ECMO non-invasive cardiopulmonary function monitoring system and auxiliary offline method

Abstract

The invention relates to the technical field of measuring devices for examining respiratory organs, and provides an ECMO non-invasive cardiopulmonary function monitoring system and an auxiliary off-line method.The method comprises the steps that in the ECMO off-line process, auxiliary displacement and self-displacement of a patient at different collection moments are collected, and an auxiliary displacement sequence and a self-displacement sequence of the patient at the current moment are determined; determining an accurate segmentation point in a self displacement sequence, and dividing a respiratory cycle sub-sequence and a real-time respiratory sub-sequence; acquiring a respiratory cycle completion ratio, and determining the carbon dioxide emission capacity of the patient at the current moment by combining the sequence and the value of all the self-discharge capacities contained in the respiratory cycle sub-sequence; eCMO noninvasive cardiopulmonary function monitoring and auxiliary offline are completed according to the auxiliary displacement sequence, the self displacement sequence and the carbon dioxide emission capacity of the patient at the current moment. The invention aims to improve the ECMO automatic auxiliary offline capability and avoid the influence of the breathing rhythm of the patient.

Description

Technical Field

[0001] This invention relates to the field of measuring devices for examining respiratory organs, and specifically to an ECMO non-invasive cardiopulmonary function monitoring system and an auxiliary method for weaning off ECMO. Background Technology

[0002] ECMO is a medical device used to replace a patient's cardiopulmonary function, continuously supplying oxygen to the blood and maintaining vital signs when the patient's cardiopulmonary function fails. After the patient's condition improves, the ECMO device needs to be removed, and the patient must rely on their own cardiopulmonary function. During ECMO weaning, medical staff need to assess the patient's cardiopulmonary function recovery by observing the changes in the patient's own output and the ECMO's assisted output. When the increase in the patient's own output is greater than or equal to the decrease in assisted output, the patient's own cardiopulmonary function can withstand the carbon dioxide emissions from weaning, and medical staff can use a gradual shutdown and dynamic cessation method for weaning.

[0003] However, the autologous output, which characterizes a patient's cardiopulmonary function, fluctuates significantly depending on the patient's breathing rhythm. When comparing the autologous output, which is affected by the patient's breathing rhythm, with the assisted output, it is impossible to directly assess the weaning status in real time through numerical relationships, which can easily lead to insufficient automated assisted weaning capabilities of ECMO. Summary of the Invention

[0004] This invention provides a non-invasive ECMO cardiopulmonary function monitoring system and an assisted weaning method to address the problem that the patient's own output is affected by respiratory rhythm, making it impossible to directly assess the weaning status in real time through the numerical relationship between the patient's own output and assisted output, thus leading to inaccurate evaluation of the automated ECMO weaning capability. The specific technical solution adopted is as follows: In a first aspect, one embodiment of the present invention provides a method for non-invasive ECMO cardiopulmonary function monitoring and assisted weaning from ECMO, the method comprising the following steps: During ECMO weaning, the patient's assisted displacement and autogenous displacement are collected at the current moment and at a number of preset collection moments before the current moment. Based on the assisted displacement and autogenous displacement, the patient's assisted displacement sequence and autogenous displacement sequence at the current moment are determined. Based on the values ​​of self-displacement contained in the self-displacement sequence and the time interval of self-displacement collection, the initial segmentation point in the self-displacement sequence is selected. Combined with the changing trend of self-displacement contained in the self-displacement sequence, the precise segmentation point in the self-displacement sequence is determined. Based on the precise segmentation point, the respiratory cycle subsequence and the real-time respiratory subsequence are divided from the self-displacement sequence. Based on the values ​​and quantities of all self-emissions contained in the respiratory cycle subsequence, the average cycle emission and respiratory cycle length of the respiratory cycle subsequence are obtained. Based on the respiratory cycle length of the respiratory cycle subsequence and the quantity of self-emissions contained in the real-time respiratory subsequence, the respiratory cycle completion ratio of the real-time respiratory subsequence is obtained. Combining the order and values ​​of all self-emissions contained in the respiratory cycle subsequence, the patient's carbon dioxide emission capacity at the current moment is determined. Based on the patient's current assisted output sequence, intrinsic output sequence, and carbon dioxide emission capacity, ECMO non-invasive cardiopulmonary function monitoring and assisted weaning are performed.

[0005] Furthermore, the specific method for selecting the initial segmentation point in its own displacement sequence is as follows: The patient's own exhaust volume sequence was processed using the Fast Fourier Transform algorithm to obtain its spectrum. The reciprocal of the frequency with the largest energy amplitude in the spectrum of the patient's own exhaust volume sequence was recorded as the patient's average respiratory cycle. The rounded value of the ratio of the patient's average respiratory cycle to the time interval of the own exhaust volume sampling was recorded as the number of respiratory cycle samples. Based on the maximum value of the patient's own output sequence at the current moment, a number of own outputs are sampled to the left and right at each respiratory cycle interval in the own output sequence. One own output is selected, and all selected own outputs are recorded as the initial segmentation point.

[0006] Furthermore, the specific method for determining the precise segmentation point in the displacement sequence by combining the displacement change trend contained in the displacement sequence includes: Using the order of its own displacement in its own displacement sequence as the independent variable and the value of its own displacement as the dependent variable, the least squares method is used to fit all its own displacements contained in the displacement vector to obtain the displacement curve and all the maximum points on the displacement curve. The displacement value closest to the maximum value in its own displacement sequence is recorded as the maximum displacement value, and the maximum displacement value closest to the initial segmentation point is recorded as the precise segmentation point. One initial segmentation point corresponds to one precise segmentation point.

[0007] Furthermore, the specific method for dividing the respiratory cycle subsequence and real-time respiratory subsequence from the self-output sequence includes: Using precise split points, the self-output sequence is divided into self-output quantum sequences, and each self-output quantum sequence is recorded as a respiratory cycle subsequence. The last respiratory cycle subsequence is denoted as the real-time respiratory subsequence.

[0008] Furthermore, the specific methods for obtaining the cycle-average output and cycle length of the respiratory cycle subsequence are as follows: The average displacement of all self-outputs contained within a respiratory cycle subsequence is denoted as the periodic average displacement of the respiratory cycle subsequence. The number of self-output volumes contained within a respiratory cycle subsequence is denoted as the respiratory cycle length of the respiratory cycle subsequence.

[0009] Furthermore, the specific method for obtaining the respiratory cycle completion ratio of the real-time respiratory subsequence includes: The respiratory cycle length of the respiratory cycle subsequence whose acquisition time is closest to the current time is taken as the ideal respiratory cycle length of the real-time respiratory subsequence. The number of self-explosions contained in the real-time breathing subsequence is denoted as the respiratory cycle length of the real-time breathing subsequence. The product of the ratio of the respiratory cycle length of the real-time respiratory subsequence to the ideal respiratory cycle length and 100% is denoted as the respiratory cycle completion ratio of the real-time respiratory subsequence.

[0010] Furthermore, the method for determining the patient's carbon dioxide emission capacity at the current moment by combining the order and values ​​of all self-emissions contained within the respiratory cycle subsequence includes the following specific methods: Any respiratory cycle subsequence is denoted as the target respiratory cycle subsequence. The rounded value of the product of the respiratory cycle length of the target respiratory cycle subsequence and the respiratory cycle completion ratio of the real-time respiratory subsequence is denoted as the number of markers. The number of markers of self-output contained in the target respiratory cycle subsequence is denoted as the marked self-output of the target respiratory cycle subsequence. The ratio of the self-output at the current moment to the marked self-output of the target respiratory cycle subsequence is denoted as the relative respiratory intensity of the target respiratory cycle subsequence. The product of the relative respiratory intensity and the average cycle displacement of the target respiratory cycle subsequence is denoted as the cardiopulmonary output of the target respiratory cycle subsequence. The patient's carbon dioxide emission capacity at the current moment is determined by the mean of cardiopulmonary output across all respiratory cycle subsequences.

[0011] Furthermore, the method for determining the patient's carbon dioxide emission capacity at the current moment based on the average cardiopulmonary output of all respiratory cycle subsequences includes: The average cardiopulmonary output of all respiratory cycle subsequences is recorded as the patient's carbon dioxide emission capacity at the current moment.

[0012] Furthermore, the specific methods for performing non-invasive cardiopulmonary function monitoring and assisted weaning from ECMO based on the patient's current assisted output sequence, intrinsic output sequence, and carbon dioxide emission capacity include: The average of all auxiliary emissions contained in the patient's auxiliary emission sequence at the current moment is denoted as the auxiliary emission mean. The average of all self-emissions contained in the patient's self-emission sequence at the current moment is denoted as the self-emission mean. The sum of the auxiliary emission mean and the self-emission mean is denoted as the patient's carbon dioxide emission. The sum of the patient's current carbon dioxide emission capacity and the current auxiliary emission capacity is recorded as the patient's real-time carbon dioxide emission at the current moment. When the patient's real-time carbon dioxide output is greater than or equal to the patient's total carbon dioxide output, ECMO weaning will continue until ECMO weaning is completed. When the patient's real-time carbon dioxide output is greater than the patient's total carbon dioxide output, the ECMO monitoring system will issue an alarm and stop ECMO weaning.

[0013] Secondly, embodiments of the present invention also provide an ECMO non-invasive cardiopulmonary function monitoring system, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0014] The beneficial effects of this invention are: To avoid the influence of the patient's respiratory rhythm on their own output, this application divides the own output sequence according to the patient's respiratory cycle. Specifically, firstly, preliminary segmentation points are selected in the own output sequence based on the patient's respiratory rhythm. Considering that the patient's respiratory rhythm may change over time, and that the average respiratory cycle can only roughly represent the patient's respiratory rhythm and cannot accurately complete the division of the own output sequence, the precise segmentation points in the own output sequence are determined by combining the trend of changes in own output contained in the own output sequence. Based on the precise segmentation points, respiratory cycle subsequences and real-time respiratory subsequences are divided from the own output sequence to eliminate the influence of changes in the patient's respiratory rhythm on the respiratory cycle segmentation. Then, to avoid interference from the patient's respiratory rhythm on their own output, the patient's own output at the same curve position in different respiratory cycle subsequences is used to determine the patient's... The system determines the patient's carbon dioxide emission capacity at the current moment by monitoring changes in the patient's own output volume. This carbon dioxide emission capacity is the patient's actual carbon dioxide emission capacity at the current moment. Finally, based on the patient's assisted output volume sequence, own output volume sequence, and carbon dioxide emission capacity at the current moment, the system compares the patient's physiologically required carbon dioxide emission volume with the total amount of carbon dioxide actually emitted by the patient through the ECMO machine and their own respiration at the current moment. This enables non-invasive cardiopulmonary function monitoring and assisted weaning from ECMO, addressing the issue that the patient's own output volume is affected by respiratory rhythm, making it impossible to directly assess the weaning status in real time through the numerical relationship between the patient's own output volume and assisted output volume. This leads to inaccurate evaluation of the automated ECMO weaning capability, improves the automated ECMO weaning capability, and avoids the influence of the patient's respiratory rhythm on ECMO weaning. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating a non-invasive ECMO cardiopulmonary function monitoring and assisted weaning method according to an embodiment of the present invention. Figure 2 This is a flowchart illustrating the process of obtaining precise segmentation points according to an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figure 1 The diagram illustrates a flowchart of a non-invasive ECMO cardiopulmonary function monitoring and assisted weaning method according to an embodiment of the present invention. The method includes the following steps: Step S001: During the ECMO weaning process, collect the patient's assisted displacement and autogenous displacement at the current time and at a preset number of different collection times before, and determine the patient's assisted displacement sequence and autogenous displacement sequence at the current time based on the assisted displacement and autogenous displacement.

[0019] After the doctor issues the ECMO weaning command, the ECMO control system controls the ECMO device to reduce blood flow at a rate of 0.5 LPM until the blood flow drops to 0 or the ECMO monitoring system issues an alarm.

[0020] When weaning from ECMO, it is necessary to assess the patient's cardiopulmonary function recovery by observing the changes in the patient's own output and the ECMO's assisted output. Therefore, during the ECMO weaning process, it is necessary to obtain the patient's own output and assisted output from the ventilator control system and the ECMO control system, respectively.

[0021] During ECMO weaning, the ventilator's gas exchange volume and carbon dioxide concentration difference are collected through the ventilator's control system, and the ECMO's gas exchange volume and carbon dioxide concentration difference are collected through the ECMO control system. The product of the ventilator's gas exchange volume and carbon dioxide concentration difference is recorded as the assisted output, and the product of the ECMO's gas exchange volume and carbon dioxide concentration difference is recorded as the autologous output.

[0022] In this embodiment, the gas exchange volume and carbon dioxide concentration difference are collected every 0.03 seconds. That is to say, this embodiment obtains an auxiliary displacement and a self-displacement every 0.03 seconds.

[0023] Arrange the current time and the previous 2000 auxiliary displacements in chronological order of the collection time corresponding to the auxiliary displacements to obtain the patient's auxiliary displacement sequence at the current time. Arrange the current time and the previous 2000 self-displacements in chronological order of the collection time corresponding to the self-displacements to obtain the patient's self-displacement sequence at the current time.

[0024] In practical applications, as other implementation methods, implementers can decide the interval of data collection time and the value of the number of data contained in the auxiliary displacement sequence and the self-displacement sequence according to the actual situation. This application does not impose any special restrictions.

[0025] At this point, the patient's auxiliary displacement sequence and auto-displacement sequence at the current moment are obtained.

[0026] Step S002: Based on the values ​​of self-displacement contained in the self-displacement sequence and the time interval of self-displacement acquisition, select the preliminary segmentation point in the self-displacement sequence. Combined with the changing trend of self-displacement contained in the self-displacement sequence, determine the precise segmentation point in the self-displacement sequence. Based on the precise segmentation point, divide the self-displacement sequence into respiratory cycle subsequence and real-time respiratory subsequence.

[0027] The patient's breathing exhibits cyclical changes, meaning that the curves showing changes in autovolumetric output over time are similar across different respiratory cycles, only differing in amplitude. To avoid the influence of the patient's respiratory rhythm on autovolumetric output, it is necessary to divide the patient's respiratory cycle into autovolumetric output sequences and analyze the subsequences within the autovolumetric output sequence corresponding to each respiratory cycle separately.

[0028] First, the respiratory cycle subsequences are divided based on the periodic characteristics exhibited by the self-emission sequence.

[0029] The patient's own exhaust sequence was processed using the Fast Fourier Transform algorithm to obtain its spectrum. The reciprocal of the frequency with the largest energy amplitude in the spectrum of the patient's own exhaust sequence was recorded as the patient's average respiratory cycle.

[0030] The patient's average respiratory cycle is the time it takes for the patient to take one breath at the current moment. The average respiratory cycle can provide information about the patient's breathing rhythm. However, it should be understood that the patient's breathing rhythm may change over time. The average respiratory cycle can only roughly represent the patient's breathing rhythm and cannot accurately complete the division of their own output sequence.

[0031] Furthermore, the auto-emission sequence is divided based on the maximum auto-emission value contained in the patient's auto-emission sequence at the current moment.

[0032] The rounded value of the ratio of the patient's average respiratory cycle to the time interval of the self-output sampling is recorded as the number of respiratory cycle samples for the patient. The maximum self-output value contained in the patient's self-output sequence at the current moment is selected. Based on the maximum self-output value, a number of self-output values ​​are sampled to the right of the self-output sequence every respiratory cycle interval, and one self-output value is selected. At the same time, a number of self-output values ​​are sampled to the left of the self-output sequence every respiratory cycle interval, and one self-output value is selected. All selected self-output values ​​are recorded as the initial segmentation points.

[0033] The number of respiratory cycle samples for a patient is the number of self-output samples contained in one respiratory cycle of the patient. The maximum value of self-output contained in the patient's self-output sequence at the current moment is selected as the benchmark because the sampling time corresponding to the maximum value of self-output is usually the moment when the patient's self-output is the largest in one respiratory cycle. The moment when the self-output is the largest in other respiratory cycles is reflected as the maximum value in the self-output vector, and the period between the maximum value and the maximum value is similar to the average respiratory cycle.

[0034] The initial segmentation point can initially separate the autovoilability of different cycles within the autovoilability vector, but its accuracy can be affected by changes in the patient's respiratory rhythm. It's important to note that when selecting autovoilability to the right of the autovoilability sequence based on the maximum autovoilability value, if no corresponding autovoilability is available, the maximum value is used as the benchmark, and a certain number of autovoilabilities are sampled to the left of the autovoilability sequence at each respiratory cycle interval. This selected autovoilability is then recorded as the initial segmentation point. Similarly, when selecting autovoilability to the left of the autovoilability sequence based on the maximum autovoilability value, if no corresponding autovoilability is available, the maximum value is used as the benchmark, and a certain number of autovoilabilities are sampled to the right of the autovoilability sequence at each respiratory cycle interval. This selected autovoilability is then recorded as the initial segmentation point. For clarity, a situation where no corresponding autovoilability is available is an example where the maximum autovoilability value is the last autovoilability in the sequence; in this case, it's impossible to select an autovoilability to the right of the sequence.

[0035] Using the order of its own displacement in its own displacement sequence as the independent variable and the value of its own displacement as the dependent variable, the least squares method is used to fit all its own displacements included in the displacement vector to obtain the displacement curve. All maxima on the displacement curve are then identified, and the displacement closest to a maxima in the displacement sequence is recorded as the displacement maxima. The displacement maxima closest to the initial segmentation point is recorded as the precise segmentation point.

[0036] It is understandable that each maximum point on the displacement curve corresponds to the nearest maximum displacement value; that is, each maximum point on the displacement curve corresponds to a maximum displacement value. Simultaneously, each initial segmentation point corresponds to a precise segmentation point, and multiple precise segmentation points can be obtained from the displacement sequence. The flowchart for obtaining precise segmentation points is as follows: Figure 2 As shown.

[0037] Using precise split points, the self-output sequence is divided into self-output quantum sequences, and each self-output quantum sequence is recorded as a respiratory cycle subsequence.

[0038] For ease of understanding, an example of dividing the respiratory cycle subsequence is as follows: If the self-displacement vector contains 2000 self-displacements, and the precise split points are the 400th, 800th, and 1200th self-displacements, then the precise split points divide the self-displacement quantum sequence into 4 self-displacement quantum sequences, that is, 4 respiratory cycle subsequences. Among them, the 1st to the 400th self-displacement constitutes the first respiratory cycle subsequence, the 401st to the 800th self-displacement constitutes the second respiratory cycle subsequence, the 801st to the 1200th self-displacement constitutes the third respiratory cycle subsequence, and the 1201st to the 2000th self-displacement constitutes the fourth respiratory cycle subsequence.

[0039] This embodiment determines the precise segmentation point by combining the maximum value in its own displacement vector with the initial segmentation point, thus eliminating the influence of changes in the patient's breathing rhythm on the segmentation of the respiratory cycle.

[0040] It is understood that the patient’s own output over 60 seconds is obtained in this embodiment. When a human is at rest, the average interval between breaths is 3 to 5 seconds, so 12 to 20 respiratory cycle subsequences can usually be obtained, with each respiratory cycle subsequence corresponding to one respiratory cycle.

[0041] Since the first and last respiratory cycle subsequences may correspond to incomplete respiratory cycles, they are no longer included in the analysis of subsequent respiratory cycle subsequences.

[0042] Since the last respiratory cycle subsequence is the most accurate collection of the patient's respiratory information at the current moment, the last respiratory cycle subsequence is recorded as the real-time respiratory subsequence.

[0043] At this point, the respiratory cycle subsequence and the real-time respiratory subsequence have been obtained.

[0044] Step S003: Based on the values ​​and quantities of all self-emissions contained in the respiratory cycle subsequence, obtain the average cycle emission and respiratory cycle length of the respiratory cycle subsequence. Based on the respiratory cycle length of the respiratory cycle subsequence and the quantity of self-emissions contained in the real-time respiratory subsequence, obtain the respiratory cycle completion ratio of the real-time respiratory subsequence. Combine the order and values ​​of all self-emissions contained in the respiratory cycle subsequence to determine the patient's carbon dioxide emission capacity at the current moment.

[0045] By analyzing the patient's own output at the same curve position in different respiratory cycle subsequences, we can determine the change in the patient's own output at the current moment and avoid interference from the patient's breathing rhythm on their own output.

[0046] During the same respiratory cycle, the autovolumetric output at different times will fluctuate dramatically due to the patient's breathing process. Therefore, the actual real-time measured autovolumetric output accurately represents the patient's carbon dioxide emission capacity at the current moment. All autovolumetric outputs within a respiratory cycle should be considered to accurately represent the patient's actual carbon dioxide emission capacity within that respiratory cycle.

[0047] The average of all self-output volumes contained within the same respiratory cycle subsequence is denoted as the periodic average output volume of the respiratory cycle subsequence. The number of self-output volumes contained within the same respiratory cycle subsequence is denoted as the respiratory cycle length of the respiratory cycle subsequence.

[0048] The cycle-average output (CEPA) of a respiratory cycle subsequence represents the patient's actual carbon dioxide emission capacity within one respiratory cycle corresponding to the subsequence. A higher CEPA indicates a stronger actual carbon dioxide emission capacity within that subsequence. The respiratory cycle length (RCS) of a respiratory cycle subsequence represents the length of one respiratory cycle within the subsequence. A longer RCS indicates a longer respiratory cycle within the subsequence.

[0049] Since changes in a patient's breathing rhythm occur gradually, the length of the respiratory cycle of the subsequence whose acquisition time is closest to the current time is taken as the length of the respiratory cycle that should appear in the real-time respiratory subsequence.

[0050] Specifically, the respiratory cycle length of the respiratory cycle subsequence whose acquisition time is closest to the current time is taken as the ideal respiratory cycle length of the real-time respiratory subsequence. The number of self-explosions contained in the real-time respiratory subsequence is recorded as the respiratory cycle length of the real-time respiratory subsequence. The product of the ratio of the respiratory cycle length of the real-time respiratory subsequence to the ideal respiratory cycle length and 100% is recorded as the respiratory cycle completion ratio of the real-time respiratory subsequence.

[0051] Any respiratory cycle subsequence is denoted as the target respiratory cycle subsequence. The rounded value of the product of the respiratory cycle length of the target respiratory cycle subsequence and the respiratory cycle completion ratio of the real-time respiratory subsequence is denoted as the number of markers. The number of markers of self-output contained in the target respiratory cycle subsequence is denoted as the marker self-output of the target respiratory cycle subsequence.

[0052] The labeled self-output of the target respiratory cycle subsequence is the self-output corresponding to the self-output at the current moment in the target respiratory cycle subsequence. By directly comparing the labeled self-output of the target respiratory cycle subsequence with the self-output at the current moment, the respiratory intensity of the respiratory cycle corresponding to the real-time respiratory subsequence can be directly compared with that of the respiratory cycle corresponding to the target respiratory cycle subsequence.

[0053] The ratio of the current self-output volume to the labeled self-output volume of the target respiratory cycle subsequence is denoted as the relative respiratory intensity of the target respiratory cycle subsequence.

[0054] The relative respiratory intensity of any respiratory cycle subsequence can be obtained using the same method.

[0055] When the relative respiratory intensity of a respiratory cycle subsequence is greater, the patient's current self-output is greater than the respiratory intensity of the patient corresponding to the marked self-output, and the patient's carbon dioxide output is greater and their cardiopulmonary function is stronger at the current moment.

[0056] The product of the relative respiratory intensity and the average cycle output of the target respiratory cycle subsequence is denoted as the cardiopulmonary output of the target respiratory cycle subsequence. The average of the cardiopulmonary outputs of all respiratory cycle subsequences is denoted as the patient's carbon dioxide emission capacity at the current moment.

[0057] The patient's carbon dioxide emission capacity at the current moment represents the amount of carbon dioxide emitted by the patient's own cardiopulmonary function.

[0058] This allows us to obtain the patient's carbon dioxide emission capacity at the current moment.

[0059] Step S004: Based on the patient's assisted output sequence, autogenous output sequence, and carbon dioxide emission capacity at the current moment, complete the ECMO non-invasive cardiopulmonary function monitoring and assist in weaning from ECMO.

[0060] The average of all auxiliary emissions contained in the patient's auxiliary emission sequence at the current moment is denoted as the auxiliary emission mean. The average of all self-emissions contained in the patient's self-emission sequence at the current moment is denoted as the self-emission mean. The sum of the auxiliary emission mean and the self-emission mean is denoted as the patient's carbon dioxide emission.

[0061] The sum of the patient's current carbon dioxide emission capacity and the current auxiliary emission capacity is denoted as the patient's real-time carbon dioxide emission at the current moment. The ratio of the patient's real-time carbon dioxide emission to the patient's total carbon dioxide emission is denoted as the estimated weaning status.

[0062] The patient's carbon dioxide output is a calculated value based on the patient's physiological needs for carbon dioxide output, while the patient's real-time carbon dioxide output at the current moment is the total amount of carbon dioxide actually emitted by the patient through the ECMO machine and their own respiration at that moment. When the patient's real-time carbon dioxide output at the current moment is greater than or equal to the patient's carbon dioxide output, the patient's cardiopulmonary function can withstand the reduction in carbon dioxide output when weaning off ECMO, and the patient's own cardiopulmonary function can support the ECMO weaning action. In this case, the weaning status estimate is greater than or equal to 1. Conversely, when the patient's real-time carbon dioxide output at the current moment is less than the patient's carbon dioxide output, the patient's cardiopulmonary function cannot withstand the reduction in carbon dioxide output when weaning off ECMO, and the patient's own cardiopulmonary function cannot support the ECMO weaning action. Weaning should be stopped immediately. In this case, the weaning status estimate is less than 1.

[0063] When the estimated weaning status is less than 1, the ECMO monitoring system will issue an alarm and stop ECMO weaning; when the estimated weaning status is greater than or equal to 1, ECMO weaning will continue until the blood flow drops to 0 and weaning is completed.

[0064] At this point, the non-invasive cardiopulmonary function monitoring and assisted weaning from ECMO were completed.

[0065] Based on the same inventive concept as the above method, this embodiment of the invention also provides an ECMO non-invasive cardiopulmonary function monitoring system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described methods for ECMO non-invasive cardiopulmonary function monitoring and assisted weaning.

[0066] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for non-invasive cardiopulmonary function monitoring and assisted weaning from ECMO, characterized in that, The method includes the following steps: During ECMO weaning, the patient's assisted displacement and autogenous displacement are collected at the current moment and at a number of preset collection moments before the current moment. Based on the assisted displacement and autogenous displacement, the patient's assisted displacement sequence and autogenous displacement sequence at the current moment are determined. Based on the values ​​of self-displacement contained in the self-displacement sequence and the time interval of self-displacement collection, the initial segmentation point in the self-displacement sequence is selected. Combined with the changing trend of self-displacement contained in the self-displacement sequence, the precise segmentation point in the self-displacement sequence is determined. Based on the precise segmentation point, the respiratory cycle subsequence and the real-time respiratory subsequence are divided from the self-displacement sequence. Based on the values ​​and quantities of all self-emissions contained in the respiratory cycle subsequence, the average cycle emission and respiratory cycle length of the respiratory cycle subsequence are obtained. Based on the respiratory cycle length of the respiratory cycle subsequence and the quantity of self-emissions contained in the real-time respiratory subsequence, the respiratory cycle completion ratio of the real-time respiratory subsequence is obtained. Combining the order and values ​​of all self-emissions contained in the respiratory cycle subsequence, the patient's carbon dioxide emission capacity at the current moment is determined. Based on the patient's current assisted output sequence, intrinsic output sequence, and carbon dioxide emission capacity, ECMO non-invasive cardiopulmonary function monitoring and assisted weaning are performed.

2. The method for non-invasive cardiopulmonary function monitoring and assisted weaning from ECMO according to claim 1, characterized in that, The specific method for selecting the initial segmentation point in its own displacement sequence is as follows: The patient's own exhaust volume sequence was processed using the Fast Fourier Transform algorithm to obtain its spectrum. The reciprocal of the frequency with the largest energy amplitude in the spectrum of the patient's own exhaust volume sequence was recorded as the patient's average respiratory cycle. The rounded value of the ratio of the patient's average respiratory cycle to the time interval of the own exhaust volume sampling was recorded as the number of respiratory cycle samples. Based on the maximum value of the patient's own output sequence at the current moment, a number of own outputs are sampled to the left and right at each respiratory cycle interval in the own output sequence. One own output is selected, and all selected own outputs are recorded as the initial segmentation point.

3. The method for non-invasive cardiopulmonary function monitoring and assisted weaning from ECMO according to claim 1, characterized in that, The method for determining the precise segmentation point in the displacement sequence by combining the displacement change trend contained in the displacement sequence includes the following specific methods: Using the order of its own displacement in its own displacement sequence as the independent variable and the value of its own displacement as the dependent variable, the least squares method is used to fit all its own displacements contained in the displacement vector to obtain the displacement curve and all the maximum points on the displacement curve. The displacement value closest to the maximum value in its own displacement sequence is recorded as the maximum displacement value, and the maximum displacement value closest to the initial segmentation point is recorded as the precise segmentation point. One initial segmentation point corresponds to one precise segmentation point.

4. The method for non-invasive cardiopulmonary function monitoring and assisted weaning from ECMO according to claim 1, characterized in that, The specific method for dividing the respiratory cycle subsequence and real-time respiratory subsequence from the self-output sequence includes: Using precise split points, the self-output sequence is divided into self-output quantum sequences, and each self-output quantum sequence is recorded as a respiratory cycle subsequence. The last respiratory cycle subsequence is denoted as the real-time respiratory subsequence.

5. The method for non-invasive cardiopulmonary function monitoring and assisted weaning from ECMO according to claim 1, characterized in that, The specific methods for obtaining the cycle average output and respiratory cycle length of the respiratory cycle subsequence are as follows: The average displacement of all self-outputs contained within a respiratory cycle subsequence is denoted as the periodic average displacement of the respiratory cycle subsequence. The number of self-output volumes contained within a respiratory cycle subsequence is denoted as the respiratory cycle length of the respiratory cycle subsequence.

6. The method for non-invasive cardiopulmonary function monitoring and assisted weaning from ECMO according to claim 1, characterized in that, The specific method for obtaining the respiratory cycle completion ratio of the real-time respiratory subsequence includes: The respiratory cycle length of the respiratory cycle subsequence whose acquisition time is closest to the current time is taken as the ideal respiratory cycle length of the real-time respiratory subsequence. The number of self-explosions contained in the real-time breathing subsequence is denoted as the respiratory cycle length of the real-time breathing subsequence. The product of the ratio of the respiratory cycle length of the real-time respiratory subsequence to the ideal respiratory cycle length and 100% is denoted as the respiratory cycle completion ratio of the real-time respiratory subsequence.

7. The method for non-invasive cardiopulmonary function monitoring and assisted weaning from ECMO according to claim 1, characterized in that, The method for determining the patient's carbon dioxide emission capacity at the current moment by combining the order and values ​​of all self-emissions contained in the respiratory cycle subsequence includes the following specific methods: Any respiratory cycle subsequence is denoted as the target respiratory cycle subsequence. The rounded value of the product of the respiratory cycle length of the target respiratory cycle subsequence and the respiratory cycle completion ratio of the real-time respiratory subsequence is denoted as the number of markers. The number of markers of self-output contained in the target respiratory cycle subsequence is denoted as the marked self-output of the target respiratory cycle subsequence. The ratio of the self-output at the current moment to the marked self-output of the target respiratory cycle subsequence is denoted as the relative respiratory intensity of the target respiratory cycle subsequence. The product of the relative respiratory intensity and the average cycle displacement of the target respiratory cycle subsequence is denoted as the cardiopulmonary output of the target respiratory cycle subsequence. The patient's carbon dioxide emission capacity at the current moment is determined by the mean of cardiopulmonary output across all respiratory cycle subsequences.

8. The ECMO non-invasive cardiopulmonary function monitoring and assisted weaning method according to claim 7, characterized in that, The method for determining the patient's carbon dioxide emission capacity at the current moment based on the average cardiopulmonary output of all respiratory cycle subsequences includes: The average cardiopulmonary output of all respiratory cycle subsequences is recorded as the patient's carbon dioxide emission capacity at the current moment.

9. The method for non-invasive cardiopulmonary function monitoring and assisted weaning from ECMO according to claim 1, characterized in that, The method for performing non-invasive ECMO cardiopulmonary function monitoring and assisted weaning based on the patient's current assisted output sequence, intrinsic output sequence, and carbon dioxide emission capacity includes the following specific methods: The average of all auxiliary emissions contained in the patient's auxiliary emission sequence at the current moment is denoted as the auxiliary emission mean. The average of all self-emissions contained in the patient's self-emission sequence at the current moment is denoted as the self-emission mean. The sum of the auxiliary emission mean and the self-emission mean is denoted as the patient's carbon dioxide emission. The sum of the patient's current carbon dioxide emission capacity and the current auxiliary emission capacity is recorded as the patient's real-time carbon dioxide emission at the current moment. When the patient's real-time carbon dioxide output is greater than or equal to the patient's total carbon dioxide output, ECMO weaning continues until ECMO weaning is completed. When the patient's real-time carbon dioxide output is greater than the patient's total carbon dioxide output, the ECMO monitoring system will issue an alarm and stop ECMO weaning.

10. An ECMO noninvasive cardiopulmonary function monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as claimed in any one of claims 1-9.

Images