A monitoring system and method for extracorporeal membrane oxygenation (ECMO)-related respiratory parameters

Abstract

The present invention relates to the field of extracorporeal membrane oxygenation technology, and in particular to a monitoring system and method for extracorporeal membrane oxygenation (ECMO)-related respiratory parameters, comprising: a data acquisition module for real-time acquisition of extracorporeal membrane oxygenation (ECMO)-related respiratory parameters; a data preprocessing module for preprocessing extracorporeal membrane oxygenation (ECMO)-related respiratory parameters; an interface parameter calculation module for real-time calculation of an extracorporeal membrane oxygenation monitoring interface parameter set; a data visualization module for real-time display of a monitoring interface parameter curve set; a real-time monitoring module for real-time monitoring of changes in the monitoring interface parameter curve set; a CO2 emission concentration prediction module for predicting membrane lung CO2 emission concentration; and an equipment operating parameter adjustment module for adjusting ventilator operating parameters and membrane lung operating parameters. The present invention can monitor and adjust the operating parameters of the ventilator and membrane lung in real time, thereby improving the efficiency of extracorporeal membrane oxygenation management.

Description

Technical Field

[0001] The present invention relates to the technical field of extracorporeal membrane oxygenation, and in particular to a monitoring system and method for extracorporeal membrane oxygenation (ECMO)-related respiratory parameters. Background Art

[0002] ECMO refers to an artificial heart-lung machine with extracorporeal membrane oxygenation. Its English name is Extra-corporeal Membrane Oxygenation. ECMO draws venous blood out of the body, oxygenates it through an artificial heart-lung bypass made of special materials, removes carbon dioxide, and then returns the oxygenated blood to the patient's body to partially or completely replace the patient's cardiopulmonary function. Traditional gas exchange monitoring methods mainly rely on intermittent detection methods such as blood gas analysis, so it is impossible to monitor the patient's gas exchange in real time and continuously, resulting in time lags in treatment decisions.

[0003] Chinese Patent Publication No. CN116870283A discloses a method for monitoring core ECMO parameters and a portable ECMO monitor. The method comprises a first blood oxygen sampling unit for collecting a first blood oxygen sampling signal from the blood output from the oxygenator and transmitting it to a digital conversion unit; a second blood oxygen sampling unit for collecting a second blood oxygen sampling signal from the blood input from the oxygenator and transmitting it to the digital conversion unit; the digital conversion unit for digitally converting the first and second blood oxygen sampling signals to obtain corresponding blood oxygen digital signals and transmitting them to a controller; and the controller for receiving the blood oxygen digital signals and calculating a first SpO2 of the blood output from the oxygenator and a second SpO2 of the blood input from the oxygenator, respectively, and calculating the blood oxygen change rate for the current ECMO session. The first and second blood oxygen sampling units are electrically connected to the digital conversion unit, which is in turn electrically connected to the controller. This solution relies excessively on intermittent monitoring methods such as blood gas analysis, resulting in discontinuous information acquisition and making it difficult to timely reflect the patient's real-time gas exchange status. Summary of the Invention

[0004] To this end, the present invention provides a monitoring system and method for extracorporeal membrane oxygenation (ECMO)-related respiratory parameters, so as to overcome the problem in the prior art of over-reliance on intermittent detection methods such as blood gas analysis, resulting in discontinuous information acquisition and difficulty in timely reflecting the patient's real-time gas exchange status.

[0005] To achieve the above objectives, the present invention provides a monitoring system for extracorporeal membrane oxygenation (ECMO)-related respiratory parameters, comprising:

[0006] Data acquisition module, used to collect extracorporeal membrane oxygenation ECMO-related respiratory parameters in real time;

[0007] A data preprocessing module, used to preprocess the extracorporeal membrane oxygenation ECMO-related respiratory parameters to obtain extracorporeal membrane oxygenation respiratory parameters, the data preprocessing module being connected to the data acquisition module;

[0008] an interface parameter calculation module, configured to calculate a set of extracorporeal membrane oxygenation monitoring interface parameters in real time according to the extracorporeal membrane oxygenation respiratory parameters, wherein the interface parameter calculation module is connected to the data preprocessing module;

[0009] a data visualization module for displaying a monitoring interface parameter curve set in real time according to the extracorporeal membrane oxygenation monitoring interface parameter set, the data visualization module being connected to the interface parameter calculation module;

[0010] A real-time monitoring module, configured to assess the patient's status based on the patient's respiratory data, and to monitor changes in the monitoring interface parameter curve set in real time based on the status assessment results, the real-time monitoring module being connected to the data visualization module;

[0011] a CO2 emission concentration prediction module, for constructing a membrane lung CO2 emission concentration prediction model based on the extracorporeal membrane oxygenation monitoring interface parameter set, and for predicting the membrane lung CO2 emission concentration based on the membrane lung CO2 concentration prediction model to obtain a membrane lung CO2 emission concentration prediction value, the membrane lung CO2 emission concentration prediction module being connected to the interface parameter calculation module;

[0012] The equipment operating parameter adjustment module is used to adjust the ventilator operating parameters and the membrane lung operating parameters according to the membrane lung CO2 emission concentration prediction value. The equipment operating parameter adjustment module is connected to the CO2 emission concentration prediction module.

[0013] Furthermore, the data preprocessing module obtains the extracorporeal membrane oxygenation ECMO-related respiratory parameters at each moment of the data acquisition device, fits the extracorporeal membrane oxygenation ECMO-related respiratory parameters according to the curve fitting method, obtains the calibration curve equation, obtains the calibration coefficient Aj according to the calibration curve equation, and calibrates the extracorporeal membrane oxygenation ECMO-related respiratory parameters by combining the calibration coefficient Aj with the preset calibration coefficient Aj0 according to the data processing module to obtain actual calibration data, and preprocesses the actual calibration data according to the abnormal data detection algorithm to obtain extracorporeal membrane oxygenation respiratory parameters.

[0014] Furthermore, the interface parameter calculation module comprehensively evaluates the extracorporeal membrane oxygenation respiratory parameters according to a data comprehensive evaluation method to obtain a comprehensive evaluation value PM, compares the comprehensive evaluation value PM with a preset comprehensive evaluation value PM0, judges the data preprocessing effect according to the comparison result, and calculates the extracorporeal membrane oxygenation monitoring interface parameter set in real time according to the judgment result, wherein:

[0015] When PM≥PM0, the interface parameter calculation module determines that the data preprocessing effect meets the standard, and the interface parameter calculation module performs real-time calculation of the extracorporeal membrane oxygenation monitoring interface parameter set;

[0016] When PM<PM0, the interface parameter calculation module determines that the data preprocessing effect does not meet the standard, the interface parameter calculation module does not perform real-time calculation of the extracorporeal membrane oxygenation monitoring interface parameter set, and re-controls the data preprocessing module to preprocess the extracorporeal membrane oxygenation ECMO-related respiratory parameters until PM≥PM0.

[0017] Furthermore, the data visualization module fits the actual monitoring interface measurement data of each element in the extracorporeal membrane oxygenation monitoring interface parameter set at each moment according to the curve fitting method to obtain an actual extracorporeal membrane oxygenation monitoring interface parameter curve corresponding to each element, and calculates the similarity between the actual extracorporeal membrane oxygenation monitoring interface parameter curve and the preset monitoring interface parameter curve corresponding to each element according to the similarity measurement method to obtain the actual parameter curve similarity MS_i corresponding to each element;

[0018] The data visualization module compares the actual parameter curve similarity MS_i corresponding to each element with the preset actual parameter curve similarity MS0_i corresponding to each element, judges the fitting effect of the monitoring interface parameter curve corresponding to each element according to the comparison result, and displays the monitoring interface parameter curve set in real time according to the judgment result, wherein:

[0019] When MS_i≥MS0_i, the data visualization module determines that the fitting effect of the monitoring interface parameter curve corresponding to the element meets the standard, the data visualization module adds the monitoring interface parameter curve corresponding to the element to the monitoring interface parameter curve set, and displays the monitoring interface parameter curve set in real time;

[0020] When MS_i<MS0_i, the data visualization module determines that the fitting effect of the monitoring interface parameter curve corresponding to the element does not meet the standard, and the data visualization module recalculates the similarity between the actual extracorporeal membrane oxygenation monitoring interface parameter curve and the preset monitoring interface parameter curve corresponding to the element according to the similarity measurement method until MS_i≥MS0_i.

[0021] Furthermore, the real-time monitoring module calculates the patient's respiratory data A1 according to the patient's respiratory frequency Fv, oxygenation state Yh, and ventilation state Tq, and sets A1=α1×Fv+α2×Yh+α3×Tq, α1+α2+α3=1, 0<A1<1, α1 represents a coefficient for adjusting the patient's respiratory frequency Fv, α2 represents a coefficient for adjusting the oxygenation state Yh, and α3 represents a coefficient for adjusting the ventilation state Tq, and compares the patient's respiratory data A1 with the preset patient's respiratory data A0, judges the patient's respiratory function according to the comparison result, and evaluates the patient's status according to the judgment result, wherein:

[0022] When A1>A0, the real-time monitoring module determines that the patient's respiratory function is weak, and the real-time monitoring module assesses the patient's condition as a severe dangerous condition;

[0023] When A1=A0, the real-time monitoring module determines that the patient's respiratory function is moderate, and the real-time monitoring module assesses the patient's condition as moderately dangerous;

[0024] When A1<A0, the real-time monitoring module determines that the patient's respiratory function is a strong respiratory function, and the real-time monitoring module evaluates the patient's condition as a normal condition.

[0025] Furthermore, in the real-time monitoring module, when the real-time monitoring module assesses the patient's condition as a severe risk condition, the real-time monitoring module obtains in real time a severe risk parameter change value WQ_i of each element in the monitoring interface parameter curve set under the severe risk condition, and compares the severe risk parameter change value WQ_i of each element with the corresponding preset severe risk parameter change value WQ0_i, judges the severe risk parameter change according to the comparison result, and performs real-time monitoring of the monitoring interface parameter curve set under the severe risk condition according to the judgment result;

[0026] In the real-time monitoring module, when the real-time monitoring module assesses the patient's condition as a moderate risk condition, the real-time monitoring module obtains in real time a moderate risk parameter change value ZQ_i of each element in the monitoring interface parameter curve set under the moderate risk condition, and compares the moderate risk parameter change value ZQ_i of each element with the corresponding preset moderate risk parameter change value ZQ0_i, judges the moderate risk parameter change according to the comparison result, and monitors the monitoring interface parameter curve set under the moderate risk condition in real time according to the judgment result;

[0027] In the real-time monitoring module, when the real-time monitoring module evaluates the patient's condition as normal, the real-time monitoring module obtains the normal parameter change value CQ_i of each element in the monitoring interface parameter curve set under normal circumstances in real time, and compares the normal parameter change value CQ_i of each element with the corresponding preset normal parameter change value CQ0_i, judges the normal parameter change situation based on the comparison result, and monitors the monitoring interface parameter curve set under normal circumstances in real time based on the judgment result.

[0028] Furthermore, the CO2 emission concentration prediction module collects the ventilator CO2 emission concentration and the membrane lung CO2 emission concentration in the extracorporeal membrane oxygenation monitoring interface parameter set according to a preset collection time period, sets the collected ventilator CO2 emission concentration as the first time series X, sets the collected membrane lung CO2 emission concentration as the second time series Y, and creates a distance matrix D to store the distance between each point in the first time series X and the second time series Y, and calculates the distance matrix D according to the Euclidean distance formula, wherein D ij Represents the distance from xi to yj;

[0029] The CO2 emission concentration prediction module performs path planning on the distance matrix D according to a dynamic programming algorithm to obtain the shortest matching path information, performs feature extraction on the shortest matching path information to obtain the shortest matching path feature information, and trains the long short-term memory network model based on the shortest matching path feature information, and outputs the long short-term memory network model that meets the preset accuracy as the membrane lung CO2 emission concentration prediction model.

[0030] Furthermore, the CO2 emission concentration prediction module obtains the latest ventilator CO2 emission concentration, and inputs the preprocessed latest ventilator CO2 emission concentration into the membrane lung CO2 emission concentration prediction model to predict the membrane lung CO2 emission concentration to obtain a membrane lung CO2 emission concentration prediction value.

[0031] Furthermore, the equipment operating parameter adjustment module obtains a membrane lung CO2 emission concentration predicted change interval MYJ based on the membrane lung CO2 emission concentration predicted value, and compares the membrane lung CO2 emission concentration predicted change interval MYJ with a preset membrane lung CO2 emission concentration predicted change interval MYJ0, judges the membrane lung CO2 emission concentration predicted change according to the comparison result, and adjusts the ventilator operating parameters and the membrane lung operating parameters according to the judgment result, wherein:

[0032] When MYJ≤MYJ0, the device operating parameter adjustment module determines that the predicted change of the membrane lung CO2 emission concentration is normal, and the device operating parameter adjustment module does not adjust the ventilator operating parameters and the membrane lung operating parameters;

[0033] When MYJ>MYJ0, the equipment operating parameter adjustment module determines that the predicted change of the membrane lung CO2 emission concentration is an abnormal state, and the equipment operating parameter adjustment module adjusts the ventilator operating parameters and the membrane lung operating parameters.

[0034] The present invention also provides a method for monitoring respiratory parameters related to extracorporeal membrane oxygenation (ECMO), comprising:

[0035] Step S1, collecting extracorporeal membrane oxygenation (ECMO)-related respiratory parameters in real time, and preprocessing the extracorporeal membrane oxygenation (ECMO)-related respiratory parameters to obtain extracorporeal membrane oxygenation (ECMO) respiratory parameters;

[0036] Step S2, calculating an extracorporeal membrane oxygenation monitoring interface parameter set in real time according to the extracorporeal membrane oxygenation respiratory parameters, and displaying a monitoring interface parameter curve set in real time according to the extracorporeal membrane oxygenation monitoring interface parameter set;

[0037] Step S3, evaluating the patient's status based on the patient's respiratory data, and monitoring the changes in the monitoring interface parameter curve set in real time based on the status evaluation results;

[0038] Step S4: construct a membrane lung CO2 emission concentration prediction model based on the extracorporeal membrane oxygenation monitoring interface parameter set, and predict the membrane lung CO2 emission concentration based on the membrane lung CO2 concentration prediction model to obtain a membrane lung CO2 emission concentration prediction value, and adjust the ventilator operating parameters and the membrane lung operating parameters based on the membrane lung CO2 emission concentration prediction value.

[0039] Compared with the prior art, the beneficial effect of the present invention is that the system is set at a control terminal for real-time monitoring of the membrane oxygenation CO2 emission concentration of patients with extracorporeal membrane oxygenation ECMO combined with ventilator-assisted breathing, wherein the system collects extracorporeal membrane oxygenation ECMO-related respiratory parameters in real time through the data acquisition module to ensure the timeliness and accuracy of data acquisition, the system realizes automatic calibration of the data acquisition device through the data preprocessing module, and can preprocess the extracorporeal membrane oxygenation ECMO-related respiratory parameters in real time through the calibrated data acquisition device to ensure the accuracy of the data, the system can calculate and update the extracorporeal membrane oxygenation monitoring interface parameter set in real time based on the preprocessed data through the interface parameter calculation module, and can provide comprehensive patient status information, the system can realize automatic calibration of the data acquisition device through the data preprocessing module, and can preprocess the extracorporeal membrane oxygenation ECMO-related respiratory parameters in real time through the calibrated data acquisition device to ensure the accuracy of the data, the system can calculate and update the extracorporeal membrane oxygenation monitoring interface parameter set in real time based on the preprocessed data through the interface parameter calculation module, and can provide comprehensive patient status information, and the system can realize automatic calibration of the data acquisition device through the data preprocessing module, and can preprocess the extracorporeal membrane oxygenation ECMO-related respiratory parameters in real time based on the preprocessed data, and can provide comprehensive patient status information, and the system can realize automatic calibration of the data acquisition device through the data preprocessing module, and can Quickly identify the changing trends of the patient's respiratory parameters and improve monitoring efficiency and accuracy. The system continuously monitors the patient's respiratory data through the real-time monitoring module, and evaluates the patient's status based on these data. At the same time, it monitors the changes in the interface parameter curve in real time, and promptly discovers and responds to the patient's abnormal status. The system constructs and applies a membrane lung CO2 emission concentration prediction model based on the parameter set of the extracorporeal membrane oxygenation monitoring interface through the CO2 emission concentration prediction module, predicts the CO2 emission concentration of the membrane lung in advance, and provides a scientific basis for adjusting the operating parameters of the ventilator and membrane lung. The system adjusts the operating parameters of the ventilator and membrane lung in real time according to the predicted value of the membrane lung CO2 emission concentration through the equipment operating parameter adjustment module, ensuring that the patient's respiratory condition is in the best state and effectively optimizing extracorporeal membrane oxygenation management. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 Schematic diagram of the structure of the monitoring system for extracorporeal membrane oxygenation (ECMO) related respiratory parameters in this embodiment;

[0041] Figure 2 Schematic diagram of the process of monitoring respiratory parameters related to extracorporeal membrane oxygenation (ECMO) in this embodiment. DETAILED DESCRIPTION

[0042] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0043] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0044] See also Figure 1As shown in FIG, which is a schematic diagram of the structure of the monitoring system for extracorporeal membrane oxygenation ECMO-related respiratory parameters in this embodiment, the system includes:

[0045] Data acquisition module, used to collect extracorporeal membrane oxygenation ECMO-related respiratory parameters in real time;

[0046] A data preprocessing module, used to preprocess the extracorporeal membrane oxygenation ECMO-related respiratory parameters to obtain extracorporeal membrane oxygenation respiratory parameters, the data preprocessing module being connected to the data acquisition module;

[0047] an interface parameter calculation module, configured to calculate a set of extracorporeal membrane oxygenation monitoring interface parameters in real time according to the extracorporeal membrane oxygenation respiratory parameters, wherein the interface parameter calculation module is connected to the data preprocessing module;

[0048] a data visualization module for displaying a monitoring interface parameter curve set in real time according to the extracorporeal membrane oxygenation monitoring interface parameter set, the data visualization module being connected to the interface parameter calculation module;

[0049] A real-time monitoring module, configured to assess the patient's status based on the patient's respiratory data, and to monitor changes in the monitoring interface parameter curve set in real time based on the status assessment results, the real-time monitoring module being connected to the data visualization module;

[0050] a CO2 emission concentration prediction module, for constructing a membrane lung CO2 emission concentration prediction model based on the extracorporeal membrane oxygenation monitoring interface parameter set, and for predicting the membrane lung CO2 emission concentration based on the membrane lung CO2 concentration prediction model to obtain a membrane lung CO2 emission concentration prediction value, the membrane lung CO2 emission concentration prediction module being connected to the interface parameter calculation module;

[0051] The equipment operating parameter adjustment module is used to adjust the ventilator operating parameters and the membrane lung operating parameters according to the membrane lung CO2 emission concentration prediction value. The equipment operating parameter adjustment module is connected to the CO2 emission concentration prediction module.

[0052] Specifically, the system is set at a control terminal for real-time monitoring of the membrane oxygenation CO2 emission concentration of patients with extracorporeal membrane oxygenation ECMO combined with ventilator-assisted breathing, wherein the system collects extracorporeal membrane oxygenation ECMO-related respiratory parameters in real time through the data acquisition module to ensure the timeliness and accuracy of data acquisition, the system realizes automatic calibration of the data acquisition device through the data preprocessing module, and can preprocess the extracorporeal membrane oxygenation ECMO-related respiratory parameters in real time through the calibrated data acquisition device to ensure the accuracy of the data, the system can calculate and update the extracorporeal membrane oxygenation monitoring interface parameter set in real time based on the preprocessed data through the interface parameter calculation module, and can provide comprehensive patient status information, and the system can quickly identify the patient through the data visualization module. The system continuously monitors the patient's respiratory data through the real-time monitoring module, and evaluates the patient's condition based on these data. At the same time, it monitors the changes in the interface parameter curve in real time, and promptly discovers and responds to the patient's abnormal condition. The system constructs and applies a membrane lung CO2 emission concentration prediction model based on the parameter set of the extracorporeal membrane oxygenation monitoring interface through the CO2 emission concentration prediction module, and predicts the CO2 emission concentration of the membrane lung in advance, providing a scientific basis for adjusting the operating parameters of the ventilator and membrane lung. The system adjusts the operating parameters of the ventilator and membrane lung in real time according to the predicted value of the membrane lung CO2 emission concentration through the equipment operating parameter adjustment module, ensuring that the patient's respiratory condition is in the best state and improving the management efficiency of extracorporeal membrane oxygenation.

[0053] Specifically, the data acquisition module collects the extracorporeal membrane oxygenation ECMO-related respiratory parameters in real time according to the data acquisition device. The extracorporeal membrane oxygenation ECMO-related respiratory parameters refer to the respiratory data collected in real time according to the data acquisition device, including membrane lung extracorporeal circulation flow Ma, membrane pulmonary artery oxygen partial pressure Md, membrane pulmonary vein oxygen partial pressure Mg, membrane pulmonary artery oxygen saturation Mc, membrane pulmonary vein oxygen saturation Mf, patient blood flow Ha, patient arterial oxygen partial pressure Hd, patient venous oxygen partial pressure Hj, patient arterial oxygen saturation Hc, patient venous oxygen saturation Hf, membrane lung CO2 emission concentration MFC, patient CO2 emission concentration HZC, patient red blood cell volume RJ, patient body surface area He and patient nasopharyngeal temperature BY, the The membrane lung extracorporeal circulation flow rate Ma refers to the blood flow through the membrane lung for extracorporeal circulation, the membrane pulmonary artery oxygen partial pressure Md refers to the oxygen partial pressure of the blood at the membrane pulmonary artery end, the membrane pulmonary vein oxygen partial pressure Mg refers to the oxygen partial pressure of the blood at the membrane pulmonary vein end, the membrane pulmonary artery oxygen saturation Mc refers to the oxygen saturation of the blood at the membrane pulmonary artery end, the membrane pulmonary vein oxygen saturation Mf refers to the oxygen saturation of the blood at the membrane pulmonary vein end, the patient blood flow Ha refers to the blood flow in the patient's body, the patient arterial oxygen partial pressure Hd refers to the oxygen partial pressure in the patient's arterial blood, the patient venous oxygen partial pressure Hj refers to the oxygen partial pressure in the patient's venous blood, the patient arterial oxygen saturation Hc refers to the oxygen saturation of the patient's arterial blood, and the patient venous oxygen saturation Hf Refers to the oxygen saturation in the patient's venous blood, the patient's red blood cell volume RJ refers to the volume percentage of red blood cells in the patient's blood, the patient's body surface area He refers to the patient's body surface area, the patient's nasopharyngeal temperature BY refers to the temperature of the patient's nasopharynx, the membrane lung CO2 emission concentration MFC refers to the concentration of carbon dioxide emitted by the membrane lung, the patient's CO2 emission concentration HZC refers to the concentration of carbon dioxide emitted by the patient, the data acquisition device refers to a device for real-time acquisition of extracorporeal membrane oxygenation-related respiratory parameters, including a flow sensor, a pressure sensor, an oxygen saturation sensor, a CO2 concentration sensor, an red blood cell volume sensor, a body surface area sensor and a nasopharyngeal temperature sensor. The data acquisition module uses a flow sensor to The sensor collects the membrane lung extracorporeal circulation flow Ma and the patient's blood flow Ha in real time. The data acquisition module collects the membrane pulmonary artery oxygen partial pressure Md, the membrane pulmonary vein oxygen partial pressure Mg, the patient's arterial oxygen partial pressure Hd and the patient's venous oxygen partial pressure Hj in real time through the pressure sensor. The data acquisition module collects the membrane pulmonary artery oxygen saturation Mc, the membrane pulmonary vein oxygen saturation Mf, the patient's arterial oxygen saturation Hc and the patient's venous oxygen saturation Hf in real time through the oxygen saturation sensor. The data acquisition module collects the membrane lung CO2 emission concentration MFC and the patient's CO2 emission concentration HZC in real time through the CO2 emission concentration sensor. The data acquisition module collects the patient's red blood cell volume RJ in real time through the red blood cell volume sensor.The data acquisition module collects the patient's body surface area He in real time through the body surface area sensor, and the data acquisition module collects the patient's nasopharyngeal temperature BY in real time through the nasopharyngeal temperature sensor.

[0054] Specifically, the data preprocessing module obtains the extracorporeal membrane oxygenation ECMO-related respiratory parameters at each moment of the data acquisition device, fits the extracorporeal membrane oxygenation ECMO-related respiratory parameters according to the curve fitting method, obtains the calibration curve equation, and obtains the calibration coefficient Aj according to the calibration curve equation, and calibrates the extracorporeal membrane oxygenation ECMO-related respiratory parameters with the calibration coefficient Aj and the preset calibration coefficient Aj0 according to the data processing module to obtain actual calibration data, and preprocesses the actual calibration data according to the abnormal data detection algorithm to obtain extracorporeal membrane oxygenation respiratory parameters.

[0055] Specifically, the curve fitting method refers to a method for fitting extracorporeal membrane oxygenation ECMO-related respiratory parameters. This embodiment does not limit the specific implementation scheme of the curve fitting method. For example, it can be set to fit the extracorporeal membrane oxygenation ECMO-related respiratory parameters by the least squares method to obtain a calibration curve equation. The calibration curve equation refers to a mathematical expression obtained by converting the extracorporeal membrane oxygenation ECMO-related respiratory parameters into calibrated values ​​by the data fitting method. The calibration coefficient Aj refers to adjusting the extracorporeal membrane oxygenation ECMO-related respiratory parameters by the calibration curve equation to obtain a calibrated value. The preset calibration coefficient Aj0 refers to a preset value for comparison with the calibration coefficient Aj. For example, in the calibration curve equation y=2x+1, 2 and 1 are preset calibration coefficients. This embodiment does not limit the process of calibrating the extracorporeal membrane oxygenation ECMO-related respiratory parameters. For example, it can be set to calibrate the extracorporeal membrane oxygenation ECMO-related respiratory parameter Pi by using the calibration coefficient Aj and the preset calibration coefficient Aj0 according to the data processing module to obtain actual calibration data N i, and set the actual calibration data N i=Aj0 / Aj×Pi, the actual calibration data refers to the data obtained after calibrating the extracorporeal membrane oxygenation ECMO-related respiratory parameters by using the calibration coefficient Aj and the preset calibration coefficient Aj0 according to the data processing module. The abnormal data detection algorithm refers to a method for identifying data points in a data set that do not conform to a normal pattern. This embodiment does not limit the specific implementation scheme of the abnormal data detection algorithm. For example, the actual calibration data can be preprocessed using a 3-sigma algorithm to obtain extracorporeal membrane oxygenation respiratory parameters. The extracorporeal membrane oxygenation respiratory parameters refer to parameters used to evaluate the patient's respiratory function by preprocessing the actual calibration data according to the abnormal data detection algorithm.

[0056] Specifically, the data preprocessing module can preprocess the extracorporeal membrane oxygenation ECMO-related respiratory parameters in real time to ensure the accuracy of the data.

[0057] Specifically, the interface parameter calculation module comprehensively evaluates the extracorporeal membrane oxygenation respiratory parameters according to the data comprehensive evaluation method to obtain a comprehensive evaluation value PM, and compares the comprehensive evaluation value PM with a preset comprehensive evaluation value PM0, judges the data preprocessing effect according to the comparison result, and calculates the extracorporeal membrane oxygenation monitoring interface parameter set in real time according to the judgment result, wherein:

[0058] When PM≥PM0, the interface parameter calculation module determines that the data preprocessing effect meets the standard, and the interface parameter calculation module performs real-time calculation of the extracorporeal membrane oxygenation monitoring interface parameter set;

[0059] When PM<PM0, the interface parameter calculation module determines that the data preprocessing effect does not meet the standard, the interface parameter calculation module does not perform real-time calculation of the extracorporeal membrane oxygenation monitoring interface parameter set, and re-controls the data preprocessing module to preprocess the extracorporeal membrane oxygenation ECMO-related respiratory parameters until PM≥PM0;

[0060] The interface parameter calculation module calculates the membrane oxygen supply index MYG in real time according to the membrane oxygenator extracorporeal circulation flow Ma, the patient's red blood cell volume RJ, the membrane pulmonary artery oxygen saturation Mc, the membrane pulmonary artery oxygen partial pressure Md and the patient's body surface area He, and sets MYG = Ma × (RJ / 2.94×1.36×Mc / 100+Md×0.003)×10 / He;

[0061] The interface parameter calculation module calculates the membrane lung oxygen supply ratio MBV according to the ventilator oxygen supply index HX and the membrane lung oxygen supply index MYG, and sets MBV=HX / (HX+MYG);

[0062] The interface parameter calculation module calculates the membrane lung oxygen consumption index MHY in real time based on the membrane lung extracorporeal circulation flow Ma, the patient's red blood cell volume RJ, the membrane pulmonary artery oxygen saturation Mc, the membrane pulmonary vein oxygen saturation Mf, the patient's body surface area He, the membrane pulmonary artery oxygen partial pressure Md and the membrane pulmonary vein oxygen partial pressure Mg, and sets MHY=Ma×[RJ / 2.94×1.36×(Mc-Mf) / 100+(Md-Mg)×0.003]×10 / He;

[0063] The interface parameter calculation module calculates the membrane lung CO2 emission concentration MFC in real time according to the membrane lung ventilation volume Mh, the membrane lung carbon dioxide partial pressure Mi, the patient's body surface area He and the patient's nasopharyngeal temperature BY, and sets MFC=Mh×M i×1000 / (760×He)×[(760-18)×273 / 760×(273+BY)];

[0064] The interface parameter calculation module calculates the membrane lung respiratory quotient RQ and the membrane lung oxygen uptake ER in real time according to the membrane lung CO2 emission concentration MFC and the membrane lung oxygen consumption index MHY, respectively, setting RQ = MFC / MHY, ER = MFC / MHY×100%;

[0065] The interface parameter calculation module calculates the membrane lung carbon dioxide emission ratio MFP in real time according to the membrane lung oxygen supply index MYG and the membrane lung CO2 emission concentration MFC, and sets MFP=MYG / MFC;

[0066] The interface parameter calculation module calculates the patient's oxygen supply index HYG in real time based on the patient's blood flow Ha, the patient's red blood cell volume RJ, the patient's arterial oxygen saturation Hc, the patient's arterial oxygen partial pressure Hd and the patient's body surface area He, and sets HYG = Ha × (RJ / 2.94 × 1.36 × Hc / 100 + Hd × 0.003) × He;

[0067] The interface parameter calculation module calculates the patient's natural lung oxygen supply ratio HYV in real time according to the patient's oxygen supply index HYG and the membrane lung oxygen supply index MYG, and sets HYV=HYG / (MYG+HYG);

[0068] The interface parameter calculation module calculates the patient's oxygen consumption index HHY in real time based on the patient's blood flow Ha, the membrane lung extracorporeal circulation flow Ma, the patient's red blood cell volume RJ, the patient's arterial oxygen saturation Hc, the patient's venous oxygen saturation Hf, the patient's arterial oxygen partial pressure Hd, the patient's venous oxygen partial pressure Hj and the patient's body surface area He, and sets HHY = (Ha + Ma) × [RJ / 2.94 × 1.36 × (Hc - Hf) / 100 + (Hd - Hj) × 0.003] × 10 / He;

[0069] The interface parameter calculation module calculates the patient's CO2 emission concentration HZC in real time based on the patient's natural lung ventilation Hh, the patient's own carbon dioxide partial pressure Hi, the patient's body surface area He, and the patient's nasopharyngeal temperature BY, setting HZC = Hh × Hi × 1000 / (760 × He) × [(760-18) × 273 / 760 × (273 + BY)];

[0070] The interface parameter calculation module calculates the patient's respiratory quotient HRQ in real time based on the membrane lung CO2 emission concentration MFC, the patient's CO2 emission concentration HZC and the patient's oxygen consumption index HHY, and sets HRQ=(MFC+HZC) / HHY;

[0071] The interface parameter calculation module calculates the patient's oxygen uptake rate HER in real time according to the patient's oxygen consumption index HHY, the patient's oxygen supply index HYG and the membrane lung oxygen supply index MYG, and sets HER=HHY / (MYG+HYG)×100%;

[0072] The interface parameter calculation module calculates the patient's carbon dioxide emission ratio HZP according to the patient's oxygen supply index HYG and the patient's CO2 emission concentration HZC, and sets HZP=HYG / HZC;

[0073] The interface parameter calculation module adds the membrane lung oxygen supply index MYG, membrane lung oxygen supply ratio MBV, membrane lung oxygen consumption index MHY, membrane lung CO2 emission concentration MFC, membrane lung respiratory quotient RQ, membrane lung oxygen uptake ER, membrane lung carbon dioxide emission ratio MFP, patient oxygen supply index HYG, patient natural lung oxygen supply ratio HYV, patient oxygen consumption index HHY, patient CO2 emission concentration HZC, patient respiratory quotient HRQ, patient oxygen uptake rate HER and patient carbon dioxide emission ratio HZP to the extracorporeal membrane oxygenation monitoring interface parameter set.

[0074] Specifically, the data comprehensive evaluation method refers to a method for comprehensively evaluating the extracorporeal membrane oxygenation respiratory parameters. This embodiment does not limit the specific implementation plan of the data comprehensive evaluation method. For example, the extracorporeal membrane oxygenation respiratory parameters can be comprehensively evaluated by a principal component analysis method. The comprehensive evaluation value PM refers to a data quality indicator of the overall evaluation score of the extracorporeal membrane oxygenation respiratory parameters according to the data comprehensive method. The preset comprehensive evaluation value PM0 refers to a preset value compared with the comprehensive evaluation value PM, for example, 85 points. The extracorporeal membrane oxygenation monitoring interface parameter set refers to a parameter set for monitoring and evaluating the status of ECMO patients. The ventilator oxygen supply index HX refers to an indicator reflecting the amount of oxygen provided by the ventilator to the patient. The membrane lung ventilation Mh refers to the amount of air processed by the membrane lung per unit time. The membrane lung exhaust carbon dioxide partial pressure M i refers to the partial pressure of carbon dioxide gas discharged by the membrane lung. The patient's natural lung ventilation Hh refers to the amount of air processed by the patient's natural lung per unit time. The patient's own carbon dioxide partial pressure Hi refers to the partial pressure of carbon dioxide gas discharged by the patient's natural lung.

[0075] Specifically, the interface parameter calculation module can calculate the extracorporeal membrane oxygenation monitoring interface parameters in real time, thereby improving monitoring efficiency.

[0076] Specifically, the data visualization module fits the actual monitoring interface measurement data of each element in the extracorporeal membrane oxygenation monitoring interface parameter set at each moment according to the curve fitting method to obtain an actual extracorporeal membrane oxygenation monitoring interface parameter curve corresponding to each element, and calculates the similarity between the actual extracorporeal membrane oxygenation monitoring interface parameter curve and the preset monitoring interface parameter curve corresponding to each element according to the similarity measurement method to obtain the actual parameter curve similarity MS_i corresponding to each element;

[0077] The data visualization module compares the actual parameter curve similarity MS_i corresponding to each element with the preset actual parameter curve similarity MS0_i corresponding to each element, judges the fitting effect of the monitoring interface parameter curve corresponding to each element according to the comparison result, and displays the monitoring interface parameter curve set in real time according to the judgment result, wherein:

[0078] When MS_i≥MS0_i, the data visualization module determines that the fitting effect of the monitoring interface parameter curve corresponding to the element meets the standard, the data visualization module adds the monitoring interface parameter curve corresponding to the element to the monitoring interface parameter curve set, and displays the monitoring interface parameter curve set in real time;

[0079] When MS_i<MS0_i, the data visualization module determines that the fitting effect of the monitoring interface parameter curve corresponding to the element does not meet the standard, and the data visualization module recalculates the similarity between the actual extracorporeal membrane oxygenation monitoring interface parameter curve and the preset monitoring interface parameter curve corresponding to the element according to the similarity measurement method until MS_i≥MS0_i.

[0080] Specifically, the actual extracorporeal membrane oxygenation monitoring interface parameter curve refers to a curve obtained by a curve fitting method based on actual monitoring interface measurement data, representing the changes in various parameters over time. The similarity measurement method refers to a method for comparing the similarity between two sets of curves. This embodiment does not limit the specific implementation of the similarity measurement method. For example, the actual extracorporeal membrane oxygenation monitoring interface parameter curve can be configured to calculate the similarity between the actual extracorporeal membrane oxygenation monitoring interface parameter curve and a preset monitoring interface parameter curve corresponding to each element using cosine similarity. The preset monitoring interface parameter curve refers to a preset extracorporeal membrane oxygenation monitoring interface parameter curve, such as a preset curve showing the changes in blood flow over time. The actual parameter curve similarity MS_i refers to a value calculated by the similarity measurement method for the actual extracorporeal membrane oxygenation monitoring interface parameter curve and the preset monitoring interface parameter curve corresponding to each element. The preset actual parameter curve similarity MS0_i refers to a preset value, such as 95%, for comparison with the actual parameter curve similarity MS_i. The monitoring interface parameter curve set refers to the set of all monitoring interface parameter curves that have been judged to have met the fitting criteria. Each element refers to each monitoring interface parameter curve in the monitoring interface parameter curve set.

[0081] Specifically, the data visualization module can provide an intuitive monitoring interface parameter curve monitoring interface and accurate fitting effect judgment, thereby improving the management efficiency of extracorporeal membrane oxygenation.

[0082] Specifically, the real-time monitoring module calculates the patient's respiratory data A1 according to the patient's respiratory frequency Fv, oxygenation state Yh and ventilation state Tq, sets A1=α1×Fv+α2×Yh+α3×Tq, α1+α2+α3=1, 0<A1<1, α1 represents a coefficient for adjusting the patient's respiratory frequency Fv, α2 represents a coefficient for adjusting the oxygenation state Yh, and α3 represents a coefficient for adjusting the ventilation state Tq, and compares the patient's respiratory data A1 with the preset patient's respiratory data A0, judges the patient's respiratory function according to the comparison result, and evaluates the patient's status according to the judgment result, wherein:

[0083] When A1>A0, the real-time monitoring module determines that the patient's respiratory function is weak, and the real-time monitoring module assesses the patient's condition as a severe dangerous condition;

[0084] When A1=A0, the real-time monitoring module determines that the patient's respiratory function is moderate, and the real-time monitoring module assesses the patient's condition as moderately dangerous;

[0085] When A1<A0, the real-time monitoring module determines that the patient's respiratory function is a strong respiratory function, and the real-time monitoring module evaluates the patient's condition as a normal condition;

[0086] The real-time monitoring module calculates the patient circulation data HK based on the patient's consciousness clarity SK and the patient's urine volume HL, and sets HK=β1×SK+β2×HL, where β1 represents a coefficient for adjusting the patient's consciousness clarity SK, β2 represents a coefficient for adjusting the patient's urine volume HL, β1+β2=1, 0<HK<1, and compares the patient circulation data HK with the preset patient circulation data HK0. According to the comparison result, a state adjustment judgment is made on the patient's state assessment process, and according to the adjustment judgment result, a state adjustment is made on the patient's state assessment process, wherein:

[0087] When HK=HK0, the real-time monitoring module determines not to perform state adjustment on the patient's state assessment process;

[0088] When HK≠HK0, the real-time monitoring module determines to adjust the patient's state assessment process and sets the cycle optimization parameter ε to adjust the patient's cycle data HK.

[0089] HK-HK0

[0090] Set ε=0.24×2.784, the adjusted patient circulation data is HK1, and set HK1=ε×HK.

[0091] Specifically, the patient respiratory frequency Fv refers to the number of breaths the patient takes per minute, the oxygenation state Yh refers to the oxygen content in the patient's blood, the ventilation state Tq refers to the state of pulmonary gas exchange, the preset patient respiratory data A0 refers to a preset value for comparison with the patient respiratory data A1, for example, 0.8, the respiratory function condition refers to the comparison result based on the patient respiratory data A1 and the preset patient respiratory data A0, the patient's consciousness clarity SK refers to the degree of patient wakefulness, the patient's urine volume HL refers to the amount of urine discharged by the patient, the preset patient circulation data HK0 refers to a preset value for comparison with the patient circulation data HK, for example, 0.7, the patient's state evaluation process refers to the process for evaluating the patient's overall state, and the circulation optimization parameter refers to the parameter used to adjust the patient's circulation data HK when HK≠HK0.

[0092] Specifically, evaluating the patient's respiratory and circulatory status through the real-time monitoring module helps to promptly detect and address the patient's respiratory and circulatory problems, thereby ensuring the patient's safety.

[0093] Specifically, in the real-time monitoring module, when the real-time monitoring module assesses the patient's condition as a severe risk condition, the real-time monitoring module obtains in real time the severe risk parameter change value WQ_i of each element in the monitoring interface parameter curve set under the severe risk condition, and compares the severe risk parameter change value WQ_i of each element with the corresponding preset severe risk parameter change value WQ0_i, judges the severe risk parameter change according to the comparison result, and monitors the monitoring interface parameter curve set under the severe risk condition in real time according to the judgment result, wherein:

[0094] If WQ_i ≥ WQ0_i, the real-time monitoring module determines that the change of the severe danger parameter corresponding to the element is normal, and the real-time monitoring module adds the element to the monitoring interface parameter curve set under severe danger conditions, and performs real-time monitoring of the monitoring interface parameter curve set under severe danger conditions;

[0095] If WQ_i<WQ0_i, the real-time monitoring module determines that the change in the severe risk parameter corresponding to the element is abnormal, the real-time monitoring module does not perform real-time monitoring of the monitoring interface parameter curve set under the severe risk condition, and issues an alarm for the abnormal state of the severe risk parameter change according to the first preset alarm information;

[0096] In the real-time monitoring module, when the real-time monitoring module assesses the patient's condition as a moderate risk condition, the real-time monitoring module obtains in real time the moderate risk parameter change value ZQ_i of each element in the monitoring interface parameter curve set under the moderate risk condition, and compares the moderate risk parameter change value ZQ_i of each element with the corresponding preset moderate risk parameter change value ZQ0_i, judges the moderate risk parameter change according to the comparison result, and monitors the monitoring interface parameter curve set under the moderate risk condition in real time according to the judgment result, wherein:

[0097] If ZQ_i ≥ ZQ0_i, the real-time monitoring module determines that the change of the moderate risk parameter corresponding to the element is normal, and the real-time monitoring module adds the element to the monitoring interface parameter curve set under moderate risk, and performs real-time monitoring of the monitoring interface parameter curve set under moderate risk;

[0098] If ZQ_i<ZQ0_i, the real-time monitoring module determines that the change in the moderate risk parameter corresponding to the element is abnormal, the real-time monitoring module does not perform real-time monitoring of the monitoring interface parameter curve set under the moderate risk condition, and issues an alarm for the abnormal state of the moderate risk parameter change according to the second preset alarm information;

[0099] In the real-time monitoring module, when the real-time monitoring module evaluates the patient's condition as normal, the real-time monitoring module obtains in real time the normal parameter change value CQ_i of each element in the monitoring interface parameter curve set, and compares the normal parameter change value CQ_i of each element with the corresponding preset normal parameter change value CQ0_i, judges the normal parameter change according to the comparison result, and monitors the monitoring interface parameter curve set in real time according to the judgment result, wherein:

[0100] If CQ_i ≥ CQ0_i, the real-time monitoring module determines that the change of the common parameter corresponding to the element is normal, and the real-time monitoring module adds the element to the monitoring interface parameter curve set under normal circumstances, and performs real-time monitoring on the monitoring interface parameter curve set under normal circumstances;

[0101] If CQ_i is less than CQ0_i, the real-time monitoring module determines that the change of the common parameter corresponding to the element is in an abnormal state. The real-time monitoring module does not perform real-time monitoring of the monitoring interface parameter curve set under normal circumstances, and issues an alarm for the abnormal state of the common parameter change according to the third preset alarm information.

[0102] Specifically, the severe risk parameter change value WQ_i refers to the actual parameter change value corresponding to each element in the monitoring interface parameter curve set when the patient's status is assessed as severe risk, and the preset severe risk parameter change value WQ0_i refers to a preset value compared with the severe risk parameter change value WQ_i. For example, the preset severe risk heart rate change value is 140 beats / minute. The monitoring interface parameter curve set under severe risk refers to the parameter curve set of all parameters on the monitoring interface when the patient's status is assessed as severe risk. The first preset Assume that the alarm information refers to the alarm information when the severe risk parameter change is abnormal, for example, using a 2000Hz-5000Hz tone and using a red indicator light to prompt, repeating the alarm every 1 second, the moderate risk parameter change value ZQ_i refers to the actual parameter change value corresponding to each element in the monitoring interface parameter curve set when the patient's status is assessed as moderate risk, and the preset moderate risk parameter change value ZQ0_i refers to the preset value for comparison of the moderate risk parameter change value ZQ_i, for example, the preset moderate risk heart rate change value is 1 00 times / minute, the monitoring interface parameter curve set under moderate risk refers to the parameter curve set of all parameters on the monitoring interface when the patient's status is assessed as moderate risk, the second preset alarm information refers to the alarm information when the moderate risk parameter change is abnormal, for example, using a medium tone of 1000Hz-2000Hz, and using an orange indicator light for prompting, and repeating the alarm every 2 seconds, the common parameter change value CQ_i refers to the actual parameter change value corresponding to each element in the monitoring interface parameter curve set when the patient's status is assessed as normal, the preset common parameter change value CQ0_i refers to a preset value compared with the common parameter change value CQ_i, for example, the preset common heart rate change value is 20 beats / minute, the monitoring interface parameter curve set under normal conditions refers to the parameter curve set of all parameters on the monitoring interface when the patient's status is assessed as normal, the third preset alarm information refers to the alarm information when the common parameter change is abnormal, for example, using a tone of 60Hz-200Hz, and using a yellow indicator light for prompting, and repeating the alarm every 2 seconds.

[0103] Specifically, the real-time monitoring module can accurately assess the patient's condition and detect abnormal conditions in a timely manner by comparing the monitoring parameters with preset values.

[0104] Specifically, the CO2 emission concentration prediction module collects the ventilator CO2 emission concentration and the membrane lung CO2 emission concentration in the extracorporeal membrane oxygenation monitoring interface parameter set according to a preset collection time period, sets the collected ventilator CO2 emission concentration as the first time series X, sets the collected membrane lung CO2 emission concentration as the second time series Y, and creates a distance matrix D to store the distance between each point in the first time series X and the second time series Y, and calculates the distance matrix D according to the Euclidean distance formula, where D ij Represents the distance from xi to yj;

[0105] The CO2 emission concentration prediction module performs path planning on the distance matrix D according to a dynamic programming algorithm to obtain the shortest matching path information, performs feature extraction on the shortest matching path information to obtain the shortest matching path feature information, and trains the long short-term memory network model based on the shortest matching path feature information, and outputs the long short-term memory network model that meets the preset accuracy as the membrane lung CO2 emission concentration prediction model.

[0106] Specifically, the preset collection time period refers to the time range set before the start of data collection, for example, the preset collection time period can be set to 10 minutes, the ventilator CO2 emission concentration refers to the concentration of carbon dioxide in the gas exhaled by the patient using the ventilator, the first time series X refers to the sequence formed by arranging the collected ventilator CO2 emission concentrations in chronological order, the second time series Y refers to the sequence formed by arranging the collected membrane lung CO2 emission concentrations in chronological order, the distance matrix D refers to the matrix used to store the distances between the points in the first time series X and the second time series Y, the dynamic programming algorithm refers to an algorithm used to perform path planning on the distance matrix D, such as the interpolation method, the shortest matching path information refers to the information of the shortest matching path found in the distance matrix D by the dynamic programming algorithm, and the membrane lung CO2 emission concentration prediction model It refers to a model that meets the preset accuracy rate by training the long short-term memory network model based on the shortest matching path feature information. The shortest matching path feature information refers to a data set for training the long short-term memory network model, which is stored in the form of shortest matching path feature-membrane lung CO2 emission concentration. This embodiment does not limit the method of training the long short-term memory network model. For example, it can be set to input the membrane lung CO2 emission concentration training set into the long short-term memory network model for training, and input the membrane lung CO2 emission concentration test set into the trained long short-term memory network model, and optimize the parameters in the long short-term memory network model iteratively until the output result of the membrane lung CO2 emission concentration test set of the long short-term memory network model meets the preset accuracy rate, and the long short-term memory network model is output as a membrane lung CO2 emission concentration prediction model. For example, the preset accuracy rate can be set to 95%.

[0107] Specifically, by collecting and analyzing the CO2 emission concentration time series and training a membrane lung CO2 emission concentration prediction model, the prediction accuracy is improved.

[0108] Specifically, the CO2 emission concentration prediction module obtains the latest ventilator CO2 emission concentration, and inputs the preprocessed latest ventilator CO2 emission concentration into the membrane lung CO2 emission concentration prediction model to predict the membrane lung CO2 emission concentration, thereby obtaining a membrane lung CO2 emission concentration prediction value;

[0109] The CO2 emission concentration prediction module calculates the predicted patient CO2 emission concentration total value Qy based on the ventilator ventilation volume td, the latest ventilator CO2 emission concentration Ct, the membrane lung blood flow Vk and the membrane lung CO2 emission concentration predicted value Cmf, and sets Qy=td×Ct+Vk×Cmf. The CO2 emission concentration difference BP is calculated based on the predicted patient CO2 emission concentration total value Qy and the actual patient CO2 emission concentration total value Sc, and sets BP=Qy-Sc. The CO2 emission concentration difference BP is compared with the preset CO2 emission concentration difference BP0. The consistency state of the latest ventilator CO2 emission concentration change and the membrane lung CO2 emission concentration predicted value is judged according to the comparison result, and the CO2 emission concentration difference BP is adjusted according to the judgment result, wherein:

[0110] When BP≤BP0, the CO2 emission concentration prediction module determines that the consistency state is a compliance state, and the CO2 emission concentration prediction module does not adjust the CO2 emission concentration difference BP;

[0111] When BP>BP0, the CO2 emission concentration prediction module determines that the consistency state is a non-compliant state, and the CO2 emission concentration prediction module adjusts the CO2 emission concentration difference BP, and sets the CO2 emission concentration difference optimization parameter pnd to adjust the CO2 emission concentration difference BP, setting pnd=d0×(BP-BP0), d0>0, the adjusted CO2 emission concentration difference is BP1, and setting BP1=pnd×BP.

[0112] Specifically, the latest ventilator CO2 emission concentration refers to the CO2 concentration emitted by the ventilator at the current time point, the membrane lung CO2 emission concentration refers to the CO2 concentration emitted by the membrane lung, the membrane lung CO2 emission concentration predicted value refers to the value predicted by the membrane lung CO2 emission concentration prediction model, the preset CO2 emission concentration difference BP0 refers to the preset value compared with the actual CO2 emission concentration total value, such as 5 mmHg, the latest ventilator CO2 emission concentration change refers to the change of the ventilator CO2 emission concentration over time, and the CO2 emission concentration difference optimization parameter refers to the parameter used to adjust the CO2 emission concentration difference BP.

[0113] Specifically, the CO2 emission concentration prediction module predicts the membrane lung CO2 emission concentration and compares it with the actual value to achieve accurate monitoring of the patient's CO2 emission concentration.

[0114] Specifically, the equipment operating parameter adjustment module obtains the membrane lung CO2 emission concentration predicted change interval MYJ based on the membrane lung CO2 emission concentration predicted value, and compares the membrane lung CO2 emission concentration predicted change interval MYJ with the preset membrane lung CO2 emission concentration predicted change interval MYJ0, judges the membrane lung CO2 emission concentration predicted change according to the comparison result, and adjusts the ventilator operating parameters and the membrane lung operating parameters according to the judgment result, wherein:

[0115] When MYJ≤MYJ0, the device operating parameter adjustment module determines that the predicted change of the membrane lung CO2 emission concentration is normal, and the device operating parameter adjustment module does not adjust the ventilator operating parameters and the membrane lung operating parameters;

[0116] When MYJ>MYJ0, the device operating parameter adjustment module determines that the predicted change in the membrane lung CO2 emission concentration is abnormal, and the device operating parameter adjustment module adjusts the ventilator operating parameters and the membrane lung operating parameters, wherein:

[0117] If the real-time monitoring module assesses the patient's condition as normal, the device operating parameter adjustment module does not adjust the ventilator operating parameters and the membrane oxygenator operating parameters;

[0118] If the real-time monitoring module assesses the patient's condition as a moderately dangerous situation, the device operating parameter adjustment module adjusts the ventilator operating parameters and the membrane lung operating parameters according to the first preset prediction frequency, and issues an alarm for abnormal changes in the predicted CO2 emission concentration of the membrane lung according to the fourth preset alarm information;

[0119] If the real-time monitoring module assesses the patient's condition as a severe dangerous situation, the equipment operating parameter adjustment module adjusts the ventilator operating parameters and the membrane lung operating parameters according to the second preset prediction frequency, and alarms the abnormal state of the predicted change of the membrane lung CO2 emission concentration according to the fourth preset alarm information.

[0120] Specifically, the membrane lung CO2 emission concentration predicted change interval MYJ refers to the actual change range of the membrane lung CO2 emission concentration predicted value, the preset membrane lung CO2 emission concentration predicted change interval MYJ0 refers to the preset value compared with the membrane lung CO2 emission concentration predicted change interval MYJ, such as ±3mmHg, the membrane lung CO2 emission concentration predicted change refers to the change of the membrane lung CO2 emission concentration predicted value over time, the ventilator operating parameters refer to the parameters for adjusting the ventilator, the membrane lung operating parameters refer to the parameters for adjusting the membrane lung, the first preset prediction frequency refers to the preset frequency when the patient's condition is normal, such as once an hour, the fourth preset alarm information refers to the alarm information issued by the system when the membrane lung CO2 emission concentration predicted change reaches an abnormal state, such as using a 2500Hz-3000Hz tone and flashing blue light, repeating the alarm every 1 second, the second preset prediction frequency refers to the preset frequency when the patient's condition is in a severe and dangerous situation, such as once every 15 minutes.

[0121] Specifically, the device operating parameter adjustment module adjusts the prediction frequency and operating parameters according to the different risk conditions of the patient, and timely adjusts the operating parameters of the ventilator and membrane lung to achieve timely monitoring and early warning of the patient's condition.

[0122] See also Figure 2 , which is a flow chart of a method for monitoring respiratory parameters related to extracorporeal membrane oxygenation (ECMO) according to this embodiment, the method includes:

[0123] Step S1, collecting extracorporeal membrane oxygenation (ECMO)-related respiratory parameters in real time, and preprocessing the extracorporeal membrane oxygenation (ECMO)-related respiratory parameters to obtain extracorporeal membrane oxygenation (ECMO) respiratory parameters;

[0124] Step S2, calculating an extracorporeal membrane oxygenation monitoring interface parameter set in real time according to the extracorporeal membrane oxygenation respiratory parameters, and displaying a monitoring interface parameter curve set in real time according to the extracorporeal membrane oxygenation monitoring interface parameter set;

[0125] Step S3, evaluating the patient's status based on the patient's respiratory data, and monitoring the changes in the monitoring interface parameter curve set in real time based on the status evaluation results;

[0126] Step S4: construct a membrane lung CO2 emission concentration prediction model based on the extracorporeal membrane oxygenation monitoring interface parameter set, and predict the membrane lung CO2 emission concentration based on the membrane lung CO2 concentration prediction model to obtain a membrane lung CO2 emission concentration prediction value, and adjust the ventilator operating parameters and the membrane lung operating parameters based on the membrane lung CO2 emission concentration prediction value.

[0127] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A monitoring system for extracorporeal membrane oxygenation (ECMO)-related respiratory parameters, characterized in that: include: Data acquisition module, used to collect extracorporeal membrane oxygenation ECMO-related respiratory parameters in real time; A data preprocessing module, used to preprocess the extracorporeal membrane oxygenation ECMO-related respiratory parameters to obtain extracorporeal membrane oxygenation respiratory parameters, the data preprocessing module being connected to the data acquisition module; An interface parameter calculation module is used to calculate the extracorporeal membrane oxygenation monitoring interface parameter set in real time according to the extracorporeal membrane oxygenation respiratory parameters, and the interface parameter calculation module is connected to the data preprocessing module; a data visualization module is used to display the monitoring interface parameter curve set in real time according to the extracorporeal membrane oxygenation monitoring interface parameter set, and the data visualization module is connected to the interface parameter calculation module; a real-time monitoring module is used to evaluate the patient's status according to the patient's respiratory data, and to monitor the changes of the monitoring interface parameter curve set in real time according to the status evaluation results, and the real-time monitoring module is connected to the data a visualization module connected; a CO2 emission concentration prediction module, used to construct a membrane lung CO2 emission concentration prediction model based on the extracorporeal membrane oxygenation monitoring interface parameter set, and also used to predict the membrane lung CO2 emission concentration based on the membrane lung CO2 concentration prediction model to obtain a membrane lung CO2 emission concentration prediction value, the membrane lung CO2 emission concentration prediction module is connected to the interface parameter calculation module; an equipment operation parameter adjustment module, used to adjust the ventilator operation parameters and the membrane lung operation parameters according to the membrane lung CO2 emission concentration prediction value, the equipment operation parameter adjustment module is connected to the CO2 emission concentration prediction module; The CO2 emission concentration prediction module collects the ventilator CO2 emission concentration and the membrane lung CO2 emission concentration in the extracorporeal membrane oxygenation monitoring interface parameter set according to a preset collection time period, sets the collected ventilator CO2 emission concentration as the first time series X, sets the collected membrane lung CO2 emission concentration as the second time series Y, and creates a distance matrix D to store the distance between each point in the first time series X and the second time series Y, and calculates the distance matrix D according to the Euclidean distance formula, wherein Dij represents the distance from xi to yj; the CO2 emission concentration prediction module performs path planning on the distance matrix D according to the dynamic programming algorithm to obtain the shortest matching path information, and performs feature extraction on the shortest matching path information to obtain the shortest matching path feature information, and trains the long short-term memory network model according to the shortest matching path feature information, and outputs the long short-term memory network model that meets the preset accuracy as the membrane lung CO2 emission concentration prediction model; The CO2 emission concentration prediction module obtains the latest ventilator CO2 emission concentration, and inputs the preprocessed latest ventilator CO2 emission concentration into the membrane lung CO2 emission concentration prediction model to predict the membrane lung CO2 emission concentration to obtain the membrane lung CO2 emission concentration prediction value.

2. The monitoring system for extracorporeal membrane oxygenation (ECMO)-related respiratory parameters according to claim 1, characterized in that: The data preprocessing module obtains extracorporeal membrane oxygenation ECMO-related respiratory parameters at each moment of the data acquisition device, fits the extracorporeal membrane oxygenation ECMO-related respiratory parameters according to a curve fitting method to obtain a calibration curve equation, obtains a calibration coefficient Aj according to the calibration curve equation, and calibrates the extracorporeal membrane oxygenation ECMO-related respiratory parameters by using the calibration coefficient Aj and a preset calibration coefficient Aj0 according to the data preprocessing module to obtain actual calibration data, and preprocesses the actual calibration data according to an abnormal data detection algorithm to obtain extracorporeal membrane oxygenation respiratory parameters.

3. The monitoring system for extracorporeal membrane oxygenation (ECMO)-related respiratory parameters according to claim 2, characterized in that: The interface parameter calculation module comprehensively evaluates the extracorporeal membrane oxygenation respiratory parameters according to the data comprehensive evaluation method to obtain a comprehensive evaluation value PM, and compares the comprehensive evaluation value PM with a preset comprehensive evaluation value PM0, judges the data preprocessing effect according to the comparison result, and performs real-time calculation of the extracorporeal membrane oxygenation monitoring interface parameter set according to the judgment result, wherein: when PM≥PM0, the interface parameter calculation module determines that the data preprocessing effect meets the standard, and the interface parameter calculation module performs real-time calculation of the extracorporeal membrane oxygenation monitoring interface parameter set; when PM<PM0, the interface parameter calculation module determines that the data preprocessing effect does not meet the standard, the interface parameter calculation module does not perform real-time calculation of the extracorporeal membrane oxygenation monitoring interface parameter set, and re-controls the data preprocessing module to preprocess the extracorporeal membrane oxygenation ECMO-related respiratory parameters until PM≥PM0.

4. The monitoring system for extracorporeal membrane oxygenation (ECMO)-related respiratory parameters according to claim 3, characterized in that: The data visualization module fits the actual monitoring interface measurement data of each element in the extracorporeal membrane oxygenation monitoring interface parameter set at each moment according to the curve fitting method to obtain the actual extracorporeal membrane oxygenation monitoring interface parameter curve corresponding to each element, and calculates the similarity between the actual extracorporeal membrane oxygenation monitoring interface parameter curve and the preset monitoring interface parameter curve corresponding to each element according to the similarity measurement method to obtain the actual parameter curve similarity MS_i corresponding to each element; the data visualization module compares the actual parameter curve similarity MS_i corresponding to each element with the preset actual parameter curve similarity MS0_i corresponding to each element, and judges the fitting effect of the monitoring interface parameter curve corresponding to each element according to the comparison result, and The monitoring interface parameter curve set is displayed in real time according to the judgment result, wherein: when MS_i≥MS0_i, the data visualization module determines that the fitting effect of the monitoring interface parameter curve corresponding to the element meets the standard, the data visualization module adds the monitoring interface parameter curve corresponding to the element to the monitoring interface parameter curve set, and displays the monitoring interface parameter curve set in real time; when MS_i<MS0_i, the data visualization module determines that the fitting effect of the monitoring interface parameter curve corresponding to the element does not meet the standard, and the data visualization module recalculates the similarity between the actual extracorporeal membrane oxygenation monitoring interface parameter curve and the preset monitoring interface parameter curve corresponding to the element according to the similarity measurement method until MS_i≥MS0_i.

5. The monitoring system for extracorporeal membrane oxygenation (ECMO)-related respiratory parameters according to claim 4, characterized in that: The real-time monitoring module calculates the patient's respiratory data A1 according to the patient's respiratory frequency Fv, oxygenation state Yh and ventilation state Tq, and sets A1=α1×Fv+α2×Yh+α3×Tq, α1+α2+α3=1, 0<A1<1, α1 represents the coefficient for adjusting the patient's respiratory frequency Fv, α2 represents the coefficient for adjusting the oxygenation state Yh, and α3 represents the coefficient for adjusting the ventilation state Tq, and compares the patient's respiratory data A1 with the preset patient's respiratory data A0, and performs an evaluation of the patient's respiratory function according to the comparison result. The real-time monitoring module determines that the patient's respiratory function is weak, and the real-time monitoring module evaluates the patient's status as a severe dangerous situation; when A1=A0, the real-time monitoring module determines that the patient's respiratory function is medium, and the real-time monitoring module evaluates the patient's status as a moderate dangerous situation; when A1<A0, the real-time monitoring module determines that the patient's respiratory function is strong, and the real-time monitoring module evaluates the patient's status as a normal situation.

6. The monitoring system for extracorporeal membrane oxygenation (ECMO)-related respiratory parameters according to claim 5, characterized in that: In the real-time monitoring module, when the real-time monitoring module evaluates the patient's condition as a severe risk situation, the real-time monitoring module obtains in real time the severe risk parameter change value WQ_i of each element in the monitoring interface parameter curve set under the severe risk situation, and compares the severe risk parameter change value WQ_i of each element with the corresponding preset severe risk parameter change value WQ0_i, judges the severe risk parameter change situation according to the comparison result, and monitors the monitoring interface parameter curve set under the severe risk situation in real time according to the judgment result; in the real-time monitoring module, when the real-time monitoring module evaluates the patient's condition as a moderate risk situation, the real-time monitoring module obtains in real time the moderate risk parameter change value ZQ_i of each element in the monitoring interface parameter curve set under the moderate risk situation, The moderate risk parameter change value ZQ_i of each element is compared with the corresponding preset moderate risk parameter change value ZQ0_i, the moderate risk parameter change situation is judged according to the comparison result, and the monitoring interface parameter curve set under the moderate risk situation is monitored in real time according to the judgment result; in the real-time monitoring module, when the real-time monitoring module evaluates the patient's condition as normal, the real-time monitoring module obtains the normal parameter change value CQ_i of each element in the monitoring interface parameter curve set under normal circumstances in real time, and compares the normal parameter change value CQ_i of each element with the corresponding preset normal parameter change value CQ0_i, judges the normal parameter change situation according to the comparison result, and monitors the monitoring interface parameter curve set under normal circumstances in real time according to the judgment result.

7. The monitoring system for extracorporeal membrane oxygenation (ECMO)-related respiratory parameters according to claim 1, characterized in that: The device operating parameter adjustment module obtains the membrane lung CO2 emission concentration predicted change interval MYJ based on the membrane lung CO2 emission concentration predicted value, and compares the membrane lung CO2 emission concentration predicted change interval MYJ with the preset membrane lung CO2 emission concentration predicted change interval MYJ0, judges the membrane lung CO2 emission concentration predicted change according to the comparison result, and adjusts the ventilator operating parameters and membrane lung operating parameters according to the judgment result, wherein: when MYJ≤MYJ0, the device operating parameter adjustment module determines that the membrane lung CO2 emission concentration predicted change is normal, and the device operating parameter adjustment module does not adjust the ventilator operating parameters and membrane lung operating parameters; when MYJ>MYJ0, the device operating parameter adjustment module determines that the membrane lung CO2 emission concentration predicted change is abnormal, and the device operating parameter adjustment module adjusts the ventilator operating parameters and membrane lung operating parameters.

Images