的,当心电图事件数据确定对应的心电图事件信息为预设的心电异常事件信息时,生成并输出第一报警信息。
第一报警信息就是指心电异常事件的报警信息,其中包括心电异常事件信息和报警时间信息。因此第一报警信息是根据心电异常事件信息和报警时间信息生成的。报警时间信息进一步的可以是心电异常事件发生的时间的信息,即从时间属性信息中获得的时间信息,也可以是对心电图数据进行处理后确定心电图事件信息为预设的心电异常事件信息的系统时间的信息。
为进行不同参数区分,心电异常事件信息具有对应的项目信息,即心电项目,能够表明该异常事件是心电事件。
本发明能够产生报警信息输出的报警类型包括但不限于:
1、窦性心率事件:
a)窦性心动过速
b)窦性心动过缓
2、室上性心动过速
a)房性心动过速
b)房扑
c)房颤
d)房室折返
3、室性心动过速
a)单纯性室性心动过速
b)多形性室性心动过速
c)双向性室性心动过速
d)扭转性室性心动过速
e)早搏性室性心动过速
f)室扑
g)室颤
4、ST-T段改变
a)R-on-t室性早搏
b)R-on-P室性早搏
c)交替出现宽大T波
5、传导阻滞
a)高二度传导阻滞
b)三度传导阻滞
以上即实现了心电图数据的数据分析处理到异常报警输出的过程。
其中,第一报警信息的输出可以在多参数监护仪的显示器上本地输出,或者由多参数监护仪本地打印输出,还可以通过网络传送到接收端,比如工作站或服务端(具体可以如移动设备),以满足不同的使用需求。
步骤150,确定脉搏数据、血压数据、呼吸数据、血氧饱和度数据和体温数据中的一个或多个是否存在超出相应的设定阈值的异常数据;
在实际数据处理的过程中,步骤150与步骤120-140可以并行执行,或者任意先后执行,二者之间并无严格的先后顺序。
具体的,对于脉搏数据、血压数据、呼吸数据、血氧饱和度数据和体温数 据,可以设置有相应的参数阈值。每个参数的参数阈值都可以有不同的多组参数阈值,可以根据被监测者的实际情况进行选择。
优选的,在本发明中,可以在监测前预先根据被测对象确定监测基准数据,然后根据监测基准数据确定相应的设定阈值。
比如,对于新生儿的脉搏数据、呼吸数据的参数阈值的设定,比普通成年人的要高,在实际应用中可以根据需要选择相应的适合的参数阈值,使得多参数监护仪能够很好的匹配被监测者,达到有效监测、准确报警的目的。
当发生上述体征监护数据中的一项或多项超出设定阈值时,执行步骤160;否则继续执行步骤110,继续进行体征检测。
步骤160,根据异常数据生成其他异常事件信息,并输出第二报警信息;
具体的,当脉搏数据、血压数据、呼吸数据、血氧饱和度数据和体温数据有超出相应设定参数范围的数据时,根据具体的超出项生成其他异常事件信息。其中,其他异常事件信息具有对应的项目信息,用于指示是哪个项目的数据出现了异常。比如脉搏、血压、呼吸、血氧或体温等。
第二报警信息就是指除心电异常外的上述其它异常事件的报警信息,其中包括其他异常事件信息和报警时间信息。因此第二报警信息是根据其他异常事件信息和报警时间信息生成的。报警时间信息进一步的可以是其它异常事件发生的时间的信息,即从时间属性信息中获得的时间信息,也可以是对除心电图数据外的其它体征数据进行处理后确定这些监测数据中存在其它异常事件的系统时间的信息。
同样的,第二报警信息的输出可以在多参数监护仪的显示器上本地输出,或者由多参数监护仪本地打印输出,还可以通过网络传送到接收端,比如工作站或服务端(具体可以如移动设备),以满足不同的使用需求。
此外,本发明的多参数监护数据分析方法,还能够对异常事件发生前后的数据进行记录,以便于能够方便的进行异常分析。
为此,本发明的多参数监护数据分析方法还能够根据体征监护数据的时间 属性信息对体征监护数据进行汇总,生成体征监护数据的时间序列数据,并进行存储。
在判断到发生有与预设的心电异常事件信息相应的异常事件时,根据异常事件信息所对应的时间属性信息获取异常事件发生时间的前后预设时段内的心电图数据,生成异常事件记录数据,同时生成异常事件记录数据与第一报警信息的关联信息,并存储。该预设时间段的长短可以根据需要设定,在本实施例中优选为36秒。
在输出第一报警信息后,多参数监护仪的用户界面上事件列表栏中会显示有第一报警信息的记录,当用户通过触摸屏或鼠标等可操作设备点击该记录时,多参数监护仪接收到第一报警信息的查阅指令;此时,根据被点击的记录对应到第一报警信息,并根据异常事件记录数据与第一报警信息的关联信息查询获取到第一报警信息关联的异常事件记录数据。
在本方案中,还可以对异常事件记录数据进行分析处理,生成并输出异常事件报告数据。通过报告数据输出异常事件以及对异常事件的详细描述,具体可以包括但不限于各异常参数、发生时间、基于异常参数的分析结果等等,并可以将数据以图形化方式进行播放,比如心电图数据的图形化回放等。
同样的,对于第二报警信息产生时,也可以以同样方法,记录第二报警信息产生前后的各参数,用以方便的进行分析判断,此处不再赘述。
进一步的,还可以根据心电图数据、脉搏数据、血压数据、呼吸数据、血氧饱和度数据和体温数据等各参数进行综合考量,根据第一报警信息和第二报警信息生成报警事件数据,然后根据报警时间信息,对报警事件数据进行输出显示;报警事件数据包括体征监护数据的项目信息以及所对应的心电异常事件信息和/或其他异常事件信息。
图6为本发明实施例提供的一种多参数监护仪的结构示意图,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。
该数据监护仪还优选的包括有输出设备,具体可以是显示器、打印机或网络接口设备等,用以数据的显示、输出、传输等。
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多参数监护数据分析方法和多参数监护仪,能够对多参数监护仪监测的心电、血压、血氧、脉搏、呼吸、体温等体征数据进行自动、快速、完整的分析,对异常的心电状态、其他各项体征的异常参数,以及二者结合给出预警,并能减少干扰带来的误报现象。报警准确度高,可检测的异常种类特别是心电异常的种类多,并能够根据指令对心电数据进行动态的回放输出。本发明的多参数监护数据分析方法及相关的多参数监护仪适用范围广,具有良好的应用前景。
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 (11)

  1. 一种多参数监护数据分析方法,其特征在于,所述方法包括:
    对被测对象进行体征监护数据采集,得到所述被测对象的体征监护数据;所述体征监护数据具有时间属性信息,所述体征监护数据包括:心电图数据、脉搏数据、血压数据、呼吸数据、血氧饱和度数据和体温数据;
    对所述心电图数据进行波群特征识别,得到所述心电图数据的特征信号,根据所述特征信号对所述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,并生成心电图事件数据;
    根据所述心电图事件数据确定对应的心电图事件信息,并确定所述心电图事件信息是否为预设的心电异常事件信息;当为预设的心电异常事件信息时,输出第一报警信息;所述第一报警信息包括所述心电异常事件信息和报警时间信息;所述心电异常事件信息具有对应的项目信息;以及
    确定所述脉搏数据、血压数据、呼吸数据、血氧饱和度数据和体温数据中的一个或多个是否存在超出相应的设定阈值的异常数据,并根据所述异常数据生成其他异常事件信息;当超出所述设定阈值时,输出第二报警信息;所述第二报警信息包括所述其他异常事件信息和报警时间信息;所述其他异常事件信息具有对应的项目信息。
  2. 根据权利要求1所述的多参数监护数据分析方法,其特征在于,所述方法还包括:
    根据所述体征监护数据的时间属性信息对所述体征监护数据进行汇总,生成所述体征监护数据的时间序列数据,并进行存储。
  3. 根据权利要求1所述的多参数监护数据分析方法,其特征在于,所述方法还包括:
    当为预设的心电异常事件信息时,根据所述时间属性信息获取所述心电图数据对应时间的前后预设时段内的心电图数据,生成异常事件记录数据;
    生成所述异常事件记录数据与所述第一报警信息的关联信息。
  4. 根据权利要求3所述的多参数监护数据分析方法,其特征在于,在所述输出第一报警信息之后,所述方法还包括:
    接收对所述第一报警信息的查阅指令;
    根据所述关联信息获取所述异常事件记录数据并进行输出。
  5. 根据权利要求4所述的多参数监护数据分析方法,其特征在于,所述方法还包括:
    对所述异常事件记录数据进行分析处理,生成并输出异常事件报告数据。
  6. 根据权利要求1所述的多参数监护数据分析方法,其特征在于,所述方法还包括:
    根据所述第一报警信息和第二报警信息生成报警事件数据;
    根据所述报警时间信息,对所述报警事件数据进行输出显示;其中,所述报警事件数据包括体征监护数据的项目信息以及所对应的心电异常事件信息和/或其他异常事件信息。
  7. 根据权利要求1所述的多参数监护数据分析方法,其特征在于,所述对所述心电图数据进行波群特征识别,得到所述心电图数据的特征信号,根据所述特征信号对所述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,并生成心电图事件数据具体包括:
    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波的幅值和起止时间数据;
    根据所述心搏数据确定每个心搏的检测置信度;
    根据干扰识别二分类模型对所述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;
    根据所述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;
    根据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;
    根据所述心搏时间序列数据,对所述心搏分析数据进行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,详细特征信息包括幅值、方向、形态和起止时间的数据;
    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、所述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;
    对所述心搏分类信息进行分析匹配,生成所述心电图事件数据。
  8. 根据权利要求1所述的多参数监护数据分析方法,其特征在于,在对被测对象进行体征监护数据采集,得到所述被测对象的体征监护数据之前,所述方法还包括:
    根据所述被测对象确定监测基准数据;
    根据所述监测基准数据确定所述设定阈值。
  9. 一种多参数监护仪,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8任一项所述的方法。
  10. 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8任一项所述的方法。
  11. 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8任一项所述的方法。
PCT/CN2018/083463 2018-02-24 2018-04-18 多参数监护数据分析方法和多参数监护仪 WO2019161609A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810157159.2 2018-02-24
CN201810157159.2A CN108309262A (zh) 2018-02-24 2018-02-24 多参数监护数据分析方法和多参数监护仪

Publications (1)

Publication Number Publication Date
WO2019161609A1 true WO2019161609A1 (zh) 2019-08-29

Family

ID=62900367

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/083463 WO2019161609A1 (zh) 2018-02-24 2018-04-18 多参数监护数据分析方法和多参数监护仪

Country Status (2)

Country Link
CN (1) CN108309262A (zh)
WO (1) WO2019161609A1 (zh)

Families Citing this family (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110393520B (zh) * 2018-11-16 2022-03-29 迪姆软件(北京)有限公司 一种心电数据分析方法及装置、心电分析仪、存储介质
WO2020132816A1 (zh) * 2018-12-24 2020-07-02 深圳迈瑞生物医疗电子股份有限公司 一种应用于监护设备的显示方法及监护设备
CN110693483A (zh) * 2019-09-02 2020-01-17 乐普智芯(天津)医疗器械有限公司 一种动态心电图自动分析的方法
CN110867248A (zh) * 2019-11-13 2020-03-06 秒针信息技术有限公司 一种术后监测方法和装置
CN111067512B (zh) * 2019-12-05 2023-01-31 东软集团股份有限公司 心室颤动的检测装置、检测模型的训练装置、方法及设备
CN111259820B (zh) * 2020-01-17 2023-05-05 上海乐普云智科技股份有限公司 一种基于r点的心搏数据分类方法和装置
CN111358459A (zh) * 2020-02-11 2020-07-03 广州视源电子科技股份有限公司 一种心律失常识别方法、装置、设备和存储介质
CN113712570B (zh) * 2020-05-12 2024-03-08 深圳市科瑞康实业有限公司 一种长间歇心电信号数据预警方法
CN113647903B (zh) * 2020-05-12 2022-08-26 深圳市科瑞康实业有限公司 一种报警切换方法
CN113786200B (zh) * 2020-05-28 2022-10-11 深圳邦健生物医疗设备股份有限公司 心电信号处理方法、装置、设备及可读介质
CN113768511B (zh) * 2020-06-04 2023-09-22 深圳市理邦精密仪器股份有限公司 生理参数检测方法及电子设备
CN114533013B (zh) * 2020-11-26 2024-02-06 深圳市科瑞康实业有限公司 一种对连续获取的心搏数据进行处理的方法
CN113768516B (zh) * 2021-09-27 2024-05-14 吉林省辰一科技有限公司 一种基于人工智能的心电图异常程度检测方法及系统
CN114668401B (zh) * 2022-03-11 2023-04-18 肇庆星网医疗科技有限公司 一种ai心电训练数据标注方法、装置、电子设备及介质
CN114760440A (zh) * 2022-03-22 2022-07-15 浙江大学 一种可视化监视眼镜
CN116153505B (zh) * 2023-04-21 2023-08-18 苏州森斯缔夫传感科技有限公司 基于医用压力传感器的危重病人体征智能识别方法及系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100022902A1 (en) * 2008-07-25 2010-01-28 Brian Bruce Lee Virtual Physician Acute Myocardial Infarction Detection System and Method
CN101677770A (zh) * 2007-06-20 2010-03-24 高通股份有限公司 个人虚拟助理
CN101822535A (zh) * 2010-03-11 2010-09-08 无锡凌讯科技有限公司 Rfid远程无线家庭医疗监护仪
US20100274098A1 (en) * 2008-10-23 2010-10-28 Edwards Lifesciences Corporation Patient Monitoring System
CN102068261A (zh) * 2011-01-21 2011-05-25 上海弘周电子科技有限公司 安全监护仪
CN107714023A (zh) * 2017-11-27 2018-02-23 乐普(北京)医疗器械股份有限公司 基于人工智能自学习的静态心电图分析方法和装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101677770A (zh) * 2007-06-20 2010-03-24 高通股份有限公司 个人虚拟助理
US20100022902A1 (en) * 2008-07-25 2010-01-28 Brian Bruce Lee Virtual Physician Acute Myocardial Infarction Detection System and Method
US20100274098A1 (en) * 2008-10-23 2010-10-28 Edwards Lifesciences Corporation Patient Monitoring System
CN101822535A (zh) * 2010-03-11 2010-09-08 无锡凌讯科技有限公司 Rfid远程无线家庭医疗监护仪
CN102068261A (zh) * 2011-01-21 2011-05-25 上海弘周电子科技有限公司 安全监护仪
CN107714023A (zh) * 2017-11-27 2018-02-23 乐普(北京)医疗器械股份有限公司 基于人工智能自学习的静态心电图分析方法和装置

Also Published As

Publication number Publication date
CN108309262A (zh) 2018-07-24

Similar Documents

Publication Publication Date Title
WO2019161609A1 (zh) 多参数监护数据分析方法和多参数监护仪
WO2019161608A1 (zh) 多参数监护数据分析方法和多参数监护系统
CN108577830B (zh) 一种面向用户的体征信息动态监护方法和动态监护系统
JP6567728B2 (ja) 患者の生存性を予測する方法
Miao et al. Multi-sensor fusion approach for cuff-less blood pressure measurement
Esmaelpoor et al. A multistage deep neural network model for blood pressure estimation using photoplethysmogram signals
CN108478209B (zh) 心电信息动态监护方法和动态监护系统
Surrel et al. Online obstructive sleep apnea detection on medical wearable sensors
Charlton et al. Breathing rate estimation from the electrocardiogram and photoplethysmogram: A review
CN106413534B (zh) 连续血压测量装置、测量模型建立方法和系统
Tjahjadi et al. Noninvasive classification of blood pressure based on photoplethysmography signals using bidirectional long short-term memory and time-frequency analysis
Maqsood et al. A survey: From shallow to deep machine learning approaches for blood pressure estimation using biosensors
US20180064354A1 (en) Analysis and Characterization of Patient Signals
US11617545B2 (en) Methods and systems for adaptable presentation of sensor data
CN110897631A (zh) 孕产实时监测装置及方法
Kanawade et al. Photoplethysmography based arrhythmia detection and classification
Kılıçkaya et al. Comparison of different machine learning techniques for the cuffless estimation of blood pressure using PPG signals
Lin et al. Energy-efficient blood pressure monitoring based on single-site photoplethysmogram on wearable devices
Argha et al. Blood pressure estimation from korotkoff sound signals using an end-to-end deep-learning-based algorithm
US10327648B2 (en) Blood vessel mechanical signal analysis
Ghosh et al. Introduction of boosting algorithms in continuous non-invasive cuff-less blood pressure estimation using pulse arrival time
Yu et al. An unobtrusive stress recognition system for the smart office
US20230062753A1 (en) Apparatus and method for electrocardiogram ("ecg") signal analysis and artifact detection
Zhang et al. Cascade forest regression algorithm for non-invasive blood pressure estimation using PPG signals
Wang et al. Heart action monitoring from pulse signals using a growing hybrid polynomial network

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18907008

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18907008

Country of ref document: EP

Kind code of ref document: A1