Sputum obstruction detection method, system, terminal and medium based on lung binary tree model

Abstract

The present application discloses a sputum obstruction detection method, system, terminal and medium based on a lung binary tree model. The sputum obstruction detection method based on a lung binary tree model includes: obtaining a normal lung impedance curve of a subject under normal lung conditions; establishing a lung binary tree model, calibrating the parameters of the lung binary tree model according to the normal lung impedance curve, and obtaining normal values ​​of airway geometric parameters; obtaining the current lung impedance curve of the subject during a forced oscillation test when detecting sputum accumulation, and determining the location and degree of sputum obstruction of the subject based on the current lung impedance curve, the normal lung impedance curve and the normal values ​​of airway geometric parameters. The present application simplifies the lung binary tree model, quantitatively analyzes the accumulation of sputum in the lungs, and can accurately identify the location and degree of sputum obstruction. The forced oscillation measurement is used to improve the patient's comfort, thereby reducing the physical and psychological burden of sputum suction on the patient.

Description

Technical Field

[0001] The present application relates to the technical field of physiological signal processing and modeling analysis, and in particular to a sputum obstruction detection method, system, terminal and medium based on a lung binary tree model. Background Art

[0002] Mechanical ventilation is one of the key technologies in the clinical treatment of critically ill patients. However, mechanical ventilation often irritates the airway mucosa, leading to increased sputum in the respiratory tract. During mechanical ventilation, patients are usually unable to expel sputum through natural physiological reactions, resulting in sputum deposition in the patient's lungs. Sputum deposition can lead to many adverse reactions and induce complications, and frequent suctioning can place a physical and psychological burden on patients. Therefore, identifying sputum accumulation can provide medical staff with appropriate suctioning opportunities to reduce the physical and psychological burden of suctioning on patients.

[0003] Currently, clinical diagnosis of sputum accumulation relies primarily on auscultation, which takes a significant amount of time. Pulmonary function testing is the gold standard for diagnosing pulmonary obstruction, but this examination requires the subject to cooperate closely and perform rigorous and vigorous breathing maneuvers, which is difficult for critically ill patients to complete successfully.

[0004] Therefore, the existing technology still needs to be improved and developed. Summary of the Invention

[0005] The main purpose of this application is to provide a sputum obstruction detection method, system, terminal and medium based on a lung binary tree model, aiming to solve the problem in the existing technology that the clinical judgment of sputum accumulation relies on the doctor's stethoscope and the cooperation of the subjects, and some subjects are unable to cooperate, resulting in the inability to accurately identify the location and degree of sputum obstruction.

[0006] A first aspect of an embodiment of the present application provides a sputum obstruction detection method based on a lung binary tree model, the sputum obstruction detection method based on a lung binary tree model comprising the following steps: obtaining a normal lung impedance curve of a subject under normal lung conditions; establishing a lung binary tree model, and calibrating parameters of the lung binary tree model according to the normal lung impedance curve to obtain normal values ​​of airway geometric parameters; obtaining a current lung impedance curve of the subject during a forced oscillation test during sputum accumulation detection, and determining the location and degree of sputum obstruction in the subject based on the current lung impedance curve, the normal lung impedance curve, and the normal values ​​of the airway geometric parameters.

[0007] Optionally, in one embodiment of the present application, obtaining the normal lung impedance curve of the subject under normal lung conditions specifically includes: obtaining the pressure and flow signals at the mouth of the subject performing a forced oscillation test under normal lung conditions; preprocessing the pressure and flow signals to obtain preprocessed pressure and preprocessed flow signals; and determining the normal lung impedance curve based on the preprocessed pressure and the preprocessed flow signals.

[0008] Optionally, in one embodiment of the present application, determining the normal lung impedance curve based on the preprocessed pressure and the preprocessed flow signal specifically includes: for each frequency point, calculating the pressure autopower spectrum corresponding to the preprocessed pressure under each sliding window, the flow autopower spectrum and the cross-power spectrum corresponding to the preprocessed flow signal; calculating the first average value corresponding to the pressure autopower spectrum and the second average value corresponding to the cross-power spectrum under all sliding windows; calculating the impedance value at each frequency point based on the first average value and the second average value; and obtaining the normal lung impedance curve based on multiple impedance values ​​at different frequency points.

[0009] Optionally, in one embodiment of the present application, the parameters of the lung binary tree model are calibrated according to the normal lung impedance curve to obtain normal values ​​of airway geometric parameters, specifically including: determining the parameters to be optimized in the lung binary tree model; taking the root mean square error of the simulated impedance curve fitted by the lung binary tree model and the normal lung impedance curve as the fitness function; and optimizing the parameters to be optimized based on the fitness function to obtain normal values ​​of airway geometric parameters.

[0010] Optionally, in one embodiment of the present application, the parameters to be optimized are optimized based on the fitness function to obtain normal values ​​of airway geometric parameters, specifically including: initializing the position and velocity of each particle; wherein the position of the particle represents a combination of the parameters to be optimized, and the velocity of the particle represents the direction and magnitude of the update of the parameters to be optimized; in each iteration, the fitness value of each particle is calculated according to the fitness function, and the individual historical optimal position and the global optimal position are updated according to the fitness value to obtain the current individual historical optimal position and the current global optimal position; according to the current individual historical optimal position and the current global optimal position, the position and velocity of each particle are updated to obtain the current position and current velocity of each particle; when the current number of iterations reaches the maximum number of iterations, or the iteration is stopped when the fitness value corresponding to the current position is less than a preset threshold, the current global optimal position corresponding to the current position is used as the normal value of the airway geometric parameters.

[0011] Optionally, in one embodiment of the present application, the location and degree of sputum obstruction are obtained based on the current pulmonary impedance curve, the normal pulmonary impedance curve and the normal values ​​of the airway geometric parameters, specifically including: calculating the root mean square error value of the current pulmonary impedance curve and the normal pulmonary impedance curve at all frequencies; setting a sputum obstruction threshold, if the root mean square error value is greater than the sputum obstruction threshold, determining the current airway geometric parameter fitting value based on the current pulmonary impedance curve; and determining the location and degree of sputum obstruction based on the current airway geometric parameter fitting value and the normal values ​​of the airway geometric parameters.

[0012] Optionally, in one embodiment of the present application, the calculating of the root mean square error value between the current pulmonary impedance curve and the normal pulmonary impedance curve at all frequencies further includes: if the root mean square error value is less than the sputum blockage threshold, determining that the subject does not have sputum blockage.

[0013] A second aspect of the embodiments of the present application further provides a sputum obstruction detection system based on a lung binary tree model, wherein the sputum obstruction detection system based on a lung binary tree model includes:

[0014] A lung impedance calculation module, used to obtain a normal lung impedance curve of a subject under normal lung conditions;

[0015] A lung model parameter calibration module is used to establish a lung binary tree model, calibrate the parameters of the lung binary tree model according to the normal lung impedance curve, and obtain normal values ​​of airway geometric parameters;

[0016] The sputum obstruction identification module is used to obtain the current lung impedance curve of the subject during the forced oscillation test during sputum accumulation detection, and determine the location and degree of sputum obstruction of the subject based on the current lung impedance curve, the normal lung impedance curve and the normal values ​​of the airway geometric parameters.

[0017] A third aspect of an embodiment of the present application further provides a terminal, wherein the terminal includes: a memory, a processor, and a sputum obstruction detection program based on a pulmonary binary tree model stored in the memory and executable on the processor, wherein the sputum obstruction detection program based on a pulmonary binary tree model, when executed by the processor, implements the steps of the sputum obstruction detection method based on a pulmonary binary tree model as described above.

[0018] The fourth aspect of an embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a sputum obstruction detection program based on a pulmonary binary tree model, and when the sputum obstruction detection program based on a pulmonary binary tree model is executed by a processor, the steps of the sputum obstruction detection method based on a pulmonary binary tree model as described above are implemented.

[0019] Beneficial effects: This application provides a sputum obstruction detection method, system, terminal and medium based on the lung binary tree model. This application establishes a lung binary tree model by combining forced oscillation technology and lung physiological structure respiratory dynamics, quantitatively analyzes the accumulation of sputum in the lungs, and can accurately identify the location and degree of sputum obstruction, providing medical staff with a reference for whether to perform suction operations on patients. The use of forced oscillation measurement improves the patient's comfort, thereby reducing the physical and psychological burden of suction on patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is a flow chart of a preferred embodiment of the sputum obstruction detection method based on the lung binary tree model of the present application;

[0022] Figure 2 This is a flow chart of preprocessing of pressure and flow signals in a preferred embodiment of the sputum obstruction detection method based on the lung binary tree model of the present application;

[0023] Figure 3 This is the impedance curve calculation process in the preferred embodiment of the sputum obstruction detection method based on the lung binary tree model of the present application;

[0024] Figure 4 This is an analog diagram of a single airway circuit in a preferred embodiment of the sputum obstruction detection method based on the lung binary tree model of the present application;

[0025] Figure 5 This is a simplified binary tree circuit analogy diagram of the lung in a preferred embodiment of the sputum obstruction detection method based on the lung binary tree model of the present application;

[0026] Figure 6 This is the lung sputum obstruction identification process in the preferred embodiment of the sputum obstruction detection method based on the lung binary tree model of the present application;

[0027] Figure 7 This is a structural diagram of a preferred embodiment of the sputum obstruction detection system based on the lung binary tree model of the present application;

[0028] Figure 8 This is a structural diagram of a preferred embodiment of the terminal of this application.

[0029] Description of reference numerals:

[0030] 100. Lung impedance calculation module; 200. Lung model parameter calibration module; 300. Sputum obstruction identification module. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and effects of this application clearer and more specific, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. The described embodiments are only possible technical implementations of this application and are not all possible implementations. Based on the embodiments in this application, those skilled in the art can fully combine the embodiments of this application to obtain other embodiments without creative work, and these embodiments are also within the scope of protection of this application.

[0032] In the related art, a method predicts the patient's lung function based on CT image data. First, CT image data is obtained, airway data is extracted, and an airway model is generated using three-dimensional reconstruction technology; then, the statistical data of lung function is input into a normal model and a stenosis model for simulation to generate simulation data; finally, the simulation data is input into a lung function prediction model to output a predicted value. The disadvantages of this method are: it depends on CT image data, the cost is high, and the processing process is complex and the amount of calculation is large. However, the present application does not rely on CT image data to simulate the lungs. It measures the lung impedance curve through forced oscillation, and uses a simplified lung binary tree model and a particle swarm optimization algorithm to fit the changes in the geometric parameters of each airway of the patient, thereby identifying the location and degree of pulmonary sputum obstruction. Therefore, the present application has a lower cost of use than the above method, and the simplified binary tree model has less calculation.

[0033] In the related art, another method is to implant a sleep respiratory monitoring and obstruction location system into the nasal cavity, using a carrier catheter integrated with a pressure sensor array to monitor the contact pressure signal in the respiratory tract, and analyze the pressure signal through a processing module to obtain the pressure change in the respiratory tract to monitor the airway obstruction during sleep. The disadvantage of this method is that it is an invasive measurement method, which may cause discomfort to the patient, and is mainly used for monitoring airway obstruction in the sleeping state, and has a limited scope of application. The present application uses a non-invasive measurement method to measure the impedance of the lungs. Although it cannot directly obtain the obstruction situation in the respiratory tract, it can indirectly reflect the obstruction situation by fitting the airway geometric parameters through lung modeling and parameter optimization methods, which has a higher comfort level in practical applications. In addition, the present application is mainly aimed at locating sputum obstruction in the lungs, while the above-mentioned scheme is used for monitoring airway obstruction in the sleeping state.

[0034] The Forced Oscillation Technique (FOT) is a noninvasive method for measuring lung respiratory mechanics that does not rely on forced exhalation. It works by applying pressure waves of a certain frequency to the respiratory system during quiet breathing and measuring the pressure and flow signals at the patient's mouth to calculate respiratory system impedance. By comparing key parameters of respiratory system impedance with empirical values, such as resistance at 5 Hz (R5), resistance at 20 Hz (R20), resonant frequency (Fres), resistance at 5 Hz (X5), and resistance at 20 Hz (X20), a qualitative assessment of lung obstruction can be achieved. However, this method cannot quantitatively determine the specific location or degree of obstruction. To address this issue, this application combines a simplified binary tree circuit model of the lungs with a particle swarm optimization algorithm.

[0035] This application has the following innovations: First, a simplified airway binary tree model: Due to the complex structure of the lungs, accurate lung modeling and simulation requires a large amount of calculation. In practical applications, the computational complexity can be reduced by reducing the computational accuracy by simplifying the model. Combined with transmission line theory, the lung model is analogized to a circuit model. At the same time, it is further assumed that the lungs are a symmetrical and uniform binary tree structure and that each level of airway satisfies a specific proportional relationship. This further simplifies the model, reduces the number of model parameters, and makes it more practical. Second, a lung airway parameter fitting algorithm is used: In order to make the impedance curve of the simulation model as consistent as possible with the actual measured impedance value of the forced oscillation, the particle swarm optimization algorithm in the random optimization algorithm is used to optimize the airway parameters in the model. This method has the advantages of a small number of parameters and strong global search capabilities. The optimized airway radius parameters are compared with the airway radius parameters under normal conditions, thereby reflecting the specific location and degree of obstruction.

[0036] The following describes the sputum obstruction detection method, system, terminal and medium based on the lung binary tree model of the embodiment of the present application with reference to the accompanying drawings. In view of the problem that the judgment of sputum accumulation in the clinical practice of the above-mentioned related art relies on the doctor's auscultation and the cooperation of the subject, and some subjects are unable to cooperate, resulting in the inability to accurately identify the location and degree of sputum obstruction, the present application provides a sputum obstruction detection method based on the lung binary tree model. In this method, a lung binary tree model is established by combining forced oscillation technology and lung physiological structure respiratory dynamics, and the accumulation of sputum in the lungs is quantitatively analyzed. It can accurately identify the location and degree of sputum obstruction, and provide medical staff with a reference for whether to perform sputum suction on the patient. The use of forced oscillation measurement improves the patient's comfort to reduce the physical and psychological burden of sputum suction on the patient. The simplified model and optimized algorithm reduce the computational complexity, improve practicality, and do not rely on CT image data, reducing the cost of use. Thus, the technical problem that the judgment of sputum accumulation in the clinical practice of the related art relies on the doctor's auscultation and the cooperation of the subject, and some subjects are unable to cooperate, resulting in the inability to accurately identify the location and degree of sputum obstruction is solved.

[0037] The following specific embodiments are used to describe the technical solution of the present application in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0038] The sputum obstruction detection method based on the lung binary tree model described in the preferred embodiment of this application is as follows: Figure 1 As shown, the sputum obstruction detection method based on the lung binary tree model includes the following steps:

[0039] In step S101 , a normal lung impedance curve of a subject under normal lung conditions is obtained.

[0040] It is worth noting that the present application can calculate the human lung impedance from the pressure and flow signals collected by the forced oscillation test, and combine the simplified lung binary tree model to complete the identification of the lung airway geometric parameters, and by comparing with the airway geometric parameters under normal conditions, realize the identification of the location and degree of sputum blockage.

[0041] In one possible implementation, pressure and flow signals at the mouth of the subject undergoing a forced oscillation test under normal lung conditions are obtained; the pressure and flow signals are preprocessed to obtain preprocessed pressure and preprocessed flow signals; and a normal lung impedance curve is determined based on the preprocessed pressure and preprocessed flow signals.

[0042] Specifically, the lung impedance calculation involves collecting pressure and flow signals from the subject's mouth during a forced oscillation test while the subject's lungs are in normal condition. These pressure and flow signals are then preprocessed to calculate the lung impedance curve for the subject under normal conditions. Specifically, the subject's pressure and flow signals from the forced oscillation test are input, preprocessed, and the impedance curve is calculated, resulting in the output of the lung impedance curve under normal conditions.

[0043] Further, if Figure 2 As shown in the figure, during the preprocessing of the pressure and flow signals, the pressure and flow signals are downsampled to 128 Hz to reduce the amount of subsequent calculations; the pressure and flow changes caused by spontaneous breathing are extracted from the pressure and flow signals using a moving average filter, and the pressure and flow changes caused by spontaneous breathing are subtracted from the pressure and flow signals to obtain purer pressure and flow changes caused by forced oscillations.

[0044] In a possible implementation, for each frequency point, the pressure autopower spectrum corresponding to the pre-processed pressure under each sliding window is calculated. G pp , the flow autopower spectrum corresponding to the preprocessed flow signal G ff and cross power spectrum G fp ; Calculate the first average value corresponding to the pressure autopower spectrum and the second average value corresponding to the cross power spectrum under all sliding windows; Based on the first average value G pp_avg and the second average G fp_avg , calculating the impedance value at each frequency point; and obtaining a normal lung impedance curve based on the multiple impedance values ​​at different frequency points.

[0045] Further, if Figure 3 As shown in the calculation process of the lung impedance curve, for a certain frequency in the forced oscillation test f The pressure and flow signals under each sliding window are calculated by using a sliding window method to calculate the autopower spectrum and cross-power spectrum of the pressure and flow signals under each sliding window. G pp 、 G ff 、 G fp ;in, G pp 、 G ff 、 G fp Represent the autopower spectrum of pressure, autopower spectrum of flow and cross-power spectrum respectively; calculate the average value of the autopower spectrum of pressure, autopower spectrum of flow and cross-power spectrum under each window Gpp_avg 、 G ff_avg 、 G fp_avg To improve the accuracy of impedance calculation; according to the definition of impedance, impedance , calculate the impedance value at each frequency point; impedance is a complex number, calculate Z The real part of the respiratory resistance is ,calculate Z The imaginary part of the respiratory reactance is , Im Represents imaginary units; calculate different frequencies in sequence f Respiratory resistance R and respiratory reactance X The final complete impedance curve can be obtained, which describes the impedance characteristics of the lungs at different frequencies.

[0046] In step S102, a lung binary tree model is established, and parameters of the lung binary tree model are calibrated according to the normal lung impedance curve to obtain normal values ​​of airway geometric parameters.

[0047] It should be noted that the present application can effectively combine forced oscillation technology and respiratory dynamics modeling of the lung's physiological structure. Through a system identification method, it can quantitatively analyze the accumulation of sputum in the lungs, providing a reference for medical staff to determine whether to perform sputum suctioning on patients. The present invention first calculates the lung impedance curve under normal conditions using the pressure and flow signals recorded by the forced oscillation test when the subject's lungs are free of sputum obstruction. Combined with a simplified binary tree circuit model of the lungs, the airway geometric parameters (radius, length) under normal conditions are fitted to complete the calibration of the model parameters. In the sputum accumulation detection, the subject is again subjected to a forced oscillation test, the subject's lung impedance curve is calculated, and the airway geometric parameters are refitted. The impedance curve and airway geometric parameters are compared with the impedance curve and airway geometric parameters under normal conditions to complete the identification of the location of sputum accumulation and the degree of sputum obstruction.

[0048] In one possible implementation, the parameters to be optimized in the lung binary tree model are determined; the root mean square error between the simulated impedance curve fitted by the lung binary tree model and the normal lung impedance curve is used as a fitness function; based on the fitness function, the parameters to be optimized are optimized to obtain normal values ​​of airway geometric parameters.

[0049] It can be understood that the lung binary tree model is fitted according to the normal lung impedance curve to obtain a simulated impedance curve.

[0050] Specifically, lung model parameter calibration involves modeling the lungs as a simplified binary tree model related to airway geometry parameters based on the physiological structure and respiratory aerodynamics of the lungs. Using a system identification method, the calculated impedance curve under normal conditions is used as the standard value to fit the optimal airway geometry parameters, which serve as the normal values ​​of the airway geometry parameters. Specifically, the calculated impedance curve under normal conditions is input, the impedance curve is fitted using the binary tree model, and the optimal airway geometry parameters are found using the particle swarm optimization algorithm. The normal values ​​of the airway geometry parameters are then output.

[0051] The simplified binary tree model of the lungs is established based on the physiological structure of the lungs and the principles of respiratory aerodynamics. The lungs are simplified into a binary tree model determined by the geometric parameters of the airways. This model is used to simulate the gas flow in the lung airways. Specifically, a single airway is regarded as an axially symmetrical cylindrical pipe, and the gas is regarded as a Newtonian fluid. The gas flow in the airway is analogized to an electrical circuit using transmission line theory, and the respiratory resistance is calculated. R , compliance C and gas inertia L According to the physiological structure of the lungs, the human airway is divided into 23 levels, from the main airway (level 0) to the terminal airway (level 23). Assuming that each bifurcation of the airway is bifurcated and symmetrical, the lungs are modeled as a circuit diagram of a series-parallel structure. To simplify the calculation, it is assumed that the radius between two adjacent airways is r ,length l and wall thickness h The ratio is the same, respectively a, b, c express.

[0052] Furthermore, in the process of establishing the simplified binary tree model of the lungs, the movement of gas in a single trachea is regarded as flowing along an axially symmetrical cylindrical pipe, the gas is regarded as a Newtonian fluid, the flow process is analogized to a circuit, and combined with the transmission line theory, the following can be established: Figure 4 The circuit diagram shown is used to model the gas movement in a single airway. Q represents the airway flow, P represents the airway pressure, and the subscripts represent the different positions of the airway. Figure 4 In the figure, Q1 represents the first-order branch of the main airway, Q2 represents the second-order branch, P1 represents the pressure of the first-order branch, P2 represents the pressure of the second-order branch, and respiratory resistance R , compliance C and gas inertia L Can be calculated by pipeline geometry parameters and gas physical properties parameters; respiratory resistance Compliance Gas inertia ;in l is the length of the trachea, r is the radius of the trachea, h is the thickness of the tracheal wall, μ is the viscosity of the gas, ρ is the density of the gas, E is the effective elastic modulus, ν is the Poisson coefficient, δ For r The dimensionless constants involved, M 1, ε 1 are defined as the modulus and phase angle of the first-order Bessel function of the first kind, respectively. According to the physiological structure of the lungs, the human airway is divided into 23 levels. Level 0 is the main airway. According to the airway bifurcation, the airway level increases step by step. Level 23 airway is the terminal airway connected to the alveoli. In order to simplify the calculation, it is assumed that each bifurcation of the airway is a two-way bifurcation, and the left and right bifurcations are symmetrical. Then the lungs can be further modeled as follows Figure 5 The circuit diagram of the series-parallel structure shown in the figure, R represents respiratory resistance, L represents inertial resistance, C represents elastic resistance, and the subscript represents the corresponding airway level. Figure 5 In the figure, R0 represents the main airway respiratory resistance, L0 represents the main airway inertial resistance, C0 represents the main airway elastic resistance, R1 represents the respiratory resistance of the first-level branch of the main airway, L1 represents the inertial resistance of the first-level branch of the main airway, C1 represents the elastic resistance of the first-level branch of the main airway, and R 23 Represents the respiratory resistance of the twenty-third branch, L 23 represents the inertial resistance of the 23rd branch, C 23 represents the elastic resistance of the 23rd level branch, where the radius of each level of airway is r ,length l and wall thickness h is an undetermined parameter; in order to further reduce the number of parameters, it is assumed that the radius between the two adjacent airways r ,length l , and wall thickness h The scale factors are the same as a , b , c .

[0053] In one possible implementation, the position and velocity of each particle are initialized; wherein the position of the particle represents a combination of parameters to be optimized, and the velocity of the particle represents the direction and magnitude of the update of the parameters to be optimized; in each iteration, the fitness value of each particle is calculated according to the fitness function, and the individual historical optimal position and the global optimal position are updated according to the fitness value to obtain the current individual historical optimal position and the current global optimal position; according to the current individual historical optimal position and the current global optimal position, the position and velocity of each particle are updated to obtain the current position and current velocity of each particle; the iteration is stopped until the current number of iterations reaches the maximum number of iterations, or the fitness value corresponding to the current position is less than a preset threshold, and the current global optimal position corresponding to the current position is used as the normal value of the airway geometric parameters.

[0054] Using system identification technology, the parameters of the binary tree model are fitted through the actual measured impedance curve to obtain the airway geometry parameters under normal conditions. Specifically, the six parameters to be optimized in the binary tree model are determined ( r，l，h， a, b, c ); The root mean square error between the actual measured impedance curve and the impedance curve fitted by the model is used as the fitness function; Initialize the particle swarm and set the number of particles M , maximum number of iterations T max , inertia weight w , individual learning factor c 1. Social Learning Factor c 2. Randomly initialize the position and velocity of each particle. In each iteration, calculate the fitness value of each particle, update the individual historical optimal position and the global optimal position, and update the particle's velocity and position according to the velocity and position update formulas. Iterations terminate when the maximum number of iterations is reached or the fitness value of the global optimal position changes by less than a threshold. Finally, return the global optimal position as the optimal parameter fitting result of the model, i.e., the normal airway geometry parameters.

[0055] Furthermore, during the system identification process, based on the above binary tree circuit model established for the physiological structure of the lung, a total of 6 parameters to be optimized are included: r, l, h, a, b, c The optimization goal is to minimize the error between the final fitting result of the binary tree model and the actual measurement value; in system identification, the particle swarm optimization method in the random optimization method is adopted, and the fitness function is set as the root mean square error between the actual measured impedance curve and the impedance curve fitted by the model. x is the parameter vector to be optimized; during the initialization process, the number of particles M Set to 20, the maximum number of iterations is set to position T max , inertia weightw Set to 0.4, individual learning factor c 1. Social Learning Factor c 2 are all set to 1.5, the position of each particle x i Initialized randomly in the search space, the velocity v of each particle i Initialized to 0, individual historical optimal position pbest i Initialized to x i , the global optimal position gbest Initialized to the best fitness in the group pbest i ; In each iteration process t For each particle, calculate the current fitness value f ( x i ),like , then update pbest i =x i , in all pbest i Find the best one if ,renew gbest , for each particle i ,speed v i Update according to the following formula: ; rand () is a random number in [0, 1]. Position x i Update according to the following formula: x i =x i +v i ; The iteration stops when one of the following conditions is met: (1) The maximum number of iterations T is reached max , (2) gbest The fitness value change is less than the threshold 1e-5 ;Finally return to the global optimal position gbest , which is the optimal parameter fitting result of the model (i.e., the airway geometric parameters under normal circumstances).

[0056] It is understood that the system identification method in this application uses particle swarm optimization, a stochastic optimization method, to optimize the unknown parameters in the model. This method has the advantages of a small number of parameters, fast convergence, and strong global search capabilities. Other optimization methods such as genetic algorithms, gradient descent, and simulated annealing can also be used to optimize model parameters.

[0057] In step S103, the current lung impedance curve of the subject during the forced oscillation test is obtained, and the location and degree of sputum obstruction of the subject are determined based on the current lung impedance curve, the normal lung impedance curve and the normal values ​​of the airway geometric parameters.

[0058] In one possible implementation, the root mean square error (RMSE) between the current pulmonary impedance curve and the normal pulmonary impedance curve at all frequencies is calculated; a sputum blockage threshold is set; if the RMS error is greater than the sputum blockage threshold, the current airway geometry parameter fitting value is determined based on the current pulmonary impedance curve; and the location and degree of sputum blockage are determined based on the current airway geometry parameter fitting value and the normal value of the airway geometry parameter.

[0059] Specifically, identification of sputum obstruction: During sputum accumulation detection, the system performs a forced oscillation test on the subject again and calculates the lung impedance curve and the optimal airway geometry parameter fitting value from the forced oscillation test. These are then compared with the lung impedance curve and airway geometry parameter values ​​under normal conditions to identify the location and degree of sputum obstruction. Specifically, the system inputs the pressure and flow signals during sputum accumulation detection, along with the calibrated normal airway geometry parameters. The impedance curve and airway geometry parameter fitting values ​​during sputum accumulation are calculated, compared with the normal values, and the location and degree of sputum obstruction are output.

[0060] In a possible implementation, if the root mean square error value is smaller than the sputum blockage threshold, it is determined that the subject does not have sputum blockage.

[0061] Specifically, the impedance curve of the second measurement is compared with the impedance curve under normal conditions, and the root mean square error (RMS) of the two at all frequencies is calculated. RMSE ) to achieve this; set a threshold value to determine whether the change in the impedance curve is sufficient to indicate the occurrence of sputum obstruction. RMSE If the value is less than the threshold, it is considered that there is no sputum obstruction and the subject may be in a normal state or the degree of sputum obstruction is mild and not enough to cause a significant change in the impedance curve; if RMSE If the value is greater than the threshold, it is considered that sputum obstruction has occurred and further analysis is needed to determine the location and extent of the sputum obstruction. Positioning sputum obstruction: Assume that sputum obstruction mainly changes the parameters in the model. r (airway radius), while other parameters (such as l，h ) may be less affected or the change of radius is mainly considered in this scheme; r As the parameters to be optimized, the particle swarm optimization algorithm or other optimization algorithms are used to fit the optimal airway geometry parameters under sputum obstruction. By comparing the radius under normal conditions r and optimal radius in case of sputum obstruction r’, it is possible to identify changes in airway radius parameters caused by sputum obstruction. Based on the location of the radius parameter change (i.e., which level or levels of airway radius have changed significantly), the location of sputum obstruction can be inferred.

[0062] Further, if Figure 6 As shown, in the process of identifying the location and degree of sputum obstruction, the calibrated model parameters have been obtained through the impedance curve under normal conditions. r 、 l 、 h ,in r 、 l 、 h They represent the radius, length, and wall thickness of the airway from level 0 to level 23 under normal conditions. When performing sputum obstruction detection, the forced oscillation experiment is performed again. The second measured impedance curve (i.e., the current lung impedance curve) is obtained according to the same steps as step S101. The second measured impedance curve is compared with the impedance curve under normal conditions, and the root mean square error of the two at all frequencies is calculated. E ;

[0063] ;

[0064] in, N is the total number of frequency points, and Represent the respiratory resistance and respiratory reactance under normal circumstances. E If the value is less than the threshold, it is considered that no sputum obstruction occurs; if E If it is greater than the threshold, it is considered that sputum obstruction occurs. It is further assumed that sputum obstruction only changes the parameters in the model. r , then r As the parameter to be optimized, the particle swarm optimization algorithm in step S102 is used again to obtain the optimal parameter r’ (Right now Figure 6 The model radius of r and r’ By comparing, the change in airway radius parameters caused by sputum obstruction can be obtained, and the location of sputum obstruction can be further obtained, thereby providing corresponding suggestions to doctors.

[0065] Next, a sputum obstruction detection system based on a lung binary tree model proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0066] Figure 7 It is a structural diagram of the sputum obstruction detection system based on the lung binary tree model in an embodiment of the present application.

[0067] like Figure 7As shown, the sputum obstruction detection system based on the lung binary tree model includes: a lung impedance calculation module 100 , a lung model parameter calibration module 200 and a sputum obstruction identification module 300 .

[0068] Specifically, the lung impedance calculation module 100 is used to obtain a normal lung impedance curve of a subject under normal lung conditions;

[0069] A lung model parameter calibration module 200 is used to establish a lung binary tree model, calibrate the parameters of the lung binary tree model according to the normal lung impedance curve, and obtain normal values ​​of airway geometric parameters;

[0070] The sputum obstruction identification module 300 is used to obtain the current lung impedance curve of the subject during the forced oscillation test during sputum accumulation detection, and determine the location and degree of sputum obstruction of the subject based on the current lung impedance curve, the normal lung impedance curve and the normal values ​​of the airway geometric parameters.

[0071] Figure 8 This is a diagram of the structure of a terminal provided in an embodiment of the present application. The terminal may include:

[0072] Memory 501 , processor 502 , and computer programs stored in the memory 501 and executable on the processor 502 .

[0073] When the processor 502 executes the program, the sputum obstruction detection method based on the lung binary tree model provided in the above embodiment is implemented.

[0074] Furthermore, the terminal further includes:

[0075] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0076] The memory 501 is used to store computer programs that can be run on the processor 502 .

[0077] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0078] If the memory 501, processor 502, and communication interface 503 are implemented independently, the communication interface 503, memory 501, and processor 502 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EIS) bus. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0079] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0080] The processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0081] This embodiment also provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the computer-readable storage medium implements the above-mentioned sputum obstruction detection method based on the lung binary tree model.

[0082] One embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the Figure 1 Any of the corresponding embodiments provides a sputum obstruction detection method based on a lung binary tree model.

[0083] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to user analysis data, user storage data, user display data, etc.) and signals involved in the present invention are all information, data and signals authorized by the user or fully authorized by all parties; and the collection, use and processing of relevant information, data and signals comply with the laws, regulations and standards of relevant countries and regions.

[0084] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0085] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0086] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0087] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable storage medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable storage medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (not exhaustive) of computer-readable storage media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable storage medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0088] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logical functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0089] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0090] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0091] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

[0092] It should be understood that the application of this application is not limited to the above examples. For ordinary technicians in this field, they can make improvements or changes based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to this application.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A sputum obstruction detection method based on a lung binary tree model, characterized in that: The sputum obstruction detection method based on the lung binary tree model includes: Obtaining a normal lung impedance curve of a subject undergoing forced oscillation testing under normal lung conditions; Establishing a lung binary tree model, and calibrating parameters of the lung binary tree model according to the normal lung impedance curve to obtain normal values ​​of airway geometric parameters, wherein the normal values ​​of the airway geometric parameters include airway radius; Obtaining a current lung impedance curve of the subject during a forced oscillation test during sputum accumulation detection, and determining a location of sputum obstruction in the subject based on the current lung impedance curve, the normal lung impedance curve, and the normal values ​​of the airway geometric parameters; The step of calibrating the parameters of the lung binary tree model according to the normal lung impedance curve to obtain normal values ​​of airway geometric parameters specifically includes: Determining parameters to be optimized in the lung binary tree model; The root mean square error between the simulated impedance curve fitted by the lung binary tree model and the normal lung impedance curve is used as a fitness function; Based on the fitness function, the parameters to be optimized are optimized to obtain normal values ​​of airway geometric parameters; The determining the location of the subject's sputum obstruction according to the current lung impedance curve, the normal lung impedance curve, and the normal value of the airway geometry parameter specifically includes: Calculating root mean square errors (RMS) between the current pulmonary impedance curve and the normal pulmonary impedance curve at all frequencies; Setting a sputum blockage threshold, and if the root mean square error value is greater than the sputum blockage threshold, determining a current airway geometry parameter fitting value according to the current lung impedance curve; The location of sputum obstruction is determined according to the current airway geometric parameter fitting value and the normal value of the airway geometric parameter.

2. The sputum obstruction detection method based on the lung binary tree model according to claim 1, characterized in that: The step of obtaining a normal lung impedance curve of a subject undergoing a forced oscillation test under normal lung conditions specifically includes: obtaining pressure and flow signals at the mouth of the subject undergoing a forced oscillation test under normal lung conditions; Preprocessing the pressure and flow signals to obtain preprocessed pressure and preprocessed flow signals; A normal pulmonary impedance curve is determined according to the preprocessed pressure and the preprocessed flow signal.

3. The sputum obstruction detection method based on the lung binary tree model according to claim 2, characterized in that: Determining a normal pulmonary impedance curve according to the preprocessed pressure and the preprocessed flow signal specifically includes: For each frequency point, calculate the pressure autopower spectrum corresponding to the preprocessed pressure under each sliding window, and the flow autopower spectrum and cross-power spectrum corresponding to the preprocessed flow signal; Calculating a first average value corresponding to the pressure autopower spectrum and a second average value corresponding to the cross-power spectrum under all sliding windows; Calculating the impedance value at each frequency point according to the first average value and the second average value; A normal lung impedance curve is obtained according to the multiple impedance values ​​at different frequency points.

4. The sputum obstruction detection method based on the lung binary tree model according to claim 1, characterized in that: Optimizing the parameters to be optimized based on the fitness function to obtain normal values ​​of airway geometric parameters specifically includes: Initializing the position and velocity of each particle; wherein the position of the particle represents a combination of the parameters to be optimized, and the velocity of the particle represents the direction and magnitude of the update of the parameters to be optimized; In each iteration, the fitness value of each particle is calculated according to the fitness function, and the individual historical optimal position and the global optimal position are updated according to the fitness value to obtain the current individual historical optimal position and the current global optimal position; updating the position and velocity of each particle according to the current individual historical optimal position and the current global optimal position to obtain the current position and current velocity of each particle; When the current number of iterations reaches the maximum number of iterations, or the fitness value corresponding to the current position is less than a preset threshold, the iteration is stopped, and the current global optimal position corresponding to the current position is used as the normal value of the airway geometric parameter.

5. The sputum obstruction detection method based on the lung binary tree model according to claim 1, characterized in that: The step of calculating the root mean square error between the current lung impedance curve and the normal lung impedance curve at all frequencies further includes: If the root mean square error value is less than the sputum blockage threshold, it is determined that the subject does not have sputum blockage.

6. A sputum obstruction detection system based on a lung binary tree model, characterized in that: The sputum obstruction detection system based on the lung binary tree model is applied to the sputum obstruction detection method based on the lung binary tree model according to any one of claims 1 to 5; the sputum obstruction detection system based on the lung binary tree model comprises: A lung impedance calculation module is used to obtain a normal lung impedance curve of a subject undergoing forced oscillation testing under normal lung conditions; a lung model parameter calibration module, configured to establish a lung binary tree model, calibrate the parameters of the lung binary tree model according to the normal lung impedance curve, and obtain normal values ​​of airway geometric parameters, wherein the normal values ​​of the airway geometric parameters include airway radius; The sputum obstruction identification module is used to obtain the current lung impedance curve of the subject during the forced oscillation test during sputum accumulation detection, and determine the location of the subject's sputum obstruction based on the current lung impedance curve, the normal lung impedance curve and the normal values ​​of the airway geometric parameters.

7. A terminal, characterized in that: The terminal includes: a memory, a processor, and a sputum obstruction detection program based on a pulmonary binary tree model stored in the memory and executable on the processor. When the sputum obstruction detection program based on a pulmonary binary tree model is executed by the processor, the steps of the sputum obstruction detection method based on a pulmonary binary tree model are implemented.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a sputum obstruction detection program based on a pulmonary binary tree model. When the sputum obstruction detection program based on a pulmonary binary tree model is executed by a processor, the steps of the sputum obstruction detection method based on a pulmonary binary tree model are implemented as described in any one of claims 1 to 5.

Images