CN120093273B - Sputum obstruction detection method, system, terminal and medium based on lung binary tree model - Google Patents
Sputum obstruction detection method, system, terminal and medium based on lung binary tree modelInfo
- Publication number
- CN120093273B CN120093273B CN202510579459.XA CN202510579459A CN120093273B CN 120093273 B CN120093273 B CN 120093273B CN 202510579459 A CN202510579459 A CN 202510579459A CN 120093273 B CN120093273 B CN 120093273B
- Authority
- CN
- China
- Prior art keywords
- lung
- sputum
- binary tree
- tree model
- normal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Measuring devices for evaluating the respiratory organs
- A61B5/085—Measuring impedance of respiratory organs or lung elasticity
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Veterinary Medicine (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Physiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Primary Health Care (AREA)
- Pulmonology (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Epidemiology (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Probability & Statistics with Applications (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The application discloses a sputum obstruction detection method, a system, a terminal and a medium based on a lung binary tree model, wherein the sputum obstruction detection method based on the lung binary tree model comprises the steps of obtaining a normal lung impedance curve of a subject under the normal condition of a lung; the method comprises the steps of establishing a lung binary tree model, carrying out parameter calibration on the lung binary tree model according to a normal lung impedance curve to obtain a normal value of airway geometric parameters, obtaining a current lung impedance curve of a subject, carrying out forced oscillation test when sputum is accumulated and detected, and determining the position and degree of sputum blockage of the subject according to the current lung impedance curve, the normal lung impedance curve and the normal value of airway geometric parameters. According to the application, through simplifying a lung binary tree model and quantitatively analyzing the accumulation condition of sputum in the lung, the position and degree of the sputum blockage can be accurately identified, and the comfort level of a patient is improved by adopting forced oscillation measurement, so that the physical and psychological burden of sputum suction on the patient is reduced.
Description
Technical Field
The application relates to the technical field of physiological signal processing and modeling analysis, in particular to a sputum obstruction detection method, a system, a terminal and a medium based on a lung binary tree model.
Background
Mechanical ventilation is one of the key technologies for clinical treatment of critically ill patients. However, mechanical ventilation generally stimulates the airway mucosa, resulting in increased airway sputum. During mechanical ventilation, the patient is often unable to expel sputum out of the body through natural physiological reactions, resulting in deposition of sputum in the patient's lungs. Sputum deposition can lead to a number of adverse reactions and induced complications, and frequent sputum aspiration can place a physical and psychological burden on the patient. Therefore, the identification of sputum accumulation can provide the medical staff with proper sputum suction time to reduce the physical and psychological burden of sputum suction on patients.
The current clinical judgment of sputum accumulation mainly depends on auscultation of doctors, which takes a lot of time for the doctors. Pulmonary function testing is a gold standard for diagnosing pulmonary obstruction, but this test requires a high degree of coordination by the subject to perform a strict and powerful respiratory maneuver, which is difficult to accomplish successfully for critically ill patients.
Accordingly, the prior art is still in need of improvement and development.
Disclosure of Invention
The application mainly aims to provide a sputum obstruction detection method, a system, a terminal and a medium based on a lung binary tree model, and aims to solve the problem that in the prior art, the judgment of accumulation of sputum clinically depends on auscultation of doctors and matching of subjects, and the position and degree of the obstruction of the sputum cannot be accurately identified due to the fact that some subjects cannot be matched.
The embodiment of the application provides a sputum obstruction detection method based on a lung binary tree model, which comprises the following steps of obtaining a normal lung impedance curve of a subject under the normal condition of a lung, establishing a lung binary tree model, carrying out parameter calibration on the lung binary tree model according to the normal lung impedance curve to obtain a normal value of an airway geometric parameter, obtaining a current lung impedance curve of the subject, carrying out forced oscillation test when sputum accumulation is detected, and determining the position and degree of the sputum obstruction of the subject according to the current lung impedance curve, the normal lung impedance curve and the normal value of the airway geometric parameter.
Optionally, in one embodiment of the present application, the method for acquiring a normal lung impedance curve of a subject under normal conditions of the lung specifically includes acquiring a pressure and a flow signal of a mouth of the subject under normal conditions of the lung for a forced oscillation test, preprocessing the pressure and the flow signal to obtain a preprocessed pressure and a preprocessed flow signal, and determining a normal lung impedance curve according to the preprocessed pressure and the preprocessed flow signal.
Optionally, in an embodiment of the present application, the determining a normal pulmonary impedance curve according to the preprocessed pressure and the preprocessed flow signal specifically includes calculating, for each frequency point, a pressure self-power spectrum corresponding to the preprocessed pressure, a flow self-power spectrum corresponding to the preprocessed flow signal, and a cross-power spectrum corresponding to the preprocessed flow signal under each sliding window, calculating a first average value corresponding to the pressure self-power spectrum and a second average value corresponding to the cross-power spectrum under all sliding windows, calculating an impedance value under each frequency point according to the first average value and the second average value, and obtaining a normal pulmonary impedance curve according to a plurality of impedance values under different frequency points.
Optionally, in one embodiment of the present application, the parameter calibration is performed on the pulmonary binary tree model according to the normal pulmonary impedance curve to obtain an airway geometric parameter normal value, which specifically includes determining a parameter to be optimized in the pulmonary binary tree model, using a root mean square error of a simulated impedance curve fitted by the pulmonary binary tree model and the normal pulmonary impedance curve as an fitness function, and optimizing the parameter to be optimized based on the fitness function to obtain the airway geometric parameter normal value.
Optionally, in an embodiment of the present application, the optimizing the parameter to be optimized based on the fitness function to obtain a normal value of the geometric parameter of the air channel specifically includes initializing a position and a speed of each particle, where the position of each particle represents one of the parameter combinations to be optimized, the speed of each particle represents a direction and a magnitude of updating the parameter to be optimized, calculating, in each iteration, a fitness value of each particle according to the fitness function, and updating an individual historical optimal position and a global optimal position according to the fitness value to obtain a current individual historical optimal position and a current global optimal position, updating, according to the current individual historical optimal position and the current global optimal position, a current position and a current speed of each particle to obtain a current position and a current speed of each particle, and taking the current global optimal position corresponding to the current position as the geometric parameter value of the air channel when a current iteration number reaches a maximum iteration number or when the fitness value corresponding to the current position is smaller than a preset threshold and stops iterating.
Optionally, in one embodiment of the present application, the obtaining the position and the degree of the sputum obstruction according to the current lung impedance curve, the normal lung impedance curve and the normal airway geometric parameter value specifically includes calculating a root mean square error value of the current lung impedance curve and the normal lung impedance curve on all frequencies, setting a sputum obstruction threshold, determining a fitting value of the current airway geometric parameter according to the current lung impedance curve if the root mean square error value is greater than the sputum obstruction threshold, and determining the position and the degree of the sputum obstruction according to the fitting value of the current airway geometric parameter and the normal airway geometric parameter value.
Optionally, in one embodiment of the present application, the calculating the root mean square error value of the current lung impedance curve and the normal lung impedance curve at all frequencies further comprises determining that the subject is not experiencing sputum blockage if the root mean square error value is less than the sputum blockage threshold.
The second aspect of the embodiment of the application also provides a sputum obstruction detection system based on a pulmonary binary tree model, wherein the sputum obstruction detection system based on the pulmonary binary tree model comprises:
The lung impedance calculation module is used for acquiring a normal lung impedance curve of the subject under the normal condition of the lung;
the lung model parameter calibration module is used for establishing a lung binary tree model, and carrying out parameter calibration on the lung binary tree model according to the normal lung impedance curve to obtain a normal value of the geometric parameter of the airway;
The sputum obstruction identification module is used for acquiring a current lung impedance curve of the subject, which is subjected to forced oscillation test during sputum accumulation detection, and determining the position and degree of sputum obstruction of the subject according to the current lung impedance curve, the normal lung impedance curve and the normal value of the geometric parameter of the airway.
The third aspect of the embodiment of the application also provides a terminal, wherein the terminal comprises a memory, a processor and a sputum obstruction detection program based on a pulmonary binary tree model, wherein the sputum obstruction detection program is stored on the memory and can run on the processor, and the sputum obstruction detection program based on the pulmonary binary tree model realizes the steps of the sputum obstruction detection method based on the pulmonary binary tree model when being executed by the processor.
The fourth aspect of the embodiment of the present application further provides a computer readable storage medium, where the computer readable storage medium stores a sputum obstruction detection program based on a pulmonary binary tree model, where the sputum obstruction detection program based on the pulmonary binary tree model implements the steps of the sputum obstruction detection method based on the pulmonary binary tree model as described above when executed by a processor.
The sputum blockage detection method, the system, the terminal and the medium based on the pulmonary binary tree model have the advantages that the pulmonary binary tree model is built by combining the forced oscillation technology and the respiratory dynamics of the pulmonary physiological structure, the accumulation condition of the sputum in the lung is quantitatively analyzed, the position and the degree of the sputum blockage can be accurately identified, the reference of whether the sputum is sucked or not is provided for medical staff, the comfort level of the patient is improved by adopting the forced oscillation measurement, and the physical and psychological burden of the sputum suction on the patient is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art.
FIG. 1 is a flow chart of a preferred embodiment of the sputum obstruction detection method of the present application based on a pulmonary binary tree model;
FIG. 2 is a flow chart of preprocessing of pressure and flow signals in a preferred embodiment of the sputum obstruction detection method of the present application based on a pulmonary binary tree model;
FIG. 3 is a flow chart of impedance curve calculation in a preferred embodiment of the sputum obstruction detection method based on a pulmonary binary tree model of the present application;
FIG. 4 is an analog diagram of a single airway circuit in a preferred embodiment of the sputum obstruction detection method of the present application based on a pulmonary binary tree model;
FIG. 5 is a simplified binary tree circuit analog diagram of the lung in a preferred embodiment of the sputum obstruction detection method of the present application based on a binary tree model of the lung;
FIG. 6 is a flow chart of identifying pulmonary sputum obstruction in a preferred embodiment of the sputum obstruction method of the application based on a pulmonary binary tree model;
FIG. 7 is a block diagram of a preferred embodiment of the sputum obstruction detection system of the present application based on a pulmonary binary tree model;
fig. 8 is a block diagram of a preferred embodiment of the terminal of the present application.
Reference numerals illustrate:
100. the device comprises a lung impedance calculation module, a lung model parameter calibration module and a sputum blockage identification module.
Detailed Description
In order to make the objects, technical solutions and effects of the present application clearer and more specific, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and the described embodiments are only possible technical implementations of the present application, but not all possible implementations. Based on the embodiments of the present application, a person skilled in the art may well combine the embodiments of the present application to obtain other embodiments without inventive faculty, and these embodiments are also within the scope of the present application.
In related art, a method predicts a patient's lung function based on CT image data. Firstly, CT image data are acquired, airway data are extracted, an airway model is generated by utilizing a three-dimensional reconstruction technology, then lung function statistical data are input into a normal model and a narrow model for simulation, simulation data are generated, and finally the simulation data are input into a lung function prediction model, and a predicted value is output. The method has the defects of dependence on CT image data, high cost, complex processing process and large calculated amount. The application does not depend on CT image data to simulate the lung, the lung impedance curve is measured through forced oscillation, and the change of each airway geometric parameter of a patient is fitted through simplifying a lung binary tree model and a particle swarm optimization algorithm, so that the position and degree of the obstruction of the lung sputum are identified.
In the related technology, another method is to put into a sleep respiratory monitoring and blocking positioning system through the nasal cavity inner cavity tract, monitor the contact pressure signal in the respiratory tract by using a carrier catheter integrated with a pressure sensor array, analyze the pressure signal by a processing module, and obtain the pressure change condition in the respiratory tract so as to monitor the blocking condition of the sleep respiratory tract. The method has the defects that the invasive measurement method possibly brings discomfort to a patient, is mainly used for monitoring the respiratory tract obstruction in a sleeping state, and has limited application range. The application adopts a non-invasive measurement method to measure the impedance of the lung, and can not directly obtain the blocking condition in the respiratory tract, but fits the geometric parameters of the air outlet channel through a lung modeling and parameter optimization method, thereby indirectly reflecting the blocking condition, having higher comfort in practical application, and mainly facing the positioning of sputum in the pulmonary blocking.
Forced oscillation examination technique (FOT, forcedOscillationTechnique) is a non-invasive, forced exhalation-independent method of measuring respiratory mechanics in the lungs. The principle is that a pressure wave with a certain frequency is applied to the respiratory system in the process of calm breathing, and pressure and flow signals of the mouth of a patient are measured to calculate the impedance of the respiratory system. Qualitative determination of pulmonary obstruction can be achieved by comparing key parameters of respiratory impedance with empirical values, such as resistance at 5 hertz (R5), resistance at 20 hertz (R20), resonance frequency (Fres), resistance at 5 hertz (X5), resistance at 20 hertz (X20). However, the method cannot quantitatively judge the specific position and the blocking degree of the blocking, and therefore the method is combined with a lung simplified binary tree circuit model and a particle swarm optimization algorithm to solve the problems.
The application has the following innovation points that firstly, the air passage binary tree model is simplified, because of the complex structure of the air passage, the accurate modeling simulation calculation amount of the air passage is large, the calculation complexity is reduced by simplifying the model to reduce the calculation accuracy in practical application, the air passage model is analogically to a circuit model by combining with a transmission line theory, meanwhile, the air passage is further assumed to be in a symmetrical and uniform binary tree structure, and specific proportional relations are met among air passages of each stage, the model is further simplified, the parameter amount of the model is reduced, and the practicability is higher. Secondly, a lung airway parameter fitting algorithm is used, namely in order to enable an impedance curve of a simulation model to be consistent with an actual measured impedance value of forced oscillation as much as possible, a particle swarm optimization algorithm in a stochastic optimization algorithm is adopted to optimize airway parameters in the model, the method has the advantages of being small in parameter number, strong in global searching capability and the like, and the optimized airway radius parameters are compared with airway radius parameters under normal conditions, so that the specific position and the blocking degree of blocking can be reflected.
The following describes a sputum obstruction detection method, a system, a terminal and a medium based on a lung binary tree model according to an embodiment of the present application with reference to the accompanying drawings. Aiming at the problem that the sputum accumulation is judged clinically by doctor auscultation and subject matching in the related technology, and the position and degree of the sputum blockage cannot be accurately identified due to the fact that some subjects cannot be matched, the application provides a sputum blockage detection method based on a lung binary tree model, in the method, a lung binary tree model is established by combining a forced oscillation technology and lung physiological structure breathing dynamics, the condition that the quantitative analysis sputum accumulated in the lung can accurately identify the position and degree of sputum obstruction, provides the reference of whether inhale phlegm operation to the patient for medical personnel, adopts forced oscillation measurement to improve patient's comfort level to reduce and inhale phlegm to patient's health and psychological burden, simplified model and optimization algorithm have reduced computational complexity, have improved the practicality, and do not rely on CT image data, have reduced use cost. Therefore, the technical problems that in the related technology, the judgment of accumulation of sputum clinically depends on auscultation of doctors and matching of subjects, and the position and degree of the obstruction of the sputum cannot be accurately identified due to the fact that some subjects cannot be matched are solved.
The technical scheme of the application is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
According to the preferred embodiment of the application, as shown in fig. 1, the sputum obstruction detection method based on the lung binary tree model comprises the following steps:
In step S101, a normal lung impedance curve of the subject under normal conditions of the lung is acquired.
It is worth to say that the application can calculate the human lung impedance from the pressure and flow signals collected by the forced oscillation test, and the identification of the lung airway geometric parameters is completed by combining the simplified lung binary tree model, and the identification of the sputum blocking position and the blocking degree is realized by comparing the lung airway geometric parameters with the airway geometric parameters under the normal condition.
In one possible implementation, the method comprises the steps of obtaining pressure and flow signals of a mouth of a subject under the normal condition of a lung for forced oscillation test, preprocessing the pressure and the flow signals to obtain preprocessed pressure and preprocessed flow signals, and determining a normal lung impedance curve according to the preprocessed pressure and the preprocessed flow signals.
The method comprises the steps of calculating the lung impedance, namely collecting pressure and flow signals of a mouth of a subject under the normal condition of the lung in the forced oscillation process, and calculating a lung impedance curve of the subject under the normal condition after the pressure and flow signals are preprocessed. That is, the pressure and flow signals of the subject in the forced oscillation test are input, and then the signals are preprocessed to calculate an impedance curve, and the impedance curve of the lung under normal conditions is output.
Further, as shown in FIG. 2, 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 computation, and a moving average filter is used to extract the pressure and flow changes from the main breath from the pressure and flow signals and subtract the pressure and flow changes from the main breath from the pressure and flow signals to obtain purer pressure and flow changes from the forced oscillations.
In one possible implementation manner, for each frequency point, a pressure self-power spectrum G pp corresponding to the preprocessed pressure, a flow self-power spectrum G ff corresponding to the preprocessed flow signal, and a cross-power spectrum G fp corresponding to the preprocessed flow signal under each sliding window are calculated, a first average value corresponding to the pressure self-power spectrum and a second average value corresponding to the cross-power spectrum under all sliding windows are calculated, an impedance value under each frequency point is calculated according to the first average value G pp_avg and the second average value G fp_avg, and a normal lung impedance curve is obtained according to a plurality of impedance values under different frequency points.
Further, as shown in FIG. 3, in the calculation of the pulmonary impedance curve, for the pressure and flow signals at a certain frequency f in the forced oscillation test, the self-power spectrum and the cross-power spectrum G pp、Gff、Gfp of the pressure and flow signals under each sliding window are calculated by adopting a sliding window mode, wherein G pp、Gff、Gfp represents the self-power spectrum of the pressure, the self-power spectrum of the flow and the cross-power spectrum respectively, the average value G pp_avg、Gff_avg、Gfp_avg of the pressure self-power spectrum, the flow self-power spectrum and the cross-power spectrum under each window is calculated to improve the accuracy of impedance calculation, and the impedance is defined according to the impedanceCalculating the impedance value at each frequency point, wherein the impedance is a complex number, and calculating the real part of Z to obtain respiratory resistanceCalculating the imaginary part of Z to obtain respiratory reactanceAnd sequentially calculating the respiratory resistance R and the respiratory reactance X under different frequencies f to obtain a final complete impedance curve, wherein the curve describes the impedance characteristics of the lung under different frequencies.
In step S102, a pulmonary binary tree model is established, and parameter calibration is performed on the pulmonary binary tree model according to the normal pulmonary impedance curve, so as to obtain a normal value of the geometric parameters of the airway.
The application can effectively combine the forced oscillation technology and the respiratory dynamics modeling of the lung physiological structure, quantitatively analyze the accumulation condition of sputum in the lung by a system identification method, and provide reference for medical staff to perform sputum aspiration operation on patients. According to the application, firstly, under the condition that the lung of a subject is free from phlegm obstruction, a lung impedance curve under normal conditions is obtained through calculation of pressure and flow signals recorded by forced oscillation test. And fitting the geometric parameters (radius and length) of the airway under normal conditions by combining the lung simplified binary tree circuit model to finish the calibration of the model parameters. In sputum accumulation detection, the subjects were again subjected to a forced oscillation test, the pulmonary impedance curve of the subjects was calculated and airway geometry parameters were re-fitted. And comparing the impedance curve with the airway geometric parameters and the impedance curve and the airway geometric parameters under normal conditions, and completing identification of the accumulation position of the sputum and the degree of the sputum blockage.
In one possible implementation manner, parameters to be optimized in the lung binary tree model are determined, root mean square errors of a simulated resistance curve fitted by the lung binary tree model and the normal lung resistance curve are used as fitness functions, and the parameters to be optimized are optimized based on the fitness functions to obtain normal values of the geometric parameters of the air passage.
It can be appreciated that the pulmonary binary tree model is fitted to obtain a simulated resistance curve according to the normal pulmonary resistance curve.
The lung model parameter calibration comprises the steps of modeling the lung into a simplified binary tree model related to the airway geometric parameter according to the physiological structure and respiratory aerodynamic of the lung, and fitting the optimal airway geometric parameter as a normal value of the airway geometric parameter by taking a calculated impedance curve under normal conditions as a standard value through a system identification method. Namely, the calculated impedance curve under normal conditions is input, the binary tree model is used for fitting the impedance curve, the optimal geometric parameters of the air passage are found through a particle swarm optimization algorithm, and the normal values of the geometric parameters of the air passage are output.
A simplified binary tree model of the lung is established, the lung is simplified into a binary tree model determined by the geometrical parameters of the airway according to the physiological structure and respiratory aerodynamic principle of the lung, and the model is used for simulating the gas flow in the airway of the lung. The method comprises the steps of considering a single air passage as a cylindrical pipeline which is symmetrical along the axial direction, considering gas as Newton fluid, using a transmission line theory to convert the flow of the gas in the air passage into a circuit, calculating the formulas of respiratory resistance R, compliance C and gas inertia L, dividing the human air passage into 23 grades according to the physiological structure of the lung, dividing the human air passage into two branches from a main air passage (0 th grade) to an end air passage (23 rd grade), assuming that each branch of the air passage is divided into two branches and is symmetrical left and right, and modeling the lung as a circuit diagram of a series-parallel structure, wherein the ratio of radius R, length L and wall thickness h between two adjacent air passages is the same for simplifying calculation and is respectively represented by a, b and C.
Further, in the process of establishing a simplified binary tree model of the lung, the motion process of the gas in a single air pipe is regarded as cylindrical pipeline flow which is symmetrical along the axial direction, the gas is regarded as Newtonian fluid, the flow process is analogized into a circuit, and the theory of transmission lines is combined, finally, a circuit diagram shown in fig. 4 can be established for modeling the gas motion in a single air passage, Q represents the flow of the air passage, the pressure of the air passage represented by P, the subscript represents different positions of the air passage, in fig. 4, Q 1 represents the first branch of the main air passage, Q 2 represents the second branch, P 1 represents the pressure of the first branch, P 2 represents the pressure of the second branch, respiratory resistance R, compliance C and gas inertia L can be calculated through geometric parameters of the pipeline and physical property parameters of the gasCompliance withInertia of gasWherein l is the length of the trachea, r is the radius of the trachea, h is the thickness of the wall of the trachea, mu is the viscosity of the gas, rho is the density of the gas, E is the effective elastic modulus, v is the Poisson's coefficient, delta is the dimensionless constant associated with r, and M 1,ε1 is defined as the modulus and phase angle of the first order Bessel function, respectively. According to the lung physiological structure, human airways are divided into 23 grades, the 0 th grade is a main airway, the grade of the airways gradually increases according to the bifurcation of the airways, and the 23 grades of the airways are end airways connected with alveoli. In order to simplify the calculation, assuming that each bifurcation of the air passage is bifurcated and the left and right bifurcation is symmetrical, the lung can be further modeled as a circuit diagram of a series-parallel structure as shown in fig. 5, R represents respiratory resistance, L represents inertial resistance, C represents elastic resistance, subscript represents the corresponding airway progression, in fig. 5, R 0 represents respiratory resistance of the main air passage, L 0 represents inertial resistance of the main air passage, C 0 represents elastic resistance of the main air passage, R 1 represents respiratory resistance of the first-stage branch of the main air passage, L 1 represents inertial resistance of the first-stage branch of the main air passage, C 1 represents elastic resistance of the first-stage branch of the main air passage, R 23 represents respiratory resistance of the twenty-third-stage branch, L 23 represents inertial resistance of the twenty-third-stage branch, C 23 represents elastic resistance of the twenty-third-stage branch, wherein the radius R, length L and wall thickness h of each stage air passage are parameters to be determined, and in order to further reduce the parameter, the radius R, the length L and the wall thickness ratio between adjacent two stages are the same, and the scale factors are a, b, C, respectively.
In one possible implementation mode, initializing the position and the speed of each particle, wherein the position of each particle represents one parameter combination to be optimized, the speed of each particle represents the updating direction and the updating size of the parameter combination to be optimized, calculating the fitness value of each particle according to the fitness function in each iteration, updating the individual historical optimal position and the global optimal position according to the fitness value to obtain the current individual historical optimal position and the current global optimal position, updating the position and the speed of each particle according to the current individual historical optimal position and the current global optimal position to obtain the current position and the current speed of each particle, and stopping iteration until the current iteration number reaches the maximum iteration number or the fitness value corresponding to the current position is smaller than a preset threshold value, and taking the current global optimal position corresponding to the current position as the normal value of the geometric parameter of the airway.
And fitting parameters of the binary tree model through an actually measured impedance curve by using a system identification technology, so as to obtain the geometric parameters of the airway under normal conditions. The method comprises the steps of determining 6 parameters (r, l, h, a, b and c) to be optimized in a binary tree model, taking root mean square error of an actually measured impedance curve and an impedance curve fitted by the model as a fitness function, initializing a particle group, setting the number M of particles, the maximum iteration number T max, an inertia weight w, an individual learning factor c 1 and a social learning factor c 2, and randomly initializing the position and the speed of each particle. In each iteration, calculating the fitness value of each particle, updating the historical optimal position and the global optimal position of the individual, and updating the speed and the position of the particle according to a speed updating formula and a position updating formula. And stopping iteration when the maximum iteration number or the change of the fitness value of the global optimal position is smaller than the threshold value. And finally returning the global optimal position as the best parameter fitting result of the model, namely the airway geometric parameters under normal conditions.
Further, in the system identification process, based on the binary tree circuit model established for the lung physiological structure, 6 parameters r, l, h, a, b, c to be optimized are included, optimization aims at enabling the final fitting result and the actual measured value error of the binary tree model to be minimum, in the system identification process, a particle swarm optimization method in a random optimization method is adopted, a fitness function is set to be the root mean square error of an actually measured impedance curve and an impedance curve fitted by the model, x is a parameter vector to be optimized, in the initialization process, the number M of particles is set to be 20, the maximum iteration number is set to be a position T max, the inertia weight w is set to be 0.4, the individual learning factor c 1 and the social learning factor c 2 are set to be 1.5, the position x i of each particle is randomly initialized in a search space, the speed v i of each particle is initialized to be 0, the individual historical optimal position pbest i is initialized to be x i, the global optimal position gbest is initialized to be the iteration pbest i with the best fitness in the swarm, in each process T, the current fitness value f (x i) is calculated for each particleThen update pbest i=xi, find the best among all pbest i, ifUpdate gbest, for each particle i, velocity v i is updated according to the following formula: And rand () is a random number of [0,1 ]. The position x i is updated according to the following formula, namely x i=xi+vi, iteration is stopped when one of the following conditions is met (1) the maximum iteration number T max is reached, (2) the change of the fitness value of gbest is smaller than a threshold value 1e-5, and finally the global optimal position gbest is returned, namely the best parameter fitting result of the model (namely the airway geometric parameters under normal conditions).
It can be understood that the system identification method in the application adopts the particle swarm optimization method in the random optimization method to optimize the unknown parameters in the model, and has the advantages of less parameters, high convergence rate and strong global searching capability. Other optimization methods such as genetic algorithm, gradient descent, simulated annealing, etc. can be used in optimizing model parameters as well.
In step S103, a current lung impedance curve of the subject subjected to the forced oscillation test during sputum accumulation detection is obtained, and the position and degree of sputum obstruction of the subject are determined according to the current lung impedance curve, the normal lung impedance curve and the normal value of the airway geometric parameter.
In one possible implementation, root mean square error values of the current lung impedance curve and the normal lung impedance curve at all frequencies are calculated, a sputum obstruction threshold is set, if the root mean square error value is larger than the sputum obstruction threshold, a current airway geometric parameter fitting value is determined according to the current lung impedance curve, and the position and degree of sputum obstruction are determined according to the current airway geometric parameter fitting value and the airway geometric parameter normal value.
And in the sputum obstruction identification process, the system performs a forced oscillation test on the subject again during sputum accumulation detection, calculates a lung impedance curve and an optimal airway geometric parameter fitting value of the forced oscillation test, and compares the lung impedance curve and the airway geometric parameter value under normal conditions to complete the identification of the position and degree of the sputum obstruction. The method comprises the steps of inputting pressure and flow signals during sputum accumulation detection, calibrating the obtained normal airway geometric parameters, calculating an impedance curve and airway geometric parameter fitting value during sputum accumulation, comparing the impedance curve and airway geometric parameter fitting value with the normal value, and outputting the position and degree of sputum blockage.
In one possible implementation, if the root mean square error value is less than the sputum blockage threshold, it is determined that the subject is not experiencing sputum blockage.
The method comprises the steps of comparing an impedance curve measured for the second time with an impedance curve under normal conditions, calculating Root Mean Square Error (RMSE) of the impedance curve and the impedance curve under all frequencies, setting a threshold value for judging whether the change of the impedance curve is enough to indicate the occurrence of sputum obstruction, if the RMSE is smaller than the threshold value, judging that the sputum obstruction does not occur, the test subject may be in a normal state or the sputum obstruction degree is lighter and is insufficient to cause the significant change of the impedance curve, and if the RMSE is larger than the threshold value, judging that the sputum obstruction occurs, and further analyzing the position and the degree of the sputum obstruction. Positioning sputum obstruction, namely assuming that the sputum obstruction mainly changes a parameter r (airway radius) in a model, and other parameters (such as l and h) possibly have small influence or mainly consider the change of the radius in the scheme, taking r as a parameter to be optimized, and using a particle swarm optimization algorithm or other optimization algorithms to fit the optimal airway geometric parameters under the condition of the sputum obstruction. By comparing the radius r under normal conditions with the optimal radius r' under sputum obstruction conditions, changes in airway radius parameters due to sputum obstruction can be identified. From the location of the change in the radius parameter (i.e., which level or levels of airway radius has changed significantly), the location of the sputum obstruction can be inferred.
Further, as shown in FIG. 6, in the process of identifying the position and degree of sputum obstruction, calibrated model parameters r, l and h are obtained through impedance curves under normal conditions, wherein r, l and h respectively represent the radius, the length and the wall thickness of the airway from 0 level to 23 level under normal conditions;
;
wherein N is the total number of frequency points, AndRepresenting the respiratory resistance and respiratory reactance under normal conditions, respectively. If E is smaller than the threshold value, the sputum blockage is considered to be not generated, if E is larger than the threshold value, the sputum blockage is considered to be generated, further, if the sputum blockage only changes the parameter r in the model, r is taken as a parameter to be optimized, the step of the particle swarm optimization algorithm in the step S102 is used again to obtain an optimal parameter r '(namely, the radius of the model in fig. 6), and the parameter r and r' are compared, so that the parameter change of the airway radius caused by the sputum blockage can be obtained, the position of the sputum blockage can be further obtained, and accordingly a corresponding suggestion is provided for doctors.
Next, a sputum obstruction detection system based on a pulmonary binary tree model according to an embodiment of the present application will be described with reference to the accompanying drawings.
Fig. 7 is a block diagram of a sputum obstruction detection system based on a pulmonary binary tree model in accordance with an embodiment of the present application.
As shown in fig. 7, the sputum obstruction detection system based on the pulmonary binary tree model comprises a pulmonary impedance calculation module 100, a pulmonary model parameter calibration module 200 and a sputum obstruction identification module 300.
Specifically, the lung impedance calculation module 100 is configured to obtain a normal lung impedance curve of the subject under normal conditions of the lung;
the lung model parameter calibration module 200 is configured to establish a lung binary tree model, and perform parameter calibration on the lung binary tree model according to the normal lung impedance curve to obtain a normal value of the geometric parameter of the airway;
The sputum obstruction identification module 300 is configured to obtain a current lung impedance curve of the subject subjected to a forced oscillation test during sputum accumulation detection, and determine a position and a degree of sputum obstruction of the subject according to the current lung impedance curve, the normal lung impedance curve and the normal value of the airway geometric parameter.
Fig. 8 is a block diagram of a terminal according to an embodiment of the present application. The terminal may include:
memory 501, processor 502, and a computer program stored on memory 501 and executable on processor 502.
The processor 502 implements the sputum obstruction detection method based on the pulmonary binary tree model provided in the above embodiment when executing a program.
Further, the terminal further includes:
A communication interface 503 for communication between the memory 501 and the processor 502.
Memory 501 for storing a computer program executable on processor 502.
Memory 501 may comprise high-speed RAM memory and may also include non-volatile memory (non-volatilememory), such as at least one disk memory.
If the memory 501, the processor 502, and the communication interface 503 are implemented independently, the communication interface 503, the memory 501, and the processor 502 may be connected to each other via a bus and perform communication with each other. The bus may be an industry standard architecture (IndustryStandardArchitecture, abbreviated ISA) bus, a Peripheral Component Interconnect (PCI) bus, an extended industry standard architecture (ExtendedIndustryStandardArchitecture, abbreviated EIS) bus, or the like. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 8, but not only one bus or one type of bus.
Alternatively, 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 may perform communication with each other through internal interfaces.
The processor 502 may be a Central Processing Unit (CPU) or an application specific integrated circuit (ApplicationSpecificIntegratedCircuit ASIC) or one or more integrated circuits configured to implement embodiments of the present application.
The present embodiment also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the sputum obstruction detection method based on the pulmonary binary tree model as above.
An embodiment of the present application provides a computer program product, which comprises a computer program, wherein the computer program, when executed by a processor, implements a sputum obstruction detection method based on a pulmonary binary tree model according to any of the embodiments corresponding to fig. 1 of the present application.
It should be noted that the information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to user analysis data, user storage data, user display data, etc.) and signals related to the present invention are all information, data and signals authorized by the user or fully authorized by each party, and the collection, use and processing of related information, data and signals all comply with laws and regulations and standards of relevant countries and regions.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable storage medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable storage medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include an electrical connection (an electronic device) having one or more wires, a portable computer diskette (a magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable storage medium may even be paper or other suitable medium upon which the program is printed, as the program may be electronically captured, via optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware as in another embodiment, may be implemented using any one or combination of techniques known in the art, discrete logic circuits with logic gates for implementing logic functions on data signals, application specific integrated circuits with appropriate combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), etc.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
It is to be understood that the application is not limited in its application to the examples described above, but is capable of modification and variation in light of the above teachings by those skilled in the art, and that all such modifications and variations are intended to be included within the scope of the appended claims.
It should be noted that the above embodiments are merely for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that the technical solution described in the above embodiments may be modified or some or all of the technical features may be equivalently replaced, and these modifications or substitutions do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the embodiments of the present application.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510579459.XA CN120093273B (en) | 2025-05-07 | 2025-05-07 | Sputum obstruction detection method, system, terminal and medium based on lung binary tree model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510579459.XA CN120093273B (en) | 2025-05-07 | 2025-05-07 | Sputum obstruction detection method, system, terminal and medium based on lung binary tree model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120093273A CN120093273A (en) | 2025-06-06 |
| CN120093273B true CN120093273B (en) | 2025-09-02 |
Family
ID=95888551
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510579459.XA Active CN120093273B (en) | 2025-05-07 | 2025-05-07 | Sputum obstruction detection method, system, terminal and medium based on lung binary tree model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120093273B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3263028A1 (en) * | 2016-06-29 | 2018-01-03 | Vrije Universiteit Brussel | Improved methods for determining respiratory properties and system therefor |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5868866B2 (en) * | 2009-12-03 | 2016-02-24 | コーニンクレッカ フィリップス エヌ ヴェＫｏｎｉｎｋｌｉｊｋｅ Ｐｈｉｌｉｐｓ Ｎ．Ｖ． | Method of operating a device for estimating respiratory impedance and the device |
| US20180280646A1 (en) * | 2010-08-13 | 2018-10-04 | Respiratory Motion, Inc. | Respiratory volume monitor and ventilator |
| EP3073916A1 (en) * | 2013-11-26 | 2016-10-05 | Cardiac Pacemakers, Inc. | Detection of chronic obstructive pulmonary disease exacerbations from breathing patterns |
| US12303455B2 (en) * | 2020-08-03 | 2025-05-20 | Hill-Rom Services, Inc. | Therapeutic technique using electrical impedance spectroscopy |
-
2025
- 2025-05-07 CN CN202510579459.XA patent/CN120093273B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3263028A1 (en) * | 2016-06-29 | 2018-01-03 | Vrije Universiteit Brussel | Improved methods for determining respiratory properties and system therefor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120093273A (en) | 2025-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2536333B1 (en) | Nitric oxide measurement method and apparatus | |
| JP6564318B2 (en) | A system for evaluating real-time lung mechanics | |
| JP5647984B2 (en) | System and method for detecting deficiency in breathing of a subject | |
| US20190015614A1 (en) | Systems, devices, and methodologies to provide protective and personalized ventilation | |
| CN112842321B (en) | Pulmonary ventilation function detection method, equipment and medium based on flow-volume loop diagram | |
| US20210219908A1 (en) | Obstructive sleep apnea syndrome diagnosis method using machine learning | |
| CN105658141B (en) | Spirometer system and method for determining lung Functional Residual Capacity (FRC) with non-obstructing valves | |
| CN111110269A (en) | A rapid and intelligent diagnosis method for infant pneumonia based on a hybrid deep learning model | |
| CN116779166A (en) | Data processing method and device, health assessment method and device, electronic equipment and readable storage medium | |
| JP2017099916A (en) | Biological sound examination device and biological sound examination method | |
| CN118762851B (en) | An intelligent analysis method of medical records of pulmonary tuberculosis patients for early warning of hemoptysis | |
| CN120093273B (en) | Sputum obstruction detection method, system, terminal and medium based on lung binary tree model | |
| US20180325421A1 (en) | Method and device for measurement of exhaled respiratory gas temperature from specific regions of the airway | |
| CN114242242A (en) | Lung function measuring method based on human body morphological phenotype | |
| CN117457169B (en) | Pediatric postoperative health care management method and system | |
| CN113823413A (en) | Lung function small airway disease prediction system, method, medium and electronic device | |
| Verbraak et al. | Serial lung model for simulation and parameter estimation in body plethysmography | |
| CN115775629A (en) | Method for assessing PPCs risk based on sub-polar motion test before operation | |
| CN118401167A (en) | Device and method for determining respiratory infection from exhaled breath | |
| WO2022008577A1 (en) | Systems and methods system for assessing nasal pathologies of a subject | |
| CN109118522B (en) | Respiratory tract cilium movement characteristic analysis method and device | |
| CN119679395B (en) | Adenoid hypertrophy auxiliary detection system and method based on dynamic graph fusion | |
| CN113951867B (en) | Chronic obstructive pulmonary disease recognition device based on oral-nasal airflow signal | |
| CN114048844B (en) | D-CNN-based breathing machine false positive alarm identification method and system | |
| JPH07222732A (en) | Method and device for comprehensive evaluation of airway hyperresponsiveness and airway obstruction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |