A method for obtaining a spontaneous breathing effort curve under mechanical ventilation based on a ventilator waveform

Abstract

The application discloses a method for obtaining an autogenous breathing effort curve under mechanical ventilation based on a breathing machine waveform, which can calculate resistance and compliance in a patient's respiratory system through airway pressure and flow rate waveforms of the breathing machine when the breathing machine ventilates the patient, and then calculate the autogenous breathing effort of the patient during each breath according to the resistance and compliance and the pressure and flow rate waveforms. For each different patient, the method can calculate the change of pressure and resistance with time and the inspiratory effort intensity curve of each breath. The content can help doctors better judge the condition of the patient, thereby better assisting clinical treatment.

Description

Technical Field

[0001] This invention relates to the field of monitoring spontaneous breathing effort during mechanical ventilation. More particularly, it relates to a method for obtaining a spontaneous breathing effort curve based on ventilator waveforms during mechanical ventilation, and a method for monitoring spontaneous breathing effort in patients under mechanical ventilation. Background Technology

[0002] Mechanical ventilation (MV) refers to the provision of complete or partial artificial ventilation using a ventilator. Mechanical ventilation helps move air into and out of the lungs, with the primary goal of helping to deliver oxygen and remove carbon dioxide. There are many reasons for using mechanical ventilation, including airway obstruction due to various causes, requiring adequate oxygenation, or the removal of excess carbon dioxide from the lungs. Proper ventilator management is a particularly important concern for patients.

[0003] Currently, estimations of patient-specific respiratory mechanics have yielded some results in optimizing patient-specific mechanical ventilation. However, for patients with spontaneous breathing (SB), additional equipment or invasive clinical procedures are required to determine the patient's true respiratory mechanics because the patient's own respiratory effort obscures the observations of model-based lung mechanics. Therefore, estimating respiratory mechanics to guide MV is currently limited to fully sedated patients, and is often unreliable when patients are semi-conscious or awake due to the presence of spontaneous breathing. This problem greatly limits the use of model-based methods.

[0004] During supportive mechanical ventilation, the patient's spontaneous breathing effort triggers the ventilator, enabling it to support the patient's inspiratory effort. Insufficient or excessive ventilator support can lead to discomfort, fear, and even lung injury, all of which can cause stress and prolong ventilation time. Inspiratory strength is also a crucial parameter for the follow-up recovery of critically ill patients and a decisive factor in successful weaning from the ventilator; therefore, reliable monitoring of inspiratory strength in intensive care unit patients during supportive mechanical ventilation is essential in clinical practice.

[0005] In recent years, many methods have emerged for estimating spontaneous breathing effort. These include model-based methods. For example, Francesco, Daniel P. Redmond, and Ganesa et al. have used different spontaneous breathing models and then employed the least squares method based on ventilator waveforms to find the best-fit values ​​for respiratory parameters. This involves simulating spontaneous breathing by using various functions, either individually or in combination, to create a new function. However, these function-based methods are limited by the complexity of the functions and models, making it difficult to achieve better fits. Furthermore, model-based methods require adjusting model settings to fit different patients and varying inspiratory efforts within the same patient, significantly increasing the difficulty and reducing the efficiency of these methods.

[0006] Therefore, many methods have emerged using machine learning to study inspiratory effort. Ang CYS proposed using a convolutional autoencoder to quantify the magnitude of respiratory effort in spontaneously breathing patients. It is assumed that machine learning can reconstruct high-level features from input data, thus providing better accuracy and robustness in predicting the magnitude of spontaneous breathing effort. Using machine learning eliminates the need for mathematical modeling of processes involving spontaneous breathing effort, reducing the required computational resources, and therefore can be used to assess a patient's respiratory status and effort in real time. However, the datasets required to train the model are large and inconvenient for clinical use. Summary of the Invention

[0007] The purpose of this invention is to address the shortcomings of existing technologies by developing a method for obtaining spontaneous respiratory effort curves under mechanical ventilation based on ventilator waveforms. This method first calculates the resistance and compliance of the patient's respiratory system using the airway pressure and flow rate waveforms during ventilator ventilation. Then, it calculates the magnitude of the patient's spontaneous respiratory effort with each breath based on the resistance-compliance and pressure-flow rate waveforms. For each individual patient, this method can calculate the changes in pressure and resistance over time for each breath, as well as the inspiratory effort intensity curve for each breath. This information can help physicians better assess the patient's condition, thereby better supporting clinical treatment.

[0008] The specific solution adopted in this invention is as follows:

[0009] A method for obtaining spontaneous breathing effort curves under mechanical ventilation based on ventilator waveforms includes:

[0010] Acquire ventilator waveform data and airway pressure data of patients under mechanical ventilation;

[0011] Based on the acquired ventilator waveform data, the resistance and compliance of the patient's respiratory system at various time points are calculated;

[0012] Based on the acquired ventilator waveform data, airway pressure data, and calculated resistance and compliance of the patient's respiratory system at various time points, the inspiratory effort at each time point is calculated using an inspiratory effort formula constructed based on a circuit model of the respiratory system, thereby obtaining the patient's spontaneous breathing effort curve under mechanical ventilation; wherein, the inspiratory effort formula constructed based on the circuit model of the respiratory system is expressed as follows:

[0013]

[0014] In the formula, P mus P strives to induce the patient's breathing. aw R is the patient's airway pressure, V is the airflow velocity, and the integral of the velocity over time is the tidal volume. r and Cr These are the patient's respiratory system resistance and compliance, respectively.

[0015] Furthermore, the ventilator waveform data includes flow-time signals, pressure-time signals, and tidal volume-time signals.

[0016] Furthermore, in the calculation of the resistance and compliance of the patient's respiratory system at each time point, the average resistance and average compliance of the patient's respiratory system for each breath are calculated as the resistance and compliance at each time point of that breath.

[0017] Furthermore, in calculating the resistance and compliance of the patient's respiratory system at various time points, each breath is divided into four stages based on changes in airway pressure and flow rate: pressure rise stage, pressure stabilization stage, pressure fall stage, and end-expiration stage; the average resistance and average compliance of the patient's respiratory system at each stage of each breath are calculated as the resistance and compliance at each time point within the corresponding stage of that breath.

[0018] Furthermore, the mean resistance and mean compliance during the end-expiratory phase are calculated using the following formula:

[0019]

[0020] Where d(sumV) represents the change in tidal volume at the end of the respiratory tract, and d(P) represents the change in pressure at the end of the respiratory tract, P = P aw d(V) represents the change in flow rate during the end-respiratory phase.

[0021] Furthermore, after calculating the resistance and compliance of the patient's respiratory system at each time point, the calculation also includes smoothing the resistance and compliance of the patient's respiratory system at each time point.

[0022] Furthermore, the smoothing process specifically involves:

[0023] In the curves representing the resistance and compliance of the patient's respiratory system at various time points, the values ​​at time s are sequentially adjusted to the average values ​​of the data within the time interval [sw:s+w], where w is the sliding window length.

[0024] A method for monitoring spontaneous breathing effort in patients under mechanical ventilation, specifically:

[0025] The method described above, which uses ventilator waveforms to obtain spontaneous breathing effort curves under mechanical ventilation, is used to obtain spontaneous breathing effort curves of patients under mechanical ventilation in real time, thereby monitoring patients' spontaneous breathing effort.

[0026] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a method for acquiring a spontaneous breathing effort curve under mechanical ventilation based on a ventilator waveform or a method for monitoring a patient's spontaneous breathing effort under mechanical ventilation.

[0027] A storage medium containing computer-executable instructions, which, when executed by a computer processor, implement the method for calculating a spontaneous breathing effort curve under mechanical ventilation based on a ventilator waveform or a method for monitoring a patient's spontaneous breathing effort under mechanical ventilation.

[0028] A computer program product includes a computer program / instructions that, when executed by a processor, implement the steps of a method for calculating a spontaneous breathing effort curve under mechanical ventilation based on a ventilator waveform or a method for monitoring a patient's spontaneous breathing effort under mechanical ventilation.

[0029] Compared with the prior art, the beneficial effects of the present invention are:

[0030] This invention discloses a method for calculating the spontaneous breathing effort curve based on ventilator pressure and flow rate waveforms. A mathematical model of the human respiratory system is established using mathematical modeling methods. The calculation of the spontaneous breathing effort curve is then implemented based on this mathematical model.

[0031] Furthermore, this invention uses segmented calculation of resistance and compliance to more precisely calculate the changes in resistance and compliance at different time points during a single breath. The segmented calculation fully considers the influence of pressure and flow rate changes during respiration on resistance and compliance. A single breath waveform is divided into a pressure rise phase, a pressure stabilization phase, a pressure fall phase, and a terminal phase. This classification method is primarily based on pressure changes, and within each time point, the flow rate changes are monotonic, either monotonically increasing or monotonically decreasing, thus effectively distinguishing different stages of respiration. Differentiating between the first three phases where inspiratory effort is more pronounced and the terminal phase where there is almost no inspiratory effort, and using different calculation methods, can also improve the accuracy of resistance and compliance calculations. The segmented calculation of resistance and compliance proposed in this invention has a certain degree of interpretability.

[0032] Meanwhile, as drag and compliance change over time, the sudden shift from one time period to another causes a significant and abrupt change in the calculated inhalation effort, resulting in a jittering phenomenon in the waveform. Therefore, to address this issue, this invention employs a sliding window to smooth the drag and compliance data. By smoothing the drag and compliance data, the jittering phenomenon in the final calculated inhalation effort can be reduced.

[0033] By calculating resistance and compliance in segments and then smoothing the results using a sliding window, a patient's inspiratory effort can be calculated more accurately. This provides further support for research on patient inspiratory effort. Attached Figure Description

[0034] Figure 1 This is a flowchart of a method for calculating the spontaneous breathing effort curve under mechanical ventilation based on ventilator waveforms, according to an embodiment of the present invention.

[0035] Figure 2 This is a circuit model diagram of a ventilator-patient model.

[0036] Figure 3 This is a comparison chart of inspiratory effort and esophageal pressure fitted when only average resistance and compliance are calculated in one embodiment of the present invention.

[0037] Figure 4 This is a comparison chart of inspiratory effort and esophageal pressure fitted when segmented calculation of resistance and compliance is used in one embodiment of the present invention.

[0038] Figure 5 This is a comparison chart of inspiratory effort and esophageal pressure fitted when the resistance and compliance are calculated in segments and smoothed in one embodiment of the present invention. Detailed Implementation

[0039] The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be understood that the preferred embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0040] This invention provides a method for obtaining a spontaneous breathing effort curve under mechanical ventilation based on ventilator waveforms, the method comprising the following steps:

[0041] Step 1: Obtain ventilator waveform data and airway pressure data for the patient under mechanical ventilation;

[0042] Step 2: Based on the acquired ventilator waveform data, calculate the resistance and compliance of the patient's respiratory system at various time points;

[0043] Step 3: Based on the acquired ventilator waveform data, airway pressure data, and the calculated resistance and compliance of the patient's respiratory system at various time points, the inspiratory effort at each time point is calculated using the inspiratory effort formula constructed based on the circuit model of the respiratory system, thereby obtaining the patient's spontaneous breathing effort curve under mechanical ventilation.

[0044] This invention presents an inspiratory effort formula based on a circuit model of the respiratory system. The mechanical components of the model are described using a circuit model, effectively converting the mechanical model into a circuit model. The main components are: voltage to describe air pressure, current to describe airflow, resistance to describe resistance, and capacitance to describe elasticity. This allows the respiratory system to be represented using a circuit system. The model used in this invention is a single-chamber model, treating the entire respiratory system as a whole, and employing a resistor and capacitor to represent the entire respiratory system's obstruction of airflow. Specifically, refer to... Figure 2 To build a mathematical model of the patient's respiratory system. Figure 2 This invention presents a model of patient-ventilator interaction, divided into a patient component and a ventilator component. Only the patient component is considered in this invention. The patient component uses a linear resistor Rr and a linear capacitor Cr to represent the resistance and compliance of the patient's respiratory system. The driving force simulates spontaneous breathing, i.e., pressure generated by the respiratory muscles (respiratory muscle pressure, P). mus This drives the entire respiratory system mathematical model to generate respiratory waveforms. The specific circuit topology is as follows: respiratory system resistor R r One end is the airway pressure P aw The other end is connected to the respiratory system capacitor C. r Connected, respiratory system capacitance C r The other end is connected to the driving force voltage source P. mus Positive port, driving force voltage source P mus The negative port is grounded. Then, based on the law of conservation of mass, the differential equations for the respiratory system are written. The law of conservation of mass in a circuit can be described as: in a branch, the current is the same everywhere. Based on the relationship between voltage (U), current (I), and capacitance (C):

[0045]

[0046] Differential equations for the current and voltage at each node can be obtained. By solving these differential equations, the voltage and current at each moment can be obtained.

[0047] Based on the established single-chamber model and the law of conservation of mass, a formula concerning inspiratory effort can be derived:

[0048]

[0049] Based on the actual meaning of the respiratory system described by the circuit model, it can be known that P mus P strives to induce the patient's breathing. aw R is the patient's airway pressure, V is the airflow velocity, and the integral of the velocity over time is the tidal volume. r and C r These are the patient's respiratory system resistance and compliance, respectively.

[0050] In a specific implementation plan, the method for calculating the resistance and compliance of the patient's respiratory system at each time point based on the acquired ventilator waveform data in step two is as follows: calculate the average resistance and average compliance of the patient's respiratory system for each breath as the resistance and compliance at each time point of that breath.

[0051] Among these, patient resistance and compliance can be obtained by least-squares fitting using the patient's airway pressure, flow rate, and esophageal pressure data, according to the following formula:

[0052]

[0053] In this formula, esophageal pressure is used instead of P. mus .

[0054] Alternatively, the compliance calculation method in patent ZL202110049428.5 can be used for calculation.

[0055] The compliance C can also be estimated using respiratory mechanics equations of motion and least squares algorithms. r and airway resistance R r Estimated value;

[0056] The equations of motion for respiratory mechanics are as follows:

[0057]

[0058] Where P(t) represents pressure-time data, F(t) represents flow-time data, V(t) represents tidal volume-time data, and PEEP represents positive end-expiratory pressure.

[0059] Furthermore, fitting using the least squares method can calculate the average resistance, compliance, and reliability of the calculation during a single breath. However, during a single breath, the resistance and compliance of the patient's respiratory system constantly change due to variations in conditions such as pressure and flow rate. Using a single average resistance and compliance for a single breath can lead to errors in calculating inspiratory effort. Therefore, in a more optimized approach, such as... Figure 2 As shown, the specific method for calculating the resistance and compliance of the patient's respiratory system at various time points based on the acquired ventilator waveform data in step two is as follows:

[0060] Analyze each breath according to changes in airway pressure and flow rate, such as Figure 1As shown, the entire respiratory process is divided into four stages: the pressure rise stage, the pressure plateau stage, the pressure fall stage, and the end-expiratory stage. During the pressure rise stage, both airway pressure and flow rate increase rapidly. During the pressure plateau stage, airway pressure stabilizes with little change, while flow rate gradually rises to its peak. During the pressure fall stage, airway pressure rapidly decreases to PEEP (positive end-expiratory pressure), and flow rate also decreases rapidly. In the end-expiratory stage, pressure stabilizes at PEEP, and flow rate changes relatively slowly. This classification method is primarily based on pressure changes, and the flow rate changes monotonically within each time period, either increasing or decreasing monotonically. Therefore, it can effectively distinguish the different stages of respiration. Based on this, the average resistance and average compliance of the patient's respiratory system are calculated for each stage of each respiration as the resistance and compliance at each time point within that corresponding stage. In the first three stages, the least squares method yields a high degree of fit, making these data usable. However, in the late respiratory stage, the patient's respiratory effort is quite weak, resulting in low reliability of the pressure data fitted using the least squares method; therefore, the fitted data cannot be directly used. But observing the changes in pressure, flow rate, and other waveforms in the latter half reveals that these data remain stable during this period. If resistance and compliance are constant or show little change during this time, then the more basic formulas for calculating resistance and compliance can be used to calculate these values ​​for this period. The formulas are as follows:

[0061]

[0062] Where d(sumV) represents the change in tidal volume, and d(P) represents the change in pressure, including the patient's airway pressure and inspiratory effort. Since the patient's inspiratory effort does not change in the end-expiratory phase, P = Ps. aw d(V) represents the change in flow velocity. From this, we can obtain the resistance and compliance over several time intervals. Connecting these intervals in chronological order yields a function of resistance and compliance over time during a single breath. By using a piecewise calculation and replacing a single average resistance and compliance value with a function of resistance and compliance over time, we can improve the accuracy of the calculation.

[0063] The average compliance and average resistance of a single breath calculated using the two methods described above, based on the collected real patient waveform data, as well as some results of calculating the resistance and compliance of the patient's respiratory system in four time periods, are also recorded in Tables 1 and 2.

[0064] Table 1. Partial results of compliance calculation

[0065]

[0066] Table 2 Partial Results of Resistance Calculation

[0067]

[0068] Furthermore, after calculating drag and compliance in segmented time periods, the data undergoes abrupt changes when switching from one time period to another, causing problems in the calculation of data within this transitional period. During this time, when calculating inhalation effort, the sudden change in drag and compliance leads to a significant and abrupt change in the calculated inhalation effort, resulting in a noticeable jitter in the waveform. Therefore, in a preferred solution, based on the original drag and compliance data over time, a sliding window is added to smooth the drag and compliance data. Using a sliding window of length 2w, the value at a given time s is adjusted to the average value of the data over the time period [sw:s+w]. The result of this approach is that when drag and compliance switch, the data does not suddenly change abruptly, but rather gradually changes as a linear function over a short period. The value of w can be adjusted within a certain range. Based on subsequent calculations, the value of w can be adjusted within a certain range, typically between 7 and 10. Generally, a value of 8 yields a better result, resulting in a lower error between the calculated inspiratory effort and esophageal pressure. The final resistance-time curve and compliance-time curve are obtained through sliding window averaging.

[0069] Table 3 shows the change of resistance over time in a certain set of data before and after the resistance switching, reflecting how sliding window averaging makes the changes in resistance and compliance smoother.

[0070] Table 3. Changes in resistance before and after using the sliding window.

[0071]

[0072]

[0073] In this embodiment, using the collected ventilator waveform data, esophageal pressure data, and airway pressure data from real patients, the resistance and compliance of the patient at different times can be calculated based on the waveform and esophageal pressure data according to the above-described implementation scheme. Based on the resistance, compliance, airway pressure data, flow rate data, and the formula for calculating inspiratory effort, the inspiratory effort data can be calculated, and then compared with the patient's esophageal pressure P. esTo verify the accuracy of the calculation results, a comparison is made. The quality of the calculation results is judged by comparing the correlation and total error between the two sets of variables. Correlation and correlation coefficient are statistical indicators used to reflect the degree of correlation between variables. The closer the correlation coefficient is to 1, the stronger the correlation between the two sets of variables. The total error is the sum of the errors in the calculated inspiratory effort and esophageal pressure at each moment during a single breath.

[0074] For the same breath, Figure 3 This is a comparison chart of inspiratory effort and esophageal pressure fitted when only average resistance and compliance are calculated. Figure 4 A comparison graph of inspiratory effort and esophageal pressure fitted when piecewise calculated resistance and compliance are used.

[0075] Figure 5 A comparison graph of inspiratory effort and esophageal pressure fitted when resistance and compliance are calculated using piecewise calculations and smoothing.

[0076] The statistical results after calculating multiple sets of data are shown in Table 4:

[0077] Table 4 shows the correlation coefficients and errors between inspiratory effort and esophageal pressure.

[0078] Correlation coefficient Total error Average resistance, compliance 0.79 326.85 Segmented resistance, compliance 0.91 251.86 sliding window average 0.93 230.54

[0079] If segmented calculations are not used, the average correlation of the calculation results using a single average resistance and compliance is 0.797, and the average error is 326.85; it has a certain effect.

[0080] The average correlation calculated using segmented resistance and compliance was 0.91, with an average error of 251.86.

[0081] In addition, the results of the sliding window averaging calculation show an average correlation of 0.93 and an average error of 230.54. The final error is reduced by 30% and 8% respectively compared to the non-segmented and segmented calculations, and the correlation is increased by 0.13 and 0.02 respectively compared to the non-segmented and segmented calculations.

[0082] This invention provides a method for calculating spontaneous breathing effort curves based on ventilator airway pressure and flow rate waveforms. In the embodiments, the average resistance and compliance over several breaths were calculated, and segmented resistance and compliance calculations and sliding window averaging were performed for these breaths. For each breath, three sets of resistance and compliance data over time were obtained. Based on these sets of resistance and compliance data, inspiratory effort data under different resistance and compliance values ​​were calculated. The calculated inspiratory effort was then compared with the esophageal pressure used as a reference. This invention has universal applicability to different ventilator waveforms.

[0083] Based on the above data, it can be concluded that when using average resistance and compliance to calculate inspiratory effort, the calculated results generally do not correlate well with the esophageal pressure used as a reference value.

[0084] After performing segmented calculations using the method proposed in this invention, the accuracy of the calculation results is high, the correlation coefficient is significantly improved, and the total error is noticeably reduced. Using sliding window averaging further improves evaluation indicators such as the correlation coefficient and the total error level. The final results demonstrate that using segmented calculations and sliding window averaging based on ventilator airway pressure and flow rate to calculate resistance and compliance, and the inspiratory effort calculated accordingly, has high accuracy and a certain degree of feasibility.

[0085] Corresponding to the aforementioned embodiment of a method for obtaining spontaneous breathing effort curves under mechanical ventilation based on ventilator waveforms, the present invention also provides a method for monitoring spontaneous breathing effort in patients under mechanical ventilation, characterized in that:

[0086] The method described above, which uses ventilator waveforms to obtain spontaneous breathing effort curves under mechanical ventilation, is used to obtain spontaneous breathing effort curves of patients under mechanical ventilation in real time, thereby monitoring patients' spontaneous breathing effort.

[0087] The present invention also provides an electronic device, including one or more processors, for implementing a method for obtaining a spontaneous breathing effort curve under mechanical ventilation based on a ventilator waveform or a method for monitoring a patient's spontaneous breathing effort under mechanical ventilation as described in the above embodiments.

[0088] Embodiments of the electronic device of the present invention can be used on any device with data processing capabilities, such as a computer or other equipment or apparatus.

[0089] The device embodiment can be implemented through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor of any data processing device that houses the device loading the corresponding computer program instructions from non-volatile memory into memory for execution. From a hardware perspective, it includes a processor, memory, network interface, and non-volatile memory. In addition, the data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be elaborated further.

[0090] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0091] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the present invention according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0092] This invention also provides a computer-readable storage medium storing a program thereon, which, when executed by a processor, implements a method for obtaining a spontaneous breathing effort curve under mechanical ventilation based on a ventilator waveform or a method for monitoring a patient's spontaneous breathing effort under mechanical ventilation as described in the above embodiments.

[0093] The computer-readable storage medium can be an internal storage unit of any data processing device described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be any data processing device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., mounted on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data processing device, and can also be used to temporarily store data that has been output or will be output.

[0094] The embodiments described in this specification are merely examples of implementations of the inventive concept and are for illustrative purposes only. The scope of protection of this invention should not be considered limited to the specific forms described in these embodiments; rather, it extends to equivalent technical means conceived by those skilled in the art based on the inventive concept.

Claims

1. A method for obtaining a curve of spontaneous breathing effort under mechanical ventilation based on a ventilator waveform, characterized in that, The method comprises: acquiring ventilator waveform data and airway pressure data of a patient under mechanical ventilation; calculating resistance and compliance of the patient's respiratory system at each time point based on the acquired ventilator waveform data; calculating the inspiratory effort at each time point based on the acquired ventilator waveform data, airway pressure data, and the calculated resistance and compliance of the patient's respiratory system at each time point, and using an inspiratory effort formula constructed based on a circuit model of the respiratory system, and then obtaining the patient's spontaneous breathing effort curve under mechanical ventilation; wherein the inspiratory effort formula constructed based on the circuit model of the respiratory system is expressed as follows: where P mus is the patient's inspiratory effort, P aw is the patient's airway pressure, V is the flow rate of the airflow, the integral of the flow rate with respect to time is the tidal volume, R r and C r are the patient's respiratory system resistance and compliance, respectively; In the calculation of the resistance and compliance of the patient's respiratory system at each time point, each breath is divided into the following four stages according to the changes in airway pressure and flow rate: pressure rising stage, pressure stable stage, pressure falling stage, and end-expiratory stage; the average resistance and compliance of the patient's respiratory system at each stage of each breath are calculated as the resistance and compliance at each time point in the corresponding stage of the breath; wherein in the first three stages, the least squares method is used for fitting, and in the end-expiratory stage, the average compliance and average resistance are calculated using the following formula: where d(sumV) represents the change in tidal volume in the end-expiratory stage, and d(P) represents the change in pressure in the end-expiratory stage, P = P aw , d(V) represents the change in flow rate at the end of expiration. After calculating the resistance and compliance of the patient's respiratory system at each time point, the method further comprises smoothing the resistance and compliance of the patient's respiratory system at each time point; the smoothing process specifically comprises: In the curve constituted by the resistance and compliance of the patient's respiratory system at each time point, the value at time s is adjusted to the average value of the data in the [s-w:s+w] time period in turn; wherein w is the sliding window length.

2. The method of claim 1, wherein, The ventilator waveform data includes flow rate-time signal, pressure-time signal, and tidal volume-time signal.

3. A method of monitoring a patient's spontaneous breathing effort under mechanical ventilation, characterized in that, Specifically, The method for acquiring the patient's spontaneous breathing effort curve under mechanical ventilation in real time using the method for acquiring the spontaneous breathing effort curve under mechanical ventilation based on ventilator waveform according to any one of claims 1-2, and monitoring the patient's spontaneous breathing effort.

4. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the method for acquiring the spontaneous breathing effort curve under mechanical ventilation based on ventilator waveform according to any one of claims 1-2.

5. A storage medium containing computer executable instructions, which, when executed by a computer processor, realize the method for acquiring the spontaneous breathing effort curve under mechanical ventilation based on ventilator waveform according to any one of claims 1-2.

Images