Method and apparatus for real-time estimation of ventilator leak flow based on pressure equal point pairs

Abstract

This invention discloses a method and apparatus for real-time estimation of ventilator leakage flow based on pressure equal point pairs, relating to the field of medical device technology. The method includes: acquiring breath-hold point data and the total number g of leakage model parameters during the respiratory cycle; constructing g multivariate linear equations using the breath-hold point data and calculating g leakage model parameters; if the number of breath-hold points w is less than g, then constructing w multivariate linear equations using the data from w breath-hold points and calculating w leakage model parameters; and constructing n multivariate linear equations using point pairs of points with equal pressure during the inspiratory and expiratory phases of the respiratory cycle and calculating n leakage model parameters; and calculating the leakage flow using the g leakage model parameters. This invention can perform leakage compensation in real-time, breath-by-breath during the patient's normal breathing; it can adapt to various complex leakage situations, improving compensation accuracy; it has low computational load, a stable and reliable algorithm, and high robustness.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to a method and apparatus for real-time estimation of ventilator leakage flow based on pressure equal point pairs. Background Technology

[0002] In non-invasive ventilation (NIV) therapy, the ventilator delivers gas to the patient through interfaces such as a face mask. Gas leakage is a common and unavoidable problem due to factors such as poor mask-to-patient fit, tubing connections, or the patient's open mouth. Leakage causes a discrepancy between the flow rate measured by the ventilator (total flow rate) and the actual flow rate entering the patient's lungs (effective flow rate), thus affecting the accurate calculation of tidal volume, the assessment of patient-ventilator synchrony, and the effectiveness and safety of ventilatory support. Therefore, accurate and real-time estimation and compensation of leaked flow rate are crucial for ensuring the therapeutic effect of non-invasive ventilation.

[0003] Currently, methods for estimating leakage flow mainly fall into two categories. One category is the traditional analytical method, which mainly includes the following methods: Leak-free assumption method: Many lung function assessment methods (such as end-expiratory occlusion) require leakage-free or leak-stable conditions, which are difficult to meet in non-invasive ventilation where mask leakage is common. Sequential solution method: Some methods attempt to first estimate the leakage through specific operating conditions (such as the expiratory phase) and then use it to compensate for the inspiratory phase to calculate lung parameters. Errors in this sequential solution method can propagate and accumulate, resulting in low accuracy. Model representation method: Leakage flow is often simply represented as a linear or square root function of pressure (e.g., ...). This approach cannot accurately describe the real situation under complex leakage paths (such as the mixed flow state in mask gaps). Patient-assisted or interrupted ventilation methods: The most accurate methods often require apnea or specific ventilation patterns, interfering with the normal treatment process and making continuous, real-time monitoring impossible. Therefore, the core of traditional analytical methods is utilizing the "breath-hold point" that may exist in the respiratory cycle. The breath-hold point refers to the moment when the patient's spontaneous breathing stops, and the lungs neither inhale nor exhale, at which point the patient's true flow rate is zero. Under this ideal condition, all flow rates measured at the end of the ventilator tubing can be considered as leakage flow. By finding multiple breath-hold points at different pressure levels, a curve relating leakage flow rate to pressure can be fitted. This type of method heavily relies on the existence of breath-hold points. However, in actual clinical applications, especially for patients with spontaneous breathing, their breathing patterns are irregular, and a true breath-hold point may not be found throughout the entire respiratory cycle. This causes the method to fail directly in many cases and become unapplicable. Another type is the parameter optimization method. This type of method simplifies the respiratory system into a physical model (such as an RC circuit model) and treats leakage flow rate, respiratory resistance (R), compliance (C), etc., as unknown parameters. Then, using optimization algorithms such as least squares and RLS, a set of optimal parameters is found to maximize the fit between the model-predicted pressure-flow curve and the actual measured curve. In this way, the parameters of the leakage flow rate can be indirectly solved. Parameter optimization methods are typically complex nonlinear optimization processes, computationally intensive, and demanding in terms of computing power. This results in poor real-time performance, making it difficult to implement real-time calculation and compensation for successive breaths in resource-constrained ventilator embedded systems. It is usually only suitable for offline analysis or providing a relatively fixed compensation value. Furthermore, as a nonlinear parameter estimate, it may get trapped in local optima rather than global optima. Summary of the Invention

[0004] In order to solve the problems existing in the prior art, the present invention provides the following technical solution.

[0005] The first aspect of this invention provides a method for real-time estimation of ventilator leakage flow based on pressure equality point pairs, comprising: Acquire the breath-hold point data and the total number of leakage model parameters g during the respiratory cycle; Using the breath-holding point data, g multivariate linear equations are constructed and g leakage model parameters are calculated. Where: if the number of breath-holding points w is less than g, then w multivariate linear equations are constructed using data from w breath-holding points, and w leakage model parameters are calculated. Additionally, the pressure during the inspiratory and expiratory phases of the respiratory cycle is equal. For each pair of data points, construct n multivariate linear equations and calculate n leakage model parameters, where n = gw; The leakage flow rate is calculated using the g leakage model parameters according to the following formula: ; in, For leaked flow, For real-time monitoring of pressure, Let g be the parameters of the leakage model.

[0006] Preferably, the In each pair of points, one point is in the inspiratory phase and the other point is in the expiratory phase, and the airflow pressures corresponding to the two points are equal.

[0007] Preferably, the n leakage model parameters are calculated according to the following method: Acquire real-time pressure and flow data during the respiratory cycle and determine at least The aforementioned point pairs; Based on the above Equation (1) for constructing the respiratory dynamics equations and leakage model for a point pair: (1); in, ; ; ; For leakage model parameters; Calculate based on real-time pressure and flow data acquired during the respiratory cycle. and Solving the above equation (1) yields Leakage model parameters The optimal solution.

[0008] Preferably, the one based on the The respiratory dynamics equations and leakage model construction equations for point pairs are (1), including: When n=2, for the leakage model , combined The respiratory dynamics equations for points with equal pressure (1,2), (3,4), (5,6), and (7,8) are constructed as follows: ; in, , , ; , , ; ; ; ; ; ; ; ; ; Within a complete respiratory cycle, let's assume... and A set of isobaric time pairs corresponds to two time points in the inspiratory and expiratory phases where the pressure is equal, i.e., satisfying... Similarly, , as well as These represent three other independent pairs of isobaric inspiratory-expiratory moments within the same respiratory cycle; The difference in moisture content between two points a and b in a point pair; The difference in flow rate between two points a and b in a point pair; And so on, for the leakage model , can be combined The respiratory dynamics equations for each point pair are constructed as equation (1).

[0009] Preferably, and The following formula is used for calculation: ; ; ; ; in, and These are the real-time monitoring point-to-midpoints. and points Instantaneous flow rate at the location; and These are from the start time of the current respiratory cycle to point 1. and points The cumulative moisture volume including leakage at any given moment; and is the upper limit of integration, and represents the times of points a and b within the current respiratory cycle, respectively. The variable is the integral variable, representing the time from the start of the respiratory cycle. The duration of continuous operation.

[0010] The real-time estimation method for ventilator leakage flow based on pressure equality point pairs provided by the present invention further includes: compensating the real-time monitored flow value with the calculated leakage flow to obtain the corrected patient flow and patient tidal volume.

[0011] A second aspect of the present invention provides a device for real-time estimation of ventilator leakage flow based on pressure equality point pairs, comprising: The data acquisition module is used to acquire breath-hold point data and the total number of leakage model parameters g during the respiratory cycle; The parameter calculation module is used to construct g multivariate linear equations using the breath-holding point data and calculate g leakage model parameters. Where: if the number of breath-holding points w is less than g, then w multivariate linear equations are constructed using data from w breath-holding points, and w leakage model parameters are calculated. Additionally, the module utilizes the fact that the pressures during the inspiratory and expiratory phases of the respiratory cycle are equal. For each pair of data points, construct n multivariate linear equations and calculate n leakage model parameters, where n = gw; The leakage flow calculation module is used to calculate the leakage flow using the g leakage model parameters according to the following formula: ; in, For leaked flow, For real-time monitoring of pressure, Let g be the parameters of the leakage model.

[0012] Preferably, the parameter calculation module calculates the n leakage model parameters using the following method: Acquire real-time pressure and flow data during the respiratory cycle and determine at least The point pairs; based on the Equation (1) for constructing the respiratory dynamics equations and leakage model for a point pair: (1); in, ; ; ; For leakage model parameters; Calculate based on real-time pressure and flow data acquired during the respiratory cycle. and Solving the above equation (1) yields Leakage model parameters The optimal solution.

[0013] Preferably, the In each pair of points, one point is in the inspiratory phase and the other point is in the expiratory phase, and the airflow pressures corresponding to the two points are equal.

[0014] The real-time estimation device for ventilator leakage flow based on pressure equality point pairs provided by the present invention further includes: The compensation module uses the calculated leakage flow rate to compensate for the real-time monitored flow rate value, thereby obtaining the corrected patient flow rate and patient tidal volume.

[0015] Compared with the prior art, the present invention has the following beneficial effects: Real-time: Leakage compensation can be performed in real time and breath-by-breath during the patient's normal breathing process without interrupting normal ventilation or relying on unstable breath-holding points.

[0016] High precision and strong adaptability: It adopts a scalable polynomial model, which can adapt to various complex leakage situations and improves the compensation accuracy.

[0017] Computational efficiency: Through the innovative "pressure equal point elimination method", complex nonlinear problems are transformed into simple linear equations to be solved, with small computational load, which is fully applicable to embedded systems.

[0018] High robustness: The hybrid strategy prioritizes the use of high-quality data, and the multi-point pair solution method can effectively suppress single-point measurement noise, thus improving the stability and reliability of the algorithm. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the real-time estimation method for ventilator leakage flow based on pressure equality point pairs as described in this invention. Figure 2 This is a functional structure diagram of the ventilator leakage flow real-time estimation device based on pressure equal point pairs as described in this invention. Detailed Implementation

[0020] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0021] The method provided by this invention can be implemented in a terminal environment that may include one or more of the following components: a processor, a memory, and a display screen. The memory stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.

[0022] A processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the terminal, and performs various functions and processes data by running or executing instructions, programs, code sets or instruction sets stored in memory, and by calling data stored in memory.

[0023] Memory can include random access memory (RAM) or read-only memory (ROM). Memory can be used to store instructions, programs, code, code sets, or instructions.

[0024] The display screen is used to show the user interface of each application.

[0025] In addition, those skilled in the art will understand that the structure of the terminal described above does not constitute a limitation on the terminal. The terminal may include more or fewer components, or combine certain components, or have different component arrangements. For example, the terminal may also include radio frequency circuits, input units, sensors, audio circuits, power supplies, and other components, which will not be described in detail here.

[0026] This invention addresses problems in related technologies by providing a novel, real-time-operable method for estimating leakage flow. Specifically, it establishes a system of equations using points where the pressure is equal during the inspiratory and expiratory phases of the respiratory cycle. The parameters of the leakage model and lung mechanics parameters are simultaneously solved using elimination methods. Furthermore, the function of leakage flow with pipeline pressure is extended to a more universal polynomial expression. This method integrates physical modeling and data-driven approaches, enabling efficient and accurate solution of leakage parameters even without breath-holding points.

[0027] Example 1 like Figure 1 As shown, this embodiment of the invention provides a method for real-time estimation of ventilator leakage flow based on pressure equality point pairs, including the following steps: S101, Obtain the total number of breath-hold point data and leakage model parameters g within a respiratory cycle. In practical applications, all breath-hold points can be determined first within a complete respiratory cycle. If the total number of breath-hold points within a complete respiratory cycle is greater than the number of leakage model parameters, only the breath-hold point data within the respiratory cycle needs to be determined, without needing to obtain data on pressure equalization point pairs. If the total number of breath-hold points within a complete respiratory cycle is less than the number of leakage model parameters, then the number of pressure equalization point pairs needs to be determined based on the difference between the two. For example, if the difference between the number of breath-hold points and the number of leakage model parameters is n, then at least n needs to be determined. Data for pairs of pressure equalization points. If there is no breath-holding point within a complete respiratory cycle, the number of pairs of pressure equalization points is determined based on the number of leakage model parameters. For example, if the number of leakage model parameters is g, then at least... Data for points with equal pressure in a group.

[0028] S102, using the breath-holding point data, construct g multivariate linear equations and calculate g leakage model parameters, wherein: if the number of breath-holding points w is less than g, then use the data from w breath-holding points to construct w multivariate linear equations and calculate w leakage model parameters, and utilize the equal pressure during the inspiratory and expiratory phases of the respiratory cycle... For each pair of data points, construct n multivariate linear equations and calculate n leakage model parameters, where n = gw. If the leakage model has g parameters, then we can construct g multivariate linear equations to form a system of equations, and then solve for the g leakage model parameters using methods such as elimination. As an example, we use the following method to construct w multivariate linear equations using data from w breath-holding points and calculate w leakage model parameters: Step 1: Data extraction based on physical characteristics of the breath-hold point. According to the principles of respiratory dynamics, when a patient is at the "breath-hold point," their actual respiratory flow rate is zero (i.e., there is neither inhalation nor exhalation), and the actual patient flow rate is... According to the total flow formula including leakage. It can be seen that the total ventilator flow rate measured at any breath-hold point is... Completely equivalent to the leakage flow at that moment In the detected Each breath-holding point (set as) The system simultaneously extracts and records the corresponding airway pressure values. and the measured total flow rate .

[0029] Step 2: Substitute the values ​​into the leakage model to construct a multivariate linear equation. The extracted values ​​from the above... Substitute real data into the preset data In a polynomial model of leakage flow with unknown parameters (assuming the model form is...), ,in Given an exponential constant, (These are the parameters to be determined). Therefore, we can directly derive... An independent multivariate linear equation: ; Step 3: Parameter elimination and substitution (calculated) The expression with one parameter). Due to the number of breath-holding points. Less than the total number of unknown parameters (Right now It is impossible to obtain a unique numerical solution for all parameters. In order to "calculate..." "One leakage model parameter", employing local elimination (or parameter substitution) in algebra: from the above constructed From the equations, select One parameter to be determined (e.g.) ), which is represented as the remainder Parameters (i.e.) ,in A linear combination of ). For example: assume the leakage model is... Parameters ( ), and only found There are several breath-holding points. The equation is: .

[0030] By rearranging and transforming terms, we can calculate the value of the product. Parameters (such as) The equivalent expression for ) is: In this way, using the gold standard breath-holding point data, the elimination was successfully achieved. One degree of freedom.

[0031] Step 4: Combine the method with the isobaric point pair method for dimensionality reduction. Then, use the solution obtained from the breath-holding points... The parameter expressions are directly substituted into the complex equations subsequently constructed using the "pressure equal point pair method". In this substituted isobaric point pair related equation system, the number of unknown leakage parameters will increase from the initial... One successful reduction to One. Then, only the data from the pressure equalization points within the respiratory cycle need to be used to construct a... Solving a series of independent linear equations in multiple variables will yield the remaining solutions. One parameter. Finally, the obtained... Substituting each parameter back into the expression in step three of this step will yield all the results. The specific value of each leakage parameter.

[0032] S103, calculate the leakage flow rate using the g leakage model parameters according to the following formula: ; in, For leaked flow, For real-time monitoring of pressure, Let g be the parameters of the leakage model.

[0033] Specifically, the g leakage model parameters obtained in step S102 can be substituted into the leakage model: In this process, the leakage flow rate can be calculated based on the real-time monitored pressure data. .

[0034] In one embodiment of the present invention, In each pair of points, one point is in the inspiratory phase and the other point is in the expiratory phase, and the airflow pressures corresponding to the two points are equal.

[0035] In one embodiment of the present invention, the following method can be used to construct g multivariate linear equations using the acquired data and calculate g leakage model parameters: Obtain the number w of breath-holding points in the respiratory cycle and the total number g of leakage model parameters; Determine whether w is greater than g. If so, use the data of w breath-holding points to construct g linear equations with multiple variables and calculate the parameters of g leakage models; otherwise, use the data of w breath-holding points to construct w linear equations with multiple variables and calculate the parameters of w leakage models; and use the data of pairs of points with equal pressure to construct n linear equations with multiple variables and calculate the parameters of n leakage models, where g - w = n.

[0036] The breath-holding points provide the most direct and accurate leakage information. Therefore, in the embodiments of the present invention, it is preferred to detect whether there are breath-holding points in the breathing cycle. Assume that the leakage model has g unknown parameters and w breath-holding points have been found.

[0037] If w >= g, it means that the information is sufficient, and all g parameters can be accurately solved directly using these w points through traditional methods (such as linear regression).

[0038] If w < g, it means that the information from only the breath-holding points is insufficient. At this time, in the embodiments of the present invention, the data of w breath-holding points are used as w golden standard equations, and then the "equal-pressure point pair elimination method" is used to find and construct the remaining g - w independent equations.

[0039] In one embodiment of the present invention, the n leakage model parameters can be calculated as follows: Obtain the pressure and flow rate data monitored in real time during the breathing cycle and determine at least pairs of points; Based on the respiratory dynamics equations and leakage models of the pairs of points, construct Equation (1): (1); where ; ; ; are the leakage model parameters; Calculate and according to the pressure and flow rate data monitored in real time during the breathing cycle obtained; solve the above Equation (1) to obtain the optimal solution of the leakage model parameter .

[0040] In one embodiment of the present invention, the following method can be used to construct Equation (1) based on the respiratory dynamics equations and leakage models of groups of pairs of points with equal pressure: When n = 2, for the leakage model , combined with the respiratory dynamics equations of pairs of points with equal pressure (1, 2), (3, 4), (5, 6), (7, 8), construct the following formula: ; in, , , ; , , ; ; ; ; ; ; ; ; ; Within a complete respiratory cycle, let's assume... and A set of isobaric time pairs corresponds to two time points in the inspiratory and expiratory phases where the pressure is equal, i.e., satisfying... Similarly, , as well as These represent three other independent pairs of isobaric inspiratory-expiratory moments within the same respiratory cycle; The difference in moisture content between two points a and b in a point pair; The difference in flow rate between two points a and b in a point pair; And so on, for the leakage model , can be combined The respiratory dynamics equations for each point pair are constructed as equation (1).

[0041] In one embodiment of the present invention, the airway pressure satisfies the following formula: (5) Where R represents airway resistance and C represents lung compliance. To represent actual patient flow, To reflect the actual tidal volume of patients, For pressure.

[0042] Step 1, for the point pair (1, 2) with equal pressure, the following condition is satisfied: According to equation (5), we can obtain: (6) (7) Combining equations (6) and (7), we can obtain: (8) Assume that lung compliance and resistance C and R remain constant during a respiratory cycle.

[0043] because ,in, For leakage flow; then (9) because The leakage flow is a function of pressure, therefore the leakage flow... Equal, that is: Therefore, equation (9) can be written as: (10) Then, according to equation (10), equation (8) can be written as: (11) Furthermore, since the amount of moisture including leakage equals the sum of the actual user moisture amount and the leakage moisture amount, that is... For the pair of points (1, 2), then: ; ; Substituting into equation (11), we get: (12) in, express ,, ; Step 2, for the point pair (3, 4) with equal pressure, the following condition is met: ; Using the method in step one, we can obtain: (13) Combining (12) and (13), we get: (14) in: This represents the difference in moisture volume, including leakage, between points of equal pressure a and b. , representing the difference in leakage moisture between points a and b at which pressures are equal; , representing the flow difference, including leakage, between points of equal pressure a and b.

[0044] Step 3, Leakage moisture difference Leakage flow The integral. For points of equal pressure, 1 and 2: (15) Assumption (16) (In practice, it is not limited to the two parameters k1 and k2; any polynomial is acceptable, for example:) ; in, ...represents the leakage parameters to be identified. This polynomial can flexibly cover leakage characteristics under linear, turbulent, and mixed flow conditions.

[0045] Here we will explain the case where equation (16) contains two parameters.

[0046] Equation (15) can be simplified as: (17) in, , ; Similarly, for points 3 and 4 where the pressure is equal, we have: (18) Substituting equations (17) and (18) into equation (14), we get: (19) make Then equation (19) can be written as: (2) Among them, A, B, D, and E can all be calculated from the pressure and flow rate data including leakage obtained within one breathing cycle, and are therefore known quantities. Therefore, this is about... linear equation of two variables.

[0047] Step four: To solve the system of two linear equations, we need two more independent pairs of points with equal pressure (5, 6) and (7, 8) that satisfy the following conditions: ; Using the same method as steps one through three, we obtain: (3) In one embodiment of the present invention, if a more complex polynomial is used, it is only necessary to find a few more independent pairs of points to construct the following system of equations: ; Written in matrix form (1); in, ; ; Because of its small dimension, it can be directly calculated by matrix inversion. : .

[0048] In one embodiment of the present invention, the following method can be used to calculate based on the pressure and flow data including leakage acquired during the real-time monitoring of the respiratory cycle. and : Calculated based on real-time pressure monitoring data and flow rate data including leakage during the respiratory cycle. , , , Where i and j are the indexes of the midpoints of the points with equal pressure; Based on the calculation , , , ,calculate and .

[0049] As an example, in equations (2) and (3), calculations can be performed based on the pressure and flow rate data including leakage obtained from real-time monitoring during the respiratory cycle. , , , , , , , , , , , , , , , .

[0050] Equations (2) and (3) are two equations concerning the unknown. The equations are both linear equations because the unknowns are... It appears in linear form. Therefore, equations (2) and (3) can be rewritten as equation (4) in standard form: ; Then, for equation (4) , , , , and It can be calculated , , , , , , , , , , , , , , , Perform the calculation.

[0051] In this way, it can be calculated and .

[0052] In one embodiment of the present invention, and The following formula can be used for calculation: ; ; ; ; in, and These are the point-to-midpoints monitored in real time. and points Instantaneous flow rate at the location; and These are from the start time of the current respiratory cycle to point 1. and points The cumulative moisture volume including leakage at any given moment; and is the upper limit of integration, and represents the times of points a and b within the current respiratory cycle, respectively. The variable is the integral variable, representing the time from the start of the respiratory cycle. The duration of continuous operation.

[0053] An embodiment of the present invention provides a real-time estimation method for ventilator leakage flow based on pressure equality point pairs, which may further include the steps of: compensating the real-time monitored flow value with the calculated leakage flow to obtain the corrected patient flow and patient tidal volume. Specifically, the corrected patient flow is calculated based on the difference between the real-time monitored flow and the leakage flow, and the corrected patient tidal volume is calculated based on the integral of the corrected patient flow. Specific Implementation This specific case provides a method for solving a leakage model that includes two unknown parameters, k1 and k2. It is assumed that there are no breath-holding points.

[0055] 1. Problem Setting The goal is to solve the leakage model. Two unknown parameters and Since there are two unknowns, we need to construct two independent linear equations.

[0056] Step 1: Construct the first linear equation 2.1 Finding point pairs: Within one respiratory cycle, find two sets of "point pairs with equal pressure". The first set is point 1 and point 2, satisfying p1 = p2; the second set is point 3 and point 4, satisfying p3 = p4.

[0057] 2.2 Establishing Relationships: Based on the respiratory dynamics equations and the pressure equality characteristic, the following key relationships can be derived: ; in, It includes the moisture difference caused by leakage. The problem is poor moisture leakage. This includes the flow difference that includes leakage. These quantities can all be calculated or represented using measurement data.

[0058] 2.3 Linearization: Transforming the leakage model Substituting, the difference in leakage moisture volume This can be represented as a linear combination of k1 and k2. That is... ,in and It is a known constant obtained by integrating the pressure data.

[0059] 2.4 Simplifying the Equation: After simplifying the above relationships, we can obtain a linear equation in two variables k1 and k2, in the form of: ; Where, coefficient , and constant term All of these can be calculated from the measured pressure and flow data.

[0060] Step 2: Construct the second linear equation 3.1 Find more point pairs: To obtain a second independent equation, repeat the process in step one. In the same respiratory cycle or a subsequent cycle, find two more pairs of points with equal pressure: points 5 and 6 (p5 = p6), and points 7 and 8 (p7 = p8).

[0061] 3.2 Establishing a new equation: Using the same method as in step one, we can obtain a second linear equation in two variables k1 and k2: ; Step 3: Solve for parameters By following steps one and two, we obtained a system of two linear equations in two variables: ; This system of equations has a unique solution (provided that the chosen pairs of points form independent equations, which requires selecting points that are far apart). The values ​​of k1 and k2 can be solved very quickly using standard linear algebraic methods (such as Cramer's rule or Gaussian elimination). Once the parameters are determined, they can be used in each subsequent breath, based on the real-time measured pressure p, to solve for the equations. ; The leakage flow rate is calculated accurately in real time, thus obtaining accurate patient ventilation data.

[0062] This invention provides an innovative, efficient, and robust algorithm for estimating ventilator leakage flow, the core value of which is reflected in the following aspects: Real-time: Leakage compensation can be performed in real time and breath-by-breath during the patient's normal breathing process without interrupting normal ventilation or relying on unstable breath-holding points.

[0063] High precision and strong adaptability: It adopts a scalable polynomial model, which can adapt to various complex leakage situations and improves the compensation accuracy.

[0064] Computational efficiency: Through the innovative "pressure equal point elimination method", complex nonlinear problems are transformed into simple linear equations to be solved, with small computational load, which is fully applicable to embedded systems.

[0065] High robustness: The hybrid strategy prioritizes the use of high-quality data, and the multi-point pair solution method can effectively suppress single-point measurement noise, thus improving the stability and reliability of the algorithm.

[0066] It is evident that the technical solution of this invention breaks through the bottleneck of existing methods, provides key technical support for achieving accurate and safe non-invasive ventilation, and has high clinical application value and commercial prospects.

[0067] Example 2 like Figure 2 As shown, another aspect of the present invention also includes a functional module architecture that is completely consistent with the aforementioned method flow. That is, the embodiments of the present invention also provide a real-time estimation device for ventilator leakage flow based on pressure equality point pairs, including: Data acquisition module 201 is used to acquire breath-hold point data and the total number g of leakage model parameters during the respiratory cycle; The parameter calculation module 202 is used to construct g multivariate linear equations using the breath-holding point data and calculate g leakage model parameters, wherein: if the number of breath-holding points w is less than g, then w multivariate linear equations are constructed using the data from w breath-holding points, and w leakage model parameters are calculated, and the parameters are calculated using the equal pressure during the inspiratory and expiratory phases of the respiratory cycle. For each pair of data points, construct n multivariate linear equations and calculate n leakage model parameters, where n = gw; Leakage flow calculation module 203 is used to calculate leakage flow using the g leakage model parameters according to the following formula: ; in, For leaked flow, For real-time monitoring of pressure, Let g be the parameters of the leakage model.

[0068] Furthermore, the parameter calculation module calculates the n leakage model parameters using the following method: Acquire real-time pressure and flow data during the respiratory cycle and determine at least The point pairs; based on the Equation (1) for constructing the respiratory dynamics equations and leakage model for a point pair: (1); in, ; ; ; For leakage model parameters; Calculate based on real-time pressure and flow data acquired during the respiratory cycle. and Solving equation (1) yields the leakage model parameters. The optimal solution.

[0069] Furthermore, the aforementioned In each pair of points, one point is in the inspiratory phase and the other point is in the expiratory phase, and the airflow pressures corresponding to the two points are equal.

[0070] Furthermore, the real-time estimation device for ventilator leakage flow based on pressure equality point pairs provided in this embodiment of the invention further includes: The compensation module uses the calculated leakage flow rate to compensate for the real-time monitored flow rate value, thereby obtaining the corrected patient flow rate and patient tidal volume.

[0071] This device can be implemented using the real-time estimation method for ventilator leakage flow based on pressure equal point pairs provided in Embodiment 1 above. The specific implementation method can be found in the description in Embodiment 1, and will not be repeated here.

[0072] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention. Clearly, those skilled in the art can make various alterations and modifications to the invention without departing from its spirit and scope. Thus, if these modifications and modifications of the invention fall within the scope of the claims and their equivalents, the invention is also intended to include these modifications and modifications.

Claims

1. A method for real-time estimation of ventilator leakage flow based on pressure equality point pairs, characterized in that, include: Acquire the breath-hold point data and the total number of leakage model parameters g during the respiratory cycle; Using the breath-holding point data, g multivariate linear equations are constructed and g leakage model parameters are calculated. Where: if the number of breath-holding points w is less than g, then w multivariate linear equations are constructed using data from w breath-holding points, and w leakage model parameters are calculated. Additionally, the pressure during the inspiratory and expiratory phases of the respiratory cycle is equal. For each pair of data points, construct n multivariate linear equations and calculate n leakage model parameters, where n = gw; The leakage flow rate is calculated using the g leakage model parameters according to the following formula: ； in, For leaked flow, For real-time monitoring of pressure, Let g be the parameters of the leakage model.

2. The real-time estimation method for ventilator leakage flow based on pressure equality point pairs as described in claim 1, characterized in that, The In each pair of points, one point is in the inspiratory phase and the other point is in the expiratory phase, and the airflow pressures corresponding to the two points are equal.

3. The real-time estimation method for ventilator leakage flow based on pressure equality point pairs as described in claim 2, characterized in that, The n leakage model parameters are calculated using the following method: Acquire real-time pressure and flow data during the respiratory cycle and determine at least The aforementioned point pairs; Based on the above Equation (1) for constructing the respiratory dynamics equations and leakage model for a point pair: （1）； in, ; ; ; For leakage model parameters; Calculate based on real-time pressure and flow data acquired during the respiratory cycle. and Solving the above equation (1) yields Leakage model parameters The optimal solution.

4. The real-time estimation method for ventilator leakage flow based on pressure equality point pairs as described in claim 3, characterized in that, The basis of The respiratory dynamics equations and leakage model construction equations for point pairs are (1), including: When n=2, for the leakage model , combined The respiratory dynamics equations for points with equal pressure (1,2), (3,4), (5,6), and (7,8) are constructed as follows: ； in, , , ; , , ; ; ; ; ; ; ; ; ; Within a complete respiratory cycle, let's assume... and A set of isobaric time pairs corresponds to two time points in the inspiratory and expiratory phases where the pressure is equal, i.e., satisfying... Similarly, , as well as These represent three other independent pairs of isobaric inspiratory-expiratory times within the same respiratory cycle; The difference in moisture content between two points a and b in a point pair; The difference in flow rate between two points a and b in a point pair; And so on, for leakage models , can be combined The respiratory dynamics equations for each point pair are constructed as equation (1).

5. The real-time estimation method for ventilator leakage flow based on pressure equality point pairs as described in claim 4, characterized in that, and The following formula is used for calculation: ； ； ； ； in, and These are the point-to-midpoints monitored in real time. and points Instantaneous flow rate at the location; and These are from the start time of the current respiratory cycle to point 1. and points The cumulative moisture volume including leakage at any given moment; and is the upper limit of integration, and represents the times of points a and b within the current respiratory cycle, respectively. The variable is the integral variable, representing the time from the start of the respiratory cycle. The duration of continuous operation.

6. The method for real-time estimation of ventilator leakage flow based on pressure equality point pairs as described in claim 1, characterized in that, It also includes: using the calculated leakage flow rate to compensate for the real-time monitored flow rate value, and obtaining the corrected patient flow rate and patient tidal volume.

7. A real-time estimation device for ventilator leakage flow based on pressure equality point pairs, characterized in that, include: The data acquisition module is used to acquire breath-hold point data and the total number of leakage model parameters g during the respiratory cycle; The parameter calculation module is used to construct g multivariate linear equations using the breath-holding point data and calculate g leakage model parameters. Where: if the number of breath-holding points w is less than g, then w multivariate linear equations are constructed using data from w breath-holding points, and w leakage model parameters are calculated. Additionally, the module utilizes the fact that the pressures during the inspiratory and expiratory phases of the respiratory cycle are equal. For each pair of data points, construct n multivariate linear equations and calculate n leakage model parameters, where n = gw; The leakage flow calculation module is used to calculate the leakage flow using the g leakage model parameters according to the following formula: ； in, For leaked flow, For real-time monitoring of pressure, Let g be the parameters of the leakage model.

8. The real-time estimation device for ventilator leakage flow based on pressure equality point pairs as described in claim 7, characterized in that, The parameter calculation module calculates the n leakage model parameters using the following method: Acquire real-time pressure and flow data during the respiratory cycle and determine at least The point pairs; based on the Equation (1) for constructing the respiratory dynamics equations and leakage model for a point pair: （1）； in, ; ; ; For leakage model parameters; Calculate based on real-time pressure and flow data acquired during the respiratory cycle. and Solving equation (1) yields the leakage model parameters. The optimal solution.

9. The real-time estimation device for ventilator leakage flow based on pressure equality point pairs as described in claim 7, characterized in that, The In each pair of points, one point is in the inspiratory phase and the other point is in the expiratory phase, and the airflow pressures corresponding to the two points are equal.

10. The real-time estimation device for ventilator leakage flow based on pressure equality point pairs as described in claim 7, characterized in that, Also includes: The compensation module uses the calculated leakage flow rate to compensate for the real-time monitored flow rate value, thereby obtaining the corrected patient flow rate and patient tidal volume.

Images