WO2024082231A1 - 监测心血管参数的方法和医疗设备 - Google Patents

监测心血管参数的方法和医疗设备 Download PDF

Info

Publication number
WO2024082231A1
WO2024082231A1 PCT/CN2022/126515 CN2022126515W WO2024082231A1 WO 2024082231 A1 WO2024082231 A1 WO 2024082231A1 CN 2022126515 W CN2022126515 W CN 2022126515W WO 2024082231 A1 WO2024082231 A1 WO 2024082231A1
Authority
WO
WIPO (PCT)
Prior art keywords
cardiovascular
arterial pressure
cardiovascular parameter
monitoring data
model
Prior art date
Application number
PCT/CN2022/126515
Other languages
English (en)
French (fr)
Inventor
孙白雷
何先梁
谈帆
罗圣文
Original Assignee
深圳迈瑞生物医疗电子股份有限公司
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 深圳迈瑞生物医疗电子股份有限公司 filed Critical 深圳迈瑞生物医疗电子股份有限公司
Priority to PCT/CN2022/126515 priority Critical patent/WO2024082231A1/zh
Publication of WO2024082231A1 publication Critical patent/WO2024082231A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/021—Measuring pressure in heart or blood vessels
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/026—Measuring blood flow
    • A61B5/029—Measuring or recording blood output from the heart, e.g. minute volume

Definitions

  • the present application relates to the field of medical devices, and more specifically to a method and a medical device for monitoring cardiovascular parameters.
  • Cardiac output refers to the amount of blood ejected per minute by the left or right ventricle, and is one of the important indicators for evaluating cardiac function.
  • the gold standard for cardiac output monitoring is the thermodilution monitoring method of right heart catheterization, but the monitoring method of right heart catheterization is very traumatic to patients and has a high risk of complications. At the same time, it has high requirements for medical operations, which severely limits the promotion and use of cardiac output monitoring methods.
  • a first aspect of an embodiment of the present application provides a method for monitoring cardiovascular parameters, comprising:
  • a target estimation model suitable for the monitored subject from at least two cardiovascular parameter estimation models, wherein the at least two cardiovascular parameter estimation models have different model structure algorithm logics;
  • the target estimation model is applied to estimate the cardiovascular parameters of the monitored subject based on the arterial pressure monitoring data.
  • a second aspect of an embodiment of the present application provides a medical device, which includes a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program, when executed by the processor, executes the steps of the method for monitoring cardiovascular parameters as described above.
  • a target estimation model suitable for the monitored object is selected from at least two different cardiovascular parameter estimation models to estimate the cardiovascular parameters of the monitored object, thereby improving the accuracy of cardiovascular parameter monitoring.
  • FIG1 is a schematic flow chart showing a method for monitoring cardiovascular parameters according to an embodiment of the present application.
  • FIG2A shows an equivalent circuit model of a cardiovascular system according to another embodiment of the present application.
  • FIG2B shows an equivalent circuit model of a cardiovascular system according to another embodiment of the present application.
  • FIG2C shows an equivalent circuit model of a cardiovascular system according to another embodiment of the present application.
  • FIG3 shows a schematic block diagram of a medical device according to an embodiment of the present application.
  • the present application can be implemented in a variety of different forms and is not limited to the embodiments described in this embodiment.
  • the purpose of providing the following specific embodiments is to facilitate a clearer and more thorough understanding of the disclosure of the present application, wherein the words indicating the orientation such as upper, lower, left, right, etc. are only for the position of the structure shown in the corresponding drawings.
  • FIG. 1 is a schematic flow chart of a method 100 for monitoring cardiovascular parameters according to an embodiment of the present application.
  • the method 100 for monitoring cardiovascular parameters according to an embodiment of the present application includes the following steps:
  • step S110 arterial pressure monitoring data of the monitored object and personal attribute information of the monitored object are obtained;
  • a target estimation model suitable for the monitored subject is selected from at least two cardiovascular parameter estimation models, wherein the at least two cardiovascular parameter estimation models have different model structure algorithm logics;
  • step S130 the target estimation model is applied to estimate the cardiovascular parameters of the monitored subject according to the arterial pressure monitoring data.
  • a target estimation model suitable for the monitored object is selected from at least two different cardiovascular parameter estimation models to estimate the cardiovascular parameters of the monitored object, thereby improving the accuracy of cardiovascular parameter monitoring.
  • the method 100 for monitoring cardiovascular parameters of the embodiment of the present application can be implemented in a monitoring device.
  • the cardiovascular parameters obtained based on the method 100 for monitoring cardiovascular parameters can be output by the monitoring device, for example, they can be displayed on the monitoring interface of the monitoring device; the monitoring device can also monitor whether the cardiovascular parameters are within a preset threshold range, and generate an alarm message when the cardiovascular parameters exceed the preset threshold range.
  • the offline evaluation method 100 of the embodiment of the present application can also be implemented in a central station, a cloud service system, or other medical devices.
  • the arterial pressure monitoring data of the monitored object and the personal attribute information of the monitored object are obtained.
  • the arterial pressure monitoring data can be obtained by arterial puncture and catheterization.
  • the catheter is placed in the arterial blood vessel of the monitored part of the monitored object, and the outer end of the catheter is connected to the transducer; the catheterization site includes the radial artery, the ulnar artery, the brachial artery, etc. Since the fluid has a pressure transmission effect, the pressure in the arterial blood vessel is transmitted to the external transducer through the liquid in the catheter, and the transducer can be connected to the monitoring device, so that the monitoring device can obtain the dynamic waveform of the real-time change of the arterial pressure in the arterial blood vessel.
  • the invasive blood pressure measurement based on arterial catheterization can reflect the changes in arterial pressure more timely, accurately and dynamically.
  • Arterial pressure monitoring data can also be obtained by non-invasive continuous blood pressure monitoring method to reduce damage to the monitored object; exemplarily, the non-invasive continuous blood pressure monitoring method includes volume compensation method, arterial tension measurement method, pulse wave velocity measurement method, pulse wave morphology characteristic method, etc.
  • the personal attribute information of the monitored object includes the age, gender, height, weight, etc. of the monitored object, which can affect the mapping relationship between the arterial pressure monitoring data and the cardiovascular parameters.
  • the personal attribute information can be input by the user or automatically obtained by the monitoring device.
  • the information of the monitored object can be obtained, keywords in the information can be extracted, and the personal attribute information of the monitored object can be obtained based on the extracted keywords.
  • the information of the monitored object includes one or more of the patient information database, electronic medical records, examination application forms, etc. of the monitored object.
  • the personal attribute information of the monitored object can also be obtained by any other feasible method.
  • step S110 other relevant information of the monitored object can also be obtained, such as the monitored object's diagnosis results, medical information such as past medical history, and data on other physiological parameters of the monitored object, such as blood oxygen data, electrocardiogram data and other vital sign monitoring data collected by monitoring equipment, which are used together to estimate the cardiovascular parameters of the monitored object.
  • medical information such as past medical history
  • data on other physiological parameters of the monitored object such as blood oxygen data, electrocardiogram data and other vital sign monitoring data collected by monitoring equipment, which are used together to estimate the cardiovascular parameters of the monitored object.
  • a target estimation model suitable for the monitored object is selected from at least two cardiovascular parameter estimation models according to the arterial pressure monitoring data and personal attribute information of the monitored object.
  • the at least two cardiovascular parameter estimation models are constructed based on different algorithm logics and are pre-configured in the monitoring device.
  • the cardiovascular parameter estimation model is based on hemodynamics, combined with the physiological structure of the cardiovascular system and the analogy between hemodynamic parameters and electrical network parameters. It is known from fluid mechanics that in the cardiovascular system, the heart and blood vessels are elastic, and the blood has viscosity, inertia and compliance. However, since the whole body's vascular system is too complex, it is difficult to achieve finite element mechanical modeling of the whole body's blood vessels. Therefore, the cardiovascular system is modeled by comparing it with the electrical system. Among them, voltage is used to represent blood pressure; current is used to represent blood flow; resistance is used to represent blood viscosity resistance; inductance is used to represent blood flow inertia; and capacitance is used to represent vascular compliance.
  • an analog circuit digital simulation model composed of circuit elements can be established, and the flow state of blood flow in blood vessels can be simulated by means of circuit analysis methods. For given blood vessels and blood parameters, the change in blood flow when blood pressure changes can be calculated.
  • At least two cardiovascular parameter estimation models pre-configured in the embodiment of the present application can correspond to at least two cardiovascular parameter algorithm theories.
  • at least two cardiovascular parameter algorithm theories include any two of a lumped parameter circuit model algorithm, a lumped parameter instantaneous flow model algorithm, and a transmission line model algorithm.
  • the lumped parameter circuit model algorithm regards the heart as a current source, and the resistor and capacitor simulate the vascular resistance and vascular compliance of the circulatory system, respectively. See FIG2A, which shows a circuit model based on the lumped parameter circuit model algorithm.
  • the lumped parameter instantaneous flow model algorithm adds an arterial impedance unit on the basis of the lumped parameter circuit model algorithm, simulates the heart as a voltage source, and the arterial compliance is nonlinear. See FIG2B, which shows a circuit model based on the lumped parameter instantaneous flow model algorithm.
  • the distributed transmission model (Transmission line circuit) algorithm uses the transmission line model to capture the distribution characteristics such as propagation impedance and waveform reflection, so that the arterial tree can be simulated more accurately.
  • Figure 2C which shows a circuit model based on a distributed transmission model algorithm. As can be seen from Figures 2A-2C, different cardiovascular parameter algorithm theories simulate the cardiovascular system as completely different circuits.
  • some cardiovascular parameter estimation models may correspond to the same algorithm theory.
  • at least two cardiovascular parameter estimation models based on the lumped parameter circuit model algorithm may include a mean arterial pressure model, a Windkessel model (elastic cavity model), a Windkessel RC model, a Herd model, a Liljestrand model, etc.
  • at least two cardiovascular parameter estimation models based on the distributed transmission model may calculate cardiac output based on systolic pressure, corrected systolic pressure, vascular area and impedance, square root of pressure, etc.
  • the cardiovascular parameter estimation model of the lumped parameter instantaneous flow model includes a Godje model, a Wesseling Modelflow model, etc.
  • a theoretical selection model may be pre-trained for selecting a target estimation model.
  • the theoretical selection model may be pre-configured in a medical device for implementing the method 100 for monitoring cardiovascular parameters, and the arterial pressure monitoring data and the personal attribute information of the monitored object are input into the pre-trained theoretical selection model to obtain the output result of the theoretical selection model, and the target estimation model is selected based on the output result of the theoretical selection model.
  • the pre-training process of the theoretical selection model includes: obtaining the subject's arterial pressure monitoring data, personal attribute information and cardiovascular parameter reference values; applying at least two cardiovascular parameter estimation models respectively, and obtaining the subject's cardiovascular parameter estimation values based on the subject's arterial pressure monitoring data and personal attribute information; determining the cardiovascular parameter estimation model suitable for the subject based on the deviation between the cardiovascular parameter estimation values and the cardiovascular parameter reference values; training the theoretical selection model based on the subject's arterial pressure monitoring data, personal attribute information and the labels corresponding to the cardiovascular parameter estimation model suitable for the subject.
  • the theoretical selection model is used to select a target estimation model suitable for the subject in the first cardiovascular parameter estimation model and the second cardiovascular parameter estimation model.
  • their personal attribute information and arterial pressure monitoring data are obtained respectively, and their cardiovascular parameter reference values are obtained.
  • the cardiovascular parameter reference value can be an accurate result measured by the thermal dilution method or the Doppler flow method.
  • the cardiovascular parameter estimation values are obtained by the first cardiovascular parameter estimation model and the second cardiovascular parameter estimation model respectively, and compared with the cardiovascular parameter reference value, it can be determined that the cardiovascular parameter reference value of the subject in group A is closer to the cardiovascular parameter estimation value obtained by the first cardiovascular parameter estimation model, that is, the cardiovascular parameter estimation model applicable to the subject in group A is the first cardiovascular parameter estimation model; the cardiovascular parameter reference value of the subject in group B is closer to the cardiovascular parameter estimation value obtained by the second cardiovascular parameter estimation model, that is, the cardiovascular parameter estimation model applicable to the subject in group B is the second cardiovascular parameter estimation model.
  • the theoretical selection model can be trained based on the subject's arterial pressure monitoring data, personal attribute information, and labels corresponding to the cardiovascular parameter estimation model applicable to the subject, so that after the subject's arterial pressure monitoring data and personal attribute information are input into the theoretical selection model, the theoretical selection model can accurately output the cardiovascular parameter estimation model applicable to the subject; the trained theoretical selection model can be used to select a suitable cardiovascular parameter estimation model for the monitored subject in clinical practice.
  • the theoretical selection model can be generated by artificial intelligence technologies such as decision trees, regression analysis of past data, and random forests.
  • the target estimation model applicable to the monitored object can be selected in real time. That is, the arterial pressure monitoring data and the personal attribute information of the monitored object are input into the theoretical selection model in real time.
  • the cardiovascular parameter estimation model output by the theoretical selection model can be used as the target estimation model applicable to the monitored object to estimate the cardiovascular parameters of the monitored object. In this way, timely adjustments can be made when the cardiovascular parameter estimation model applicable to the monitored object changes, so as to ensure the accuracy of cardiovascular parameter monitoring.
  • the target estimation model applicable to the monitored object can be selected according to the set frequency.
  • the theoretical selection model can be applied at preset intervals to determine the target estimation model currently applicable to the monitored object, thereby reducing the amount of calculation of the theoretical selection model.
  • the set frequency can also be adjusted according to the fluctuation amplitude of the arterial pressure monitoring data.
  • the set frequency is proportional to the fluctuation amplitude of the arterial pressure monitoring data. If the fluctuation amplitude of the arterial pressure monitoring data is large, the set frequency is high; if the fluctuation amplitude of the arterial pressure monitoring data is large, the set frequency is low.
  • the target estimation model applicable to the monitored object is more likely to change, so a higher set frequency can be applied to ensure timely adjustment of the target estimation model; when the arterial pressure monitoring data is relatively stable, the target estimation model applicable to the monitored object is less likely to change, so a lower set frequency can be applied to reduce the amount of calculation.
  • the cardiovascular parameter estimation model in order to avoid errors caused by factors such as noise, when it is determined at least twice that the monitored object is applicable to the same estimation model, it can be determined as the target estimation model. If it is determined only once that the monitored object is applicable to another cardiovascular parameter estimation model that is different from the currently applied cardiovascular parameter estimation model, the cardiovascular parameter estimation model may not be adjusted temporarily. For example, if it is determined multiple times within a preset time that the monitored object is applicable to the same estimation model of at least two cardiovascular estimation models, the same estimation model is determined as the target estimation model. Alternatively, if it is determined N times in a row that the monitored object is applicable to the same estimation model of at least two cardiovascular parameter estimation models, the same estimation model is determined as the target estimation model, where N is an integer not less than 2.
  • the target estimation model is applied to estimate the cardiovascular parameters of the monitored object according to the arterial pressure monitoring data.
  • the cardiovascular parameters at least include cardiac output (CO); optionally, the cardiovascular parameters may also include stroke volume (SV), stroke volume variation (SVV), vascular resistance (SVR), etc.
  • the target estimation model is applied to estimate the cardiovascular parameters of the monitored object based on the arterial pressure monitoring data, specifically including: extracting waveform features from the arterial pressure monitoring data, inputting the waveform features and personal attribute information into the target estimation model to obtain the cardiovascular parameters of the monitored object.
  • the waveform features extracted from the arterial pressure monitoring data include at least one of the following: pulse timing features, pulse timing higher-order derivatives, spectrum features, energy features, and entropy features.
  • Pulse timing features include amplitude, interval, area under the curve, statistical moment, etc.
  • the arterial pressure monitoring data can be amplified, filtered, analog-to-digital converted, and other data processing to obtain the above-mentioned waveform features.
  • Different cardiovascular parameter estimation models can correspond to different waveform features.
  • the pulse wave transmission time (PWTT) of the monitored object can also be obtained, and the cardiovascular parameters obtained in step S130 can be corrected according to the pulse wave transmission time.
  • the pulse wave is formed by the interaction of the intermittent fluctuations of the heart and the various resistances encountered by the blood flowing in the blood vessels. It contains rich physiological and case information of the cardiovascular system and is closely related to the changes in cardiovascular parameters. With the increase of blood pressure, the increase of arterial dilation pressure and the decrease of arterial compliance, PWTT will shorten. Therefore, PWTT can be involved in the estimation of cardiovascular parameters. Correcting cardiovascular parameters according to the pulse wave transmission time can further improve the accuracy of cardiovascular parameter estimation.
  • the pulse wave transmission time is the time taken for the pulse wave to be transmitted between two points of the human body.
  • the at least two physiological signals can be at least two blood oxygen signals, wherein the blood oxygen signal is a photoelectric signal collected by a blood oxygen sensor.
  • the blood oxygen sensor radiates light of different wavelengths into the tissue area of the monitored object, and detects the light signal sent/reflected by the tissue area.
  • the photoelectric signal can reflect the characteristics of blood flow, and the pulse wave signal generated by the light absorption of the tissue area can be extracted from the photoelectric signal.
  • the pulse wave waveform can be extracted by processing the pulse wave signal.
  • the pulse wave transmission time between the measurement positions of the two blood oxygen signals can be obtained by comparing the pulse wave waveforms obtained from the two blood oxygen signals.
  • the at least two physiological signals may include at least one blood oxygen signal and at least one ECG signal.
  • the ECG signal may be collected by an ECG sensor of a monitoring device.
  • the peak value of the ECG signal comes from the contraction of the ventricle, while the peak value of the pulse wave signal comes from the contraction of the blood vessels. Therefore, the transmission time of blood from the heart to the blood oxygen signal measurement position, i.e., the pulse wave conduction time, may be obtained based on the ECG signal and the pulse wave signal.
  • the cardiovascular parameters obtained in step S130 are corrected according to the pulse wave transmission time.
  • the correction coefficient of the cardiovascular parameters can be calculated according to the pulse wave transmission time, and the correction coefficient is multiplied on the basis of the cardiovascular parameters obtained in step S130 to obtain the final calculation result of the cardiovascular parameters.
  • the method 100 for monitoring cardiovascular parameters of an embodiment of the present application estimates the cardiovascular parameters of the monitored object by selecting a target estimation model suitable for the monitored object from at least two different cardiovascular parameter estimation models based on the arterial pressure monitoring data and personal attribute information of the monitored object, thereby improving the accuracy of cardiovascular parameter monitoring.
  • the medical device 300 includes a memory 310 and a processor 320.
  • the memory 310 stores a computer program executed by the processor 320.
  • the steps of the method for monitoring cardiovascular parameters as described above are executed to obtain the cardiovascular parameters of the monitored object.
  • the medical device 300 of the embodiment of the present application includes but is not limited to any one or a combination of a monitor, a local central station, a remote central station, a cloud service system, and a mobile terminal.
  • the monitor is used to monitor the physiological parameters of the monitored object in real time, and the monitor may include a bedside monitor, a wearable monitor, etc.
  • the central station is used to receive monitoring data sent by medical devices such as monitors, and centrally monitor the monitoring data.
  • the processor 320 of the medical device 300 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or any conventional processor, etc.
  • the processor 320 is the control center of the medical device 300, and uses various interfaces and lines to connect various parts of the entire medical device 300.
  • the medical device 300 also includes a memory 310.
  • the memory 310 is used to store data of a ventilation object associated with the medical device 300.
  • the memory 310 also stores a program code, and the processor 320 is used to call the program code in the memory 310 to execute the steps of the method 100 for monitoring cardiovascular parameters described above.
  • the memory 310 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs required for multiple functions, etc.
  • the memory 310 may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, a plurality of disk storage devices, a flash memory device, or other volatile solid-state storage devices.
  • a non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, a plurality of disk storage devices, a flash memory device, or other volatile solid-state storage devices.
  • the medical device 300 further includes a display for displaying the cardiovascular parameters of the monitored object.
  • the display is used to provide a visual display output for the user.
  • the visual display interface provided by the display includes but is not limited to a monitoring interface, an operation interface, a parameter setting interface, an alarm interface, etc., and the display can be implemented as a touch display, or a display with an input panel, that is, the display can be used as an input/output device.
  • the medical device 300 also includes a sensor.
  • the sensor and the processor 320 can be connected via a wired communication protocol or a wireless communication protocol so that data can be exchanged between the sensor and the processor 320.
  • the sensor includes at least a transducer connected to the puncture catheter for obtaining arterial pressure monitoring data.
  • Wireless communication technology includes, but is not limited to: various generations of mobile communication technology (2G, 3G, 3G and 5G), wireless networks, Bluetooth, ZigBee, ultra-wideband UWB, NFC, etc.
  • the sensor can be independently arranged outside the medical device 300 and detachably connected to the medical device 300.
  • the processor 320 is also used to perform data processing on the monitoring data signal from the sensor.
  • the medical device 300 may also not include a sensor, and the medical device 300 can receive monitoring data collected by an external monitoring accessory through a communication module.
  • the medical device 300 may also include a communication module connected to the processor 320.
  • the medical device 300 can establish data communication with a third-party device through the communication module.
  • the processor 320 also controls the communication module to obtain data from the third-party device, or sends the monitoring data collected by the sensor to the third-party device.
  • the communication module includes but is not limited to WiFI, Bluetooth, NFC, ZigBee, ultra-wideband UWB or 2G, 3G, 3G, 5G and other mobile communication modules.
  • the medical device 300 can also establish a connection with a third-party device via a cable.
  • the third-party device includes other medical devices.
  • the third-party device can also be a cloud service system or a mobile terminal such as a mobile phone, a tablet computer, or a personal computer.
  • the medical device 300 further includes an alarm module connected to the processor 320, which is used to output an alarm prompt so that medical staff can perform corresponding rescue measures.
  • the alarm module includes but is not limited to an alarm light, an alarm speaker, etc.
  • the alarm information can be displayed on a display, the alarm light flashes to prompt the medical staff, or the alarm information is played through an alarm speaker, etc.
  • the medical device 300 may also include other input/output devices connected to the processor 320, including but not limited to input devices such as a keyboard, a mouse, a touch screen, a remote control, and output devices including but not limited to a printer, a speaker, etc.
  • input devices such as a keyboard, a mouse, a touch screen, a remote control
  • output devices including but not limited to a printer, a speaker, etc.
  • Figure 3 is only an example of the components included in the medical device 300 and does not constitute a limitation on the medical device 300.
  • the medical device 300 may include more or fewer components than those shown in Figure 3, or a combination of certain components, or different components.
  • the medical device 300 may also include a power module, a positioning and navigation device, a printing device, etc.
  • the medical device 300 of the embodiment of the present application is used to implement the above-mentioned method 100 for monitoring cardiovascular parameters, and thus also has similar advantages.
  • the disclosed devices and methods can be implemented in other ways.
  • the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.
  • the various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some modules according to the embodiments of the present application.
  • DSP digital signal processor
  • the application can also be implemented as a device program (e.g., computer program and computer program product) for executing a part or all of the methods described herein.
  • Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Cardiology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Physiology (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Hematology (AREA)
  • Medical Informatics (AREA)
  • Physics & Mathematics (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Vascular Medicine (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

一种监测心血管参数的方法和医疗设备，监测心血管参数的方法包括：获取监测对象的动脉压监测数据，以及监测对象的个人属性信息（S110)；根据动脉压监测数据和个人属性信息，在至少两种心血管参数估计模型中，选择适用于监测对象的目标估计模型，至少两种心血管参数估计模型的模型结构算法逻辑不同（S120）；应用目标估计模型，根据动脉压监测数据估计监测对象的心血管参数（S130）。本方法和医疗设备根据监测对象的动脉压监测数据及其个人属性信息，在至少两种不同的心血管参数估计模型中选择适用于监测对象的目标估计模型对检测对象的心血管参数进行估计，能够提高心血管参数监测的准确性

Description

监测心血管参数的方法和医疗设备
说明书
技术领域
本申请涉及医疗设备领域，更具体地涉及一种监测心血管参数的方法和医疗设备。
背景技术
心血管参数的监测能为患者的诊断和治疗提供直观的参数依据。心输出量(Cardiac Output，CO)指左心室或右心室每分钟射出的血液量，是评估心脏功能重要的指标之一。心输出量监测的金标准是右心插管的热稀释监测方法，但右心插管的监测方式对患者的创伤非常大，且有发生并发症的高风险，同时对医护操作要求高，严重限制了心输出量监测方法的推广使用。基于心输出量、血管张力以及动脉压间的三角关系，可以通过数学建模由动脉压推导心输出量，这种监测方式仅需要动脉穿刺置管即可，是一种微创监测心输出量的方法。
目前基于动脉血压估计心输出量的常用模型有多种，虽然这些模型表达式各异，但基本思路都是基于简化关系的数学模型。不同心输出量估计模型所使用的特征不尽相同，各自从不同的生理角度，捕捉与心输出量相关的波形特征，估测性能也在不同场景下也有所差异，单一理论模型无法适用所有场景。
发明内容
在发明内容部分中引入了一系列简化形式的概念，这将在具体实施方式部分中进一步详细说明。本申请的发明内容部分并不意味着要试图限定出所要求保护的技术方案的关键特征和必要技术特征，更不意味着试图确定所要求保护的技术方案的保护范围。
本申请实施例第一方面提供一种监测心血管参数的方法，包括：
获取监测对象的动脉压监测数据，以及所述监测对象的个人属性信息；
根据所述动脉压监测数据和所述个人属性信息，在至少两种心血管参数 估计模型中，选择适用于所述监测对象的目标估计模型，所述至少两种心血管参数估计模型的模型结构算法逻辑不同；
应用所述目标估计模型，根据所述动脉压监测数据估计所述监测对象的心血管参数。
本申请实施例第二方面提供一种医疗设备，所述医疗设备包括存储器和处理器，所述存储器上存储有由所述处理器运行的计算机程序，所述计算机程序在被所述处理器运行时执行如上所述的监测心血管参数的方法的步骤。
根据本申请实施例的监测心血管参数的方法和医疗设备根据监测对象的动脉压监测数据及其个人属性信息，在至少两种不同的心血管参数估计模型中选择适用于监测对象的目标估计模型对监测对象的心血管参数进行估计，能够提高心血管参数监测的准确性。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
在附图中：
图1示出根据本申请一实施例的监测心血管参数的方法的示意性流程图；
图2A示出根据本申请另一实施例的心血管系统等效电路模型；
图2B示出根据本申请另一实施例的心血管系统等效电路模型；
图2C示出根据本申请另一实施例的心血管系统等效电路模型；
图3示出根据本申请一实施例的医疗设备的示意性框图。
具体实施方式
为了使得本申请的目的、技术方案和优点更为明显，下面将参照附图详细描述根据本申请的示例实施例。显然，所描述的实施例仅仅是本申请的一部分实施例，而不是本申请的全部实施例，应理解，本申请不受这里描述的示例实施例的限制。基于本申请中描述的本申请实施例，本领域技术人员在没有付出创造性劳动的情况下所得到的所有其它实施例都应落入本申请的保护范围之内。
在下文的描述中，给出了大量具体的细节以便提供对本申请更为彻底的 理解。然而，对于本领域技术人员而言显而易见的是，本申请可以无需一个或多个这些细节而得以实施。在其他的例子中，为了避免与本申请发生混淆，对于本领域公知的一些技术特征未进行描述。
应当理解的是，本申请能够以不同形式实施，而不应当解释为局限于这里提出的实施例。相反地，提供这些实施例将使公开彻底和完全，并且将本申请的范围完全地传递给本领域技术人员。
在此使用的术语的目的仅在于描述具体实施例并且不作为本申请的限制。在此使用时，单数形式的“一”、“一个”和“所述/该”也意图包括复数形式，除非上下文清楚指出另外的方式。还应明白术语“组成”和/或“包括”，当在该说明书中使用时，确定所述特征、整数、步骤、操作、元件和/或部件的存在，但不排除一个或更多其它的特征、整数、步骤、操作、元件、部件和/或组的存在或添加。在此使用时，术语“和/或”包括相关所列项目的任何及所有组合。此外，本申请能够以多种不同的形式来实现，并不限于本实施例所描述的实施例。提供以下具体实施例的目的是便于对本申请公开内容更清楚透彻的理解，其中上、下、左、右等指示方位的字词仅是针对所示结构在对应附图中位置而言。
为了彻底理解本申请，将在下列的描述中提出详细的结构，以便阐释本申请提出的技术方案。本申请的可选实施例详细描述如下，然而除了这些详细描述外，本申请还可以具有其他实施方式。
下面，将参考附图描述根据本申请实施例的监测心血管参数的方法。首先参考图1，图1是本申请实施例的监测心血管参数的方法100的一个示意性流程图。如图1所示，本申请一个实施例的监测心血管参数的方法100包括如下步骤：
在步骤S110，获取监测对象的动脉压监测数据，以及所述监测对象的个人属性信息；
在步骤S120，根据所述动脉压监测数据和所述个人属性信息，在至少两种心血管参数估计模型中，选择适用于所述监测对象的目标估计模型，所述至少两种心血管参数估计模型的模型结构算法逻辑不同；
在步骤S130，应用所述目标估计模型，根据所述动脉压监测数据估计所述监测对象的心血管参数。
根据本申请实施例的监测心血管参数的方法100根据监测对象的动脉压 监测数据及其个人属性信息，在至少两种不同的心血管参数估计模型中选择适用于监测对象的目标估计模型对监测对象的心血管参数进行估计，能够提高心血管参数监测的准确性。
示例性地，本申请实施例的监测心血管参数的方法100可以实现于监护设备。基于监测心血管参数的方法100得到的心血管参数可以由监护设备输出，例如可以显示在监护设备的监测界面上；监护设备也可以监测心血管参数是否在预设阈值范围内，并在心血管参数超过预设阈值范围时生成报警信息。除了监护设备以外，本申请实施例的脱机评估方法100也可以实现于中央站、云端服务系统或其他医疗设备。
在步骤S110中，获取监测对象的动脉压监测数据，以及监测对象的个人属性信息。示例性地，动脉压监测数据可以通过动脉穿刺置管获得。具体地，通过动脉穿刺，将导管置于监测对象的被测部位的动脉血管内，导管外端与换能器相连接；置管部位包括桡动脉、尺动脉、肱动脉等。由于流体具有压力传递作用，动脉血管内的压力通过导管内的液体传递到外部的换能器上，换能器可以与监护设备相连接，从而可以使监护设备获得动脉血管内动脉压实时变化的动态波形。相比于无创血压测定方法，基于动脉置管的有创血压测定能够更及时、准确和动态地反映动脉压的变化。动脉压监测数据也可以通过无创连续血压监测方法获得，以减少对监测对象的损伤；示例性地，无创连续血压监测方法包括容积补偿法、动脉张力测量法、脉搏波波速测量法、脉搏波形态特征法等等。
监测对象的个人属性信息包括监测对象的年龄、性别、身高、体重等，能够影响动脉压监测数据与心血管参数之间的映射关系。个人属性信息可以由用户输入，或由监护设备自动获取。例如，可以获取监测对象的资料，提取资料中的关键字，根据提取到的关键字获得监测对象的个人属性信息。监测对象的资料包括监测对象的病人信息库、电子病历、检查申请单等中的一个或多个。或者，也可以通过其他任何可行的方式获得监测对象的个人属性信息。
可选地，在步骤S110中，还可以获取监测对象的其他相关信息，例如监测对象的诊断结果、既往病史等医疗信息，以及监测对象的其他生理参数的数据，例如监护设备采集的血氧数据、心电数据等生命体征监测数据，共同用于对监测对象的心血管参数进行估计。
获得监测对象的动脉压监测数据和个人属性信息之后，根据监测对象的动脉压监测数据和个人属性信息，在至少两种心血管参数估计模型中，选择适用于监测对象的目标估计模型。其中，至少两种心血管参数估计模型基于不同的算法逻辑构建，并预先配置于监护设备中。
示例性地，心血管参数估计模型是以血流动力学为基础，结合心血管系统的生理结构以及血流动力学参数与电网络参数的类比关系所建立的。由流体力学可知，在心血管系统中，心脏和血管都具有弹性，血液具有粘滞性、惯性和顺应性。而由于全身的血管系统过于庞杂，难以实现全身血管的有限元力学建模，因此采用将心血管系统与电学系统进行比拟的方式进行建模。其中，用电压表示血压；用电流表示血流；用电阻表示血液粘性阻力；用电感表示血液流动惯性；用电容表示血管顺应性。根据这样的理论基础，可以建立由电路元件组成的模拟电路数字仿真模型，借助电路分析方法来模拟血流在血管中的流动状态。对于给定的血管和血液参数，可以计算当血压变化时的血流变化。
目前的心血管参数估计模型有多种算法理论，但在临床上监测心血管参数时，通常只采用基于一种算法理论构建的心血管参数估计模型，即使考虑到不同应用场景可能影响心血管参数估计模型的准确性，至多根据应用场景调整心血管参数估计模型的模型参数，而不会改变心血管参数估计模型的算法理论，对心血管参数估计的准确性提升有限。
为了进一步提升心血管参数估计的准确性，本申请实施例中预先配置的至少两种心血管参数估计模型可以对应于至少两种心血管参数算法理论。示例性地，至少两种心血管参数算法理论包括集总参数电路模型算法、集总参数瞬时流量模型算法和传输线模型算法中的任意两个。集总参数电路模型(Lumped parameter model)算法将心脏视为电流源，将电阻和电容分别模拟循环系统的血管阻力和血管顺应性。参见图2A，其中示出了基于集总参数电路模型算法的电路模型。集总参数瞬时流量模型(Lumped parameter,instantaneous flow)算法在集总参数电路模型算法的基础上增加了动脉阻抗单元，将心脏模拟为电压源，同时动脉顺应性为非线性。参见图2B，其中示出了基于集总参数瞬时流量模型算法的电路模型。分布传输模型(Transmission line circuit)算法利用传输线模型抓取传播阻抗和波形反射等分布特征，从而能更准确的模拟动脉树。参见图2C，其中示出了基于分布传输模型算法的电 路模型。由此图2A-图2C可见，不同的心血管参数算法理论将心血管系统模拟为完全不同的电路。
在一些实施例中，预先配置的多种心血管参数估计模型中，部分心血管参数估计模型可以对应于同一种算法理论。例如，基于集总参数电路模型算法的至少两种心血管参数估计模型可以包括平均动脉压模型、Windkessel模型(弹性腔模型)、Windkessel RC模型、Herd模型、Liljestrand模型等；基于分布传输模型的至少两种心血管参数估计模型可以分别基于收缩压、校正收缩压、血管面积和阻抗、压力平方根等计算心输出量；集总参数瞬时流量模型的心血管参数估计模型包括Godje模型、Wesseling Modelflow模型等。在同一种算法理论对应的不同心血管参数估计模型中，采用不同的数学模型估计心血管参数，例如，在平均动脉压模型中，CO＝k*P m，其中P m为平均动脉压；在Windkessel RC模型中，CO＝k*P m/T·ln(P s/(P d))，其中P s为收缩压，P d为舒张压。
示例性地，可以预先训练理论选择模型，用于选择目标估计模型。理论选择模型可以预先配置于用于实现监测心血管参数的方法100的医疗设备中，将动脉压监测数据和监测对象的个人属性信息输入到预先训练的理论选择模型中，可以得到理论选择模型的输出结果，并基于理论选择模型的输出结果选取目标估计模型。
其中，理论选择模型的预先训练过程包括：获取被试对象的动脉压监测数据、个人属性信息和心血管参数参考值；分别应用至少两种心血管参数估计模型、根据被试对象的动脉压监测数据和个人属性信息得到被试对象的心血管参数估计值；根据心血管参数估计值和心血管参数参考值之间的偏差确定适用于被试对象的心血管参数估计模型；根据被试对象的动脉压监测数据、个人属性信息和适用于被试对象的心血管参数估计模型所对应的标签训练理论选择模型。
以两种心血管参数估计模型为例，假设理论选择模型用于在第一心血管参数估计模型和第二心血管参数估计模型中选择适用于被测对象的目标估计模型。对于多个被试对象，分别获取其个人属性信息和动脉压监测数据，并获取其心血管参数参考值。其中，心血管参数参考值可以是由热稀释法或多普勒流量法测得的准确结果。以每个被试对象的个人属性信息及动脉压监测数据作为输入，通过第一心血管参数估计模型和第二心血管参数估计模型分 别得到心血管参数估计值，并与心血管参数参考值进行比较，可以确定A组被试对象的心血管参数参考值与第一心血管参数估计模型得到的心血管参数估计值更为接近，即A组被试对象适用的心血管参数估计模型为第一心血管参数估计模型；B组被试对象的心血管参数参考值与第二心血管参数估计模型得到的心血管参数估计值更为接近，即B组被试对象适用的心血管参数估计模型为第二心血管参数估计模型。由此，可以根据被试对象的动脉压监测数据、个人属性信息和适用于被试对象的心血管参数估计模型所对应的标签训练理论选择模型，使得在将被试对象的动脉压监测数据和个人属性信息输入到理论选择模型后，理论选择模型能够准确输出被试对象适用的心血管参数估计模型；训练好的理论选择模型可以用于在临床中为监测对象选择合适的心血管参数估计模型。示例性地，可以通过决策树、对既往数据的回归分析、随机森林等人工智能技术生成理论选择模型。
示例性地，在监测心血管参数的过程中，可以实时选择监测对象适用的所述目标估计模型。即实时将动脉压监测数据和监测对象的个人属性信息输入到理论选择模型中，一旦理论选择模型输出的心血管参数估计模型的选择结果与当前应用的心血管参数估计模型不一致，则可以将理论选择模型输出心血管参数估计模型作为适用于监测对象的目标估计模型，用于估计监测对象的心血管参数。由此，可以在监测对象适用的心血管参数估计模型发生改变时及时作出调整，确保心血管参数监测的准确性。
或者，可以按照设定频率选择监测对象适用的目标估计模型，例如，可以每隔预设时间应用理论选择模型确定监测对象当前适用的目标估计模型，从而减少理论选择模型的运算量。在一些实施例中，还可以根据动脉压监测数据的波动幅度调节设定频率。示例性地，设定频率与动脉压监测数据的波动幅度成正比，动脉压监测数据的波动幅度较大，则设定频率较高；动脉压监测数据的波动幅度较大，则设定频率较低。当动脉压监测数据波动剧烈时，监测对象适用的目标估计模型发生改变的可能性较大，因此可以应用较高的设定频率以确保及时调整目标估计模型；当动脉压监测数据较为平稳时，监测对象适用的目标估计模型发生改变的可能性较小，因此可以应用较低的设定频率以减少运算量。
在一些实施例中，为了避免由于噪声等因素导致的误差，可以在至少两次确定监测对象适用于同一估计模型时，将其确定为目标估计模型。如果仅 一次确定监测对象适用于与当前应用的心血管参数估计模型不同的另一心血管参数估计模型，可以暂时不对心血管参数估计模型进行调整。例如，若在预设时间内连续多次确定监测对象适用于至少两种心血管估计模型中的同一估计模型，则将同一估计模型确定为目标估计模型。或者，若连续N次确定监测对象适用于至少两种心血管参数估计模型中的同一估计模型，则将同一估计模型确定为目标估计模型，其中N为不小于2的整数。
在步骤S130，应用目标估计模型，根据动脉压监测数据估计监测对象的心血管参数。其中，心血管参数至少包括心输出量(CO)；可选地，心血管参数还可以包括每搏输出量(SV)、每搏输出量变化(SVV)、血管阻力(SVR)等。
示例性地，应用目标估计模型，根据动脉压监测数据估计监测对象的心血管参数，具体包括：从动脉压监测数据中提取波形特征，将波形特征和个人属性信息输入到目标估计模型，以得到监测对象的心血管参数。其中，从动脉压监测数据中提取的波形特征包括以下至少一项：脉搏时序特征、脉搏时序高阶导数、频谱特征、能量特征、熵值特征。脉搏时序特征包括幅值、间期、曲线下面积、统计矩等。示例性地，可以对动脉压监测数据进行放大、滤波、模数转换等数据处理，以得到上述波形特征。不同的心血管参数估计模型可以对应于不同的波形特征。
在一些实施例中，还可以获取监测对象的脉搏波传导时间(PWTT)，根据脉搏波传导时间对步骤S130中获得的心血管参数进行修正。脉搏波是由心脏的间歇性波动以及血液在血管中流动所遇到的各种阻力相互作用而形成，其中包含了丰富的心血管系统生理和病例信息，与心血管参数的变化密切相关。随着血压的升高、动脉扩张压力的增加以及动脉顺应性的降低，PWTT均会缩短，因此PWTT可以参与到心血管参数的估计中，根据脉搏波传导时间对心血管参数进行修正能够进一步提高心血管参数估计的准确性。
示例性地，脉搏波传导时间为脉搏波在人体两点之间传导所用的时间，为了获取脉搏波传导时间，需要获取监测对象的至少两路生理信号。其中，至少两路生理信号可以是至少两路血氧信号，其中，血氧信号为通过血氧传感器采集的光电信号，具体地，通过血氧传感器将不同波长的光辐射到监测对象的组织区域中，并检测通过组织区域发送/反射的光信号。每次心跳时，血管的收缩和扩张都会影响光的透射或是光的反射，因此光电信号能够反应 出血液流动的特点，从光电信号中可以提取组织区域的光吸收产生的脉搏波信号。对脉搏波信号进行处理可以提取脉搏波波形。比较两路血氧信号得到的脉搏波波形可以得到两路血氧信号的测量位置之间的脉搏波传导时间。
或者，至少两路生理信号也可以包括至少一路血氧信号和至少一路心电信号。心电信号可以由监护设备的心电传感器进行采集，心电信号的峰值来自于心室的收缩，而脉搏波信号的峰值来自于血管收缩，因此根据心电信号和脉搏波信号可以得到血液自心脏送出后到达血氧信号测量位置的传输时间，即脉搏波传导时间。
在获得脉搏波传导时间后，根据脉搏波传导时间对步骤S130中获得的心血管参数进行修正。具体地，可以根据脉搏波传导时间计算心血管参数的修正系数，在步骤S130中获得的心血管参数的基础上乘以修正系数，得到心血管参数的最终计算结果。
综上所述，本申请实施例的监测心血管参数的方法100根据监测对象的动脉压监测数据及其个人属性信息，在至少两种不同的心血管参数估计模型中选择适用于监测对象的目标估计模型对监测对象的心血管参数进行估计，能够提高心血管参数监测的准确性。
本申请实施例另一方面提供了一种医疗设备，参见图3，医疗设备300包括存储器310和处理器320，存储器310上存储有由处理器320运行的计算机程序，计算机程序在被处理器310运行时执行如上所述的监测心血管参数的方法的步骤，以得到监测对象的心血管参数。
本申请实施例的医疗设备300包括但不限于监护仪、本地中央站、远程中央站、云端服务系统、移动终端中的任意一个或其组合。其中，监护仪用于对监测对象的生理参数进行实时监测，监护仪可包括床边监护仪、穿戴式监护仪等。中央站用于接收监护仪等医疗设备发送的监测数据，并对监测数据进行集中监护。
医疗设备300的处理器320可以是中央处理单元(Central Processing Unit，CPU)，还可以是其它通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其它可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。处理器320是医疗设备300的 控制中心，利用各种接口和线路连接整个医疗设备300的各个部分。
医疗设备300还包括存储器310。存储器310用于存储医疗设备300所关联的通气对象的数据。存储器310还存储有程序代码，处理器320用于调用存储器310中的程序代码而执行上文所述的监测心血管参数的方法100的步骤。存储器310可以主要包括程序存储区和数据存储区，其中，程序存储区可存储操作系统、多个功能所需的应用程序等。此外，存储器310可以包括高速随机存取存储器，还可以包括非易失性存储器，例如硬盘、内存、插接式硬盘，智能存储卡，安全数字卡，闪存卡多个磁盘存储器件、闪存器件、或其它易失性固态存储器件。
在一些实施例中，医疗设备300还包括显示器，用于显示监测对象的心血管参数。显示器用于为用户提供可视化的显示输出。具体地，显示器提供的可视化显示界面包括但不限于监测界面、操作界面、参数设置界面、报警界面等，显示例性地，显示器可以实现为触摸显示器，或者具有输入面板的显示器，即显示器可以作为输入/输出装置。
在一些实施例中，医疗设备300还包括传感器。传感器和处理器320之间可以通过有线通信协议或无线通信协议相连，以使传感器和处理器320之间可以进行数据交互。示例性地，传感器至少包括连接穿刺置管的换能器，用于获取动脉压监测数据。无线通信技术包括但不限于：各代移动通信技术(2G、3G、3G及5G)、无线网络、蓝牙(Bluetooth)、ZigBee、超宽带UWB、NFC等。在一些实施例中，传感器可以独立设置于医疗设备300之外，而与医疗设备300可拆卸地连接。处理器320还用于对来自传感器的监测数据信号进行数据处理。在其它一些实施例中，医疗设备300也可以不包括传感器，医疗设备300可以通过通信模块接收外部监测附件采集的监测数据。
医疗设备300还可以包括连接于处理器320的通信模块。在一些实施例中，医疗设备300可以通过通信模块与第三方设备建立数据通信。处理器320还控制通信模块获取第三方设备的数据，或者将传感器采集到的监测数据发送至第三方设备。通信模块包括但不限于WiFI、蓝牙、NFC、ZigBee、超宽带UWB或2G、3G、3G、5G等移动通信模块。在其它一些实施例中，医疗设备300还可以通过线缆与第三方设备建立连接。第三方设备包括其他医疗设备。第三方设备还可以是云端服务系统或手机、平板电脑、个人电脑等移动终端。
在一些实施例中，医疗设备300还包括连接处理器320的报警模块，用于输出报警提示，以便医护人员执行相应的救护措施。报警模块包括但不限于报警灯、报警扬声器等。报警信息可以显示在显示器上、通过报警灯闪烁以提示医护人员、或通过报警扬声器播放报警信息等。
为了实现用户接口和数据交换，除了显示器之外，医疗设备300还可以包括连接于处理器320的其他输入/输出装置，包括但不限于键盘、鼠标、触控显示屏、遥控器等输入设备，以及包括但不限于打印机、扬声器等输出设备。
应当理解的是，图3仅是医疗设备300包括的部件的示例，并不构成对医疗设备300的限定，且医疗设备300可以包括比图3所示更多或更少的部件，或者组合某些部件，或者不同的部件，例如医疗设备300还可以包括电源模块、定位导航装置、打印装置等。
本申请实施例的医疗设备300用于实现上述的监测心血管参数的方法100，因而也具备类似的优点。
尽管这里已经参考附图描述了示例实施例，应理解上述示例实施例仅仅是示例性的，并且不意图将本申请的范围限制于此。本领域普通技术人员可以在其中进行各种改变和修改，而不偏离本申请的范围和精神。所有这些改变和修改意在被包括在所附权利要求所要求的本申请的范围之内。
本领域普通技术人员可以意识到，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、或者计算机软件和电子硬件的结合来实现。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申请的范围。
在本申请所提供的几个实施例中，应该理解到，所揭露的设备和方法，可以通过其它的方式实现。例如，以上所描述的设备实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个设备，或一些特征可以忽略，或不执行。
在此处所提供的说明书中，说明了大量具体细节。然而，能够理解，本申请的实施例可以在没有这些具体细节的情况下实践。在一些实例中，并未详细示出公知的方法、结构和技术，以便不模糊对本说明书的理解。
类似地，应当理解，为了精简本申请并帮助理解各个发明方面中的一个或多个，在对本申请的示例性实施例的描述中，本申请的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而，并不应将该本申请的方法解释成反映如下意图：即所要求保护的本申请要求比在每个权利要求中所明确记载的特征更多的特征。更确切地说，如相应的权利要求书所反映的那样，其发明点在于可以用少于某个公开的单个实施例的所有特征的特征来解决相应的技术问题。因此，遵循具体实施方式的权利要求书由此明确地并入该具体实施方式，其中每个权利要求本身都作为本申请的单独实施例。
本领域的技术人员可以理解，除了特征之间相互排斥之外，可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述，本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。
此外，本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征，但是不同实施例的特征的组合意味着处于本申请的范围之内并且形成不同的实施例。例如，在权利要求书中，所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
本申请的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本申请实施例的一些模块的一些或者全部功能。本申请还可以实现为用于执行这里所描述的方法的一部分或者全部的装置程序(例如，计算机程序和计算机程序产品)。这样的实现本申请的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
应该注意的是上述实施例对本申请进行说明而不是对本申请进行限制，并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。本申请可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的 使用不表示任何顺序。可将这些单词解释为名称。
以上所述，仅为本申请的具体实施方式或对具体实施方式的说明，本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。本申请的保护范围应以权利要求的保护范围为准。

Claims (15)

  1. 一种监测心血管参数的方法，其特征在于，包括：
    获取监测对象的动脉压监测数据，以及所述监测对象的个人属性信息；
    根据所述动脉压监测数据和所述个人属性信息，在至少两种心血管参数估计模型中，选择适用于所述监测对象的目标估计模型，所述至少两种心血管参数估计模型的模型结构算法逻辑不同；
    应用所述目标估计模型，根据所述动脉压监测数据估计所述监测对象的心血管参数。
  2. 根据权利要求1所述的方法，其特征在于，所述心血管参数包括心输出量。
  3. 根据权利要求1所述的方法，其特征在于，所述至少两种心血管参数估计模型对应于至少两种心血管参数算法理论，所述至少两种心血管参数算法理论包括集总参数电路模型算法、集总参数瞬时流量模型算法和传输线模型算法中的任意两个。
  4. 根据权利要求1所述的方法，其特征在于，所述根据所述动脉压监测数据和所述个人属性信息，在至少两种心血管参数估计模型中，选择适用于所述监测对象的目标估计模型，包括：
    将所述动脉压监测数据和所述个人属性信息输入到预先训练的理论选择模型中，得到所述理论选择模型的输出结果，并基于所述输出结果选取所述目标估计模型。
  5. 根据权利要求4所述的方法，其特征在于，所述理论选择模型的预先训练过程还包括：
    获取被试对象的动脉压监测数据、个人属性信息和心血管参数参考值；
    分别应用所述至少两种多个心血管参数估计模型、根据所述被试对象的动脉压监测数据和个人属性信息得到所述被试对象的心血管参数估计值；
    根据所述心血管参数估计值和所述心血管参数参考值之间的偏差确定适用于所述被试对象的心血管参数估计模型；
    根据所述被试对象的动脉压监测数据、个人属性信息和适用于所述被试对象的心血管参数估计模型所对应的标签训练所述理论选择模型。
  6. 根据权利要求1所述的方法，其特征在于，所述应用所述目标估计模型，根据所述动脉压监测数据估计所述监测对象的心血管参数，包括：
    从所述动脉压监测数据中提取波形特征，将所述波形特征和所述个人属性信息输入到所述目标估计模型，以得到所述监测对象的心血管参数。
  7. 根据权利要求6所述的方法，其特征在于，所述波形特征包括以下至少一项：脉搏时序特征、脉搏时序高阶导数、频谱特征、能量特征、熵值特征。
  8. 根据权利要求1所述的方法，其特征在于，所述根据所述动脉压监测数据和所述个人属性信息，在至少两种心血管参数估计模型中，选择适用于所述监测对象的目标估计模型，包括：
    在监测所述心血管参数的过程中，实时选择确定所述监测对象适用的所述目标估计模型，或者，按照设定频率选择确定所述监测对象适用的所述目标估计模型。
  9. 据权利要求8所述的方法，其特征在于，还包括：
    根据所述动脉压监测数据的波动幅度调节所述设定频率。
  10. 根据权利要求9所述的方法，其特征在于，所述设定频率与所述动脉压监测数据的波动幅度成正比。
  11. 根据权利要求1所述的方法，其特征在于，所述根据所述动脉压监测数据和所述个人属性信息，在至少两种心血管参数估计模型中，选择适用于所述监测对象的目标估计模型，包括：
    若在预设时间内连续多次确定所述监测对象适用于所述至少两种心血管估计模型中的同一候选估计模型，则将所述同一候选估计模型确定为所述目标估计模型。
  12. 根据权利要求1所述的方法，其特征在于，所述根据所述动脉压监测数据和所述个人属性信息，在至少两种心血管参数估计模型中，选择适用于所述监测对象的目标估计模型，包括：
    若连续N次确定所述监测对象适用于所述至少两种心血管参数估计模型中的同一候选估计模型，则将所述同一候选估计模型确定为所述目标估计模型，其中N为不小于2的整数。
  13. 根据权利要求1所述的方法，其特征在于，还包括：
    获取所述监测对象的脉搏波传导时间；
    根据所述脉搏波传导时间对所述心血管参数进行修正。
  14. 根据权利要求1所述的方法，其特征在于，所述监测对象的个人属性信息包括以下至少一项：身高、性别、体重、年龄。
  15. 一种医疗设备，其特征在于，所述医疗设备包括存储器和处理器，所述存储器上存储有由所述处理器运行的计算机程序，所述计算机程序在被所述处理器运行时执行权利要求1-14中任一项所述的监测心血管参数的方法 的步骤。
PCT/CN2022/126515 2022-10-20 2022-10-20 监测心血管参数的方法和医疗设备 WO2024082231A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/126515 WO2024082231A1 (zh) 2022-10-20 2022-10-20 监测心血管参数的方法和医疗设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/126515 WO2024082231A1 (zh) 2022-10-20 2022-10-20 监测心血管参数的方法和医疗设备

Publications (1)

Publication Number Publication Date
WO2024082231A1 true WO2024082231A1 (zh) 2024-04-25

Family

ID=90736534

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/126515 WO2024082231A1 (zh) 2022-10-20 2022-10-20 监测心血管参数的方法和医疗设备

Country Status (1)

Country Link
WO (1) WO2024082231A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008019207A2 (en) * 2006-07-13 2008-02-14 Edwards Lifesciences Corporation Method and apparatus for continuous assessment of a cardiovascular parameter using the arterial pulse pressure propagation time and waveform
US20100204591A1 (en) * 2009-02-09 2010-08-12 Edwards Lifesciences Corporation Calculating Cardiovascular Parameters
US20190326017A1 (en) * 2018-04-23 2019-10-24 Tensys Medical, Inc. Apparatus and methods for computing cardiac output of a living subject via applanation tonometry
CN113160921A (zh) * 2021-05-26 2021-07-23 南京大学 一种基于血流动力学的数字人体心血管系统的构建方法和应用
WO2021250234A2 (en) * 2020-06-11 2021-12-16 Koninklijke Philips N.V. Method for estimating hemodynamic parameters

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008019207A2 (en) * 2006-07-13 2008-02-14 Edwards Lifesciences Corporation Method and apparatus for continuous assessment of a cardiovascular parameter using the arterial pulse pressure propagation time and waveform
US20100204591A1 (en) * 2009-02-09 2010-08-12 Edwards Lifesciences Corporation Calculating Cardiovascular Parameters
US20190326017A1 (en) * 2018-04-23 2019-10-24 Tensys Medical, Inc. Apparatus and methods for computing cardiac output of a living subject via applanation tonometry
WO2021250234A2 (en) * 2020-06-11 2021-12-16 Koninklijke Philips N.V. Method for estimating hemodynamic parameters
CN113160921A (zh) * 2021-05-26 2021-07-23 南京大学 一种基于血流动力学的数字人体心血管系统的构建方法和应用

Similar Documents

Publication Publication Date Title
El-Hajj et al. A review of machine learning techniques in photoplethysmography for the non-invasive cuff-less measurement of blood pressure
Elgendi et al. The use of photoplethysmography for assessing hypertension
Ding et al. Continuous blood pressure measurement from invasive to unobtrusive: Celebration of 200th birth anniversary of Carl Ludwig
Kurylyak et al. A Neural Network-based method for continuous blood pressure estimation from a PPG signal
US20180279965A1 (en) Ambulatory Blood Pressure and Vital Sign Monitoring Apparatus, System and Method
CN103892818B (zh) 一种无创中心动脉血压测量方法和设备
WO2019161608A1 (zh) 多参数监护数据分析方法和多参数监护系统
CN105636509B (zh) 评估脉管的设备、系统和方法
CN113080878A (zh) 用于生理参数监测的系统和方法
WO2022246987A1 (zh) 一种基于血流动力学的数字人体心血管系统的构建方法和应用
US20230301529A1 (en) Continuous blood pressure monitoring
CN102579017A (zh) 无创血流动力学参数分析仪
Viunytskyi et al. Non-invasive cuff-less measurement of blood pressure based on machine learning
US20150157217A1 (en) Analysis System for Cardiac Information and Analyzing Method Thereof
WO2024082231A1 (zh) 监测心血管参数的方法和医疗设备
CN116392091A (zh) 基于单通道指端ppg的连续动脉血压波形检测系统及设备
Sameen et al. Cuff-less and continuous blood pressure measurement based on pulse transit time from carotid and toe photoplethysmograms
US20230263476A1 (en) Method and apparatus for estimating the reliability of cardiac output measurements
EP4090233A1 (en) Noninvasive diagnostics of proximal heart health biomarkers
Koohi et al. Dynamic threshold algorithm to evaluate trustworthiness of the estimated blood pressure in oscillometry
Subito et al. Web-Based Wireless Monitoring System on Patient’s Vital Sign
Almahouzi et al. An integrated biosignals wearable system for low-cost blood pressure monitoring
Chin et al. Relating external compressing pressure to mean arterial pressure in non-invasive blood pressure measurements
Mustapha et al. PC based blood pressure meter for E-health application
US20230371827A1 (en) Machine learning techniques for estimating carotid-femoral pulse wave velocity and/or vascular age from single-site arterial waveform measurements