Mode switching methods, controllers, airway clearance devices, storage media, and program products

Abstract

The mode switching method, controller, airway clearance device, storage medium, and program product provided in this application embodiment, after running for a preset time in airway oscillation mode or mechanical inhalation and exhalation mode, outputs oscillating airflow at different oscillation frequencies. For any oscillation frequency, it collects the user's response information to the oscillating airflow at that frequency. Based on the response information at each oscillation frequency, it determines the user's impedance parameter, which represents the obstruction status of the user's respiratory system. Based on the impedance parameter, it determines the operating mode for the next moment and executes the operating mode. By acquiring the user's response information under the oscillating airflow, it determines the impedance parameter representing the user's respiratory system obstruction status, thereby achieving automatic adjustment of the airway clearance method according to the user's real-time respiratory status to improve the sputum expectoration effect.

Description

Technical Field

[0001] This application relates to the field of airway clearance equipment technology, and in particular to a mode switching method, controller, airway clearance equipment, storage medium and program product. Background Technology

[0002] Airway clearance techniques are an important tool in the field of respiratory therapy. They aim to clear airway secretions and maintain airway patency through mechanical means, playing a vital role in clinical scenarios such as improving dyspnea symptoms and preventing respiratory infections.

[0003] Existing airway clearance techniques include various methods, broadly categorized into airway oscillation and mechanical inhalation / exhalation. Airway oscillation methods include: high-frequency chest wall oscillation (using chest wall oscillation to promote secretion removal from the airway wall), intra-airway oscillation ventilation (using pulsed airflow to generate intra-airway oscillation), and OLE (Oscillatory Low-Frequency Expiratory, combining continuous positive pressure with low-frequency oscillation to promote secretion liquefaction through intra-airway oscillation). Mechanical inhalation methods include: MIE (Mechanical Insufflation-Exsufflation), which simulates coughing by applying positive and negative pressure changes to the airway, increasing expiratory flow to expel secretions. Of these airway clearance techniques, only the MIE device is used to assist coughing and expel secretions from the main airway; the other devices are all designed to loosen and liquefy secretions in the peripheral small airways.

[0004] Most existing airway clearance devices are based on a single airway clearance technology, with a few combining mechanical inhalation and exhalation with airway oscillation. However, using these devices as two separate modes results in poor sputum expectoration. Summary of the Invention

[0005] The mode switching method, controller, airway clearance device, storage medium, and program product provided in this application embodiment are used to improve the sputum expectoration effect by switching between two modes.

[0006] In a first aspect, embodiments of this application provide a mode switching method, including:

[0007] After running for a preset time in airway oscillation mode or mechanical inhalation and exhalation mode, it outputs oscillating airflow at different oscillation frequencies;

[0008] For any given oscillation frequency, collect the user's response information to the oscillating airflow at that oscillation frequency;

[0009] Based on the response information at each oscillation frequency, the user's impedance parameters are determined; the impedance parameters are used to indicate the obstruction status of the user's respiratory system.

[0010] The operating mode for the next moment is determined based on the impedance parameters, and the operating mode is executed.

[0011] Optionally, determining the operating mode at the next moment based on the impedance parameters includes:

[0012] Based on the impedance parameters, determine the probability of obstruction in the user's respiratory system;

[0013] The operating mode for the next moment is determined based on the blocking probability.

[0014] Optionally, determining the probability of obstruction of the user's respiratory system based on the impedance parameter includes:

[0015] The impedance parameters are input into a logistic regression model to obtain the probability of obstruction in the user's respiratory system.

[0016] Optionally, the impedance parameters include a first set of impedance parameters and a second set of impedance parameters; the first set of impedance parameters is related to the viscous resistance at each oscillation frequency; the second set of impedance parameters is related to the respiratory reactance at each oscillation frequency; the impedance parameters are input into a logistic regression model to obtain the obstruction probability of the user's respiratory system, including:

[0017] By inputting at least some of the impedance parameters from the first set of impedance parameters and the second set of impedance parameters, as well as the viscous resistance and respiratory reactance at at least some oscillation frequencies, into a logistic regression model, the obstruction probability of the user's respiratory system can be obtained.

[0018] Optionally, determining the operating mode for the next moment based on the blocking probability includes:

[0019] When the obstruction probability is greater than or equal to the expectoration threshold, the mechanical inhalation and exhalation mode is determined as the operating mode for the next moment.

[0020] When the blocking probability is less than or equal to the normal threshold, the operation stops.

[0021] When the obstruction probability is greater than the normal threshold and less than the cough threshold, the airway oscillation mode is determined as the operating mode for the next moment.

[0022] Optionally, the response information includes: a time-domain pressure signal and a time-domain flow signal; based on the response information at each oscillation frequency, the impedance parameters of the user are determined, including:

[0023] For any oscillation frequency, the viscous resistance and respiratory reactance at the oscillation frequency are determined based on the corresponding time-domain pressure signal and the time-domain flow signal.

[0024] The impedance parameters are determined based on the viscous resistance and respiratory reactance at each oscillation frequency.

[0025] Optionally, based on the corresponding time-domain pressure signal and the time-domain flow signal, the viscous resistance and respiratory reactance at the oscillation frequency are determined, including:

[0026] The time-domain pressure signal is expanded using a Fourier series to obtain the first Fourier series coefficients;

[0027] The time-domain flow signal is expanded using a Fourier series to obtain the second Fourier series coefficients;

[0028] The pressure fundamental amplitude is determined based on the first Fourier series coefficient, and the flow fundamental amplitude is determined based on the second Fourier series coefficient.

[0029] The phase difference is determined based on the first Fourier series coefficients and the second Fourier series coefficients; the phase difference is the phase difference between the curve corresponding to the time-domain pressure signal and the curve corresponding to the time-domain flow rate signal.

[0030] Based on the pressure fundamental amplitude, the flow fundamental amplitude, and the phase difference, the viscous resistance and respiratory reactance at the oscillation frequency are determined.

[0031] Optionally, the impedance parameter is determined based on the viscous resistance and respiratory reactance at each oscillation frequency, including:

[0032] Linear fitting is performed on the viscous resistance at each oscillation frequency, and the corresponding fitting coefficients are determined as the first set of impedance parameters.

[0033] The respiratory reactance at each oscillation frequency is linearly fitted, and the corresponding fitting coefficients are determined as the second set of impedance parameters.

[0034] Secondly, embodiments of this application provide a mode switching device, including:

[0035] The output module is used to output oscillating airflow at different oscillation frequencies after running for a preset time in airway oscillation mode or mechanical inhalation and exhalation mode;

[0036] The acquisition module is used to acquire the user's response information to the oscillating airflow at any given oscillation frequency.

[0037] The determining module is used to determine the user's impedance parameters based on the response information at each oscillation frequency; the impedance parameters are used to represent the obstruction status of the user's respiratory system.

[0038] The processing module is used to determine the operating mode at the next moment based on the impedance parameters, and execute the operating mode.

[0039] Thirdly, embodiments of this application provide a controller, including: a memory and a processor;

[0040] The memory stores computer-executed instructions;

[0041] The processor executes computer execution instructions stored in the memory, causing the processor to perform various possible implementations of the first aspect described above.

[0042] Fourthly, embodiments of this application provide an airway clearance device, including a controller, sensor, and execution system as described in the third aspect;

[0043] The sensor is used to: collect user response information to the oscillating airflow at any given oscillating frequency;

[0044] The execution system is used to: switch modes under the control of the controller, or to control the airway clearance device to stop operating.

[0045] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement various possible implementations of the first aspect above.

[0046] In a sixth aspect, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements various possible implementations of the first aspect described above.

[0047] The mode switching method, controller, airway clearance device, storage medium, and program product provided in this application embodiment, after running for a preset time in airway oscillation mode or mechanical inhalation and exhalation mode, outputs oscillating airflow at different oscillation frequencies. For any oscillation frequency, it collects the user's response information to the oscillating airflow at that frequency. Based on the response information at each oscillation frequency, it determines the user's impedance parameter, which represents the obstruction status of the user's respiratory system. Based on the impedance parameter, it determines the operating mode for the next moment and executes the operating mode. By acquiring the user's response information under the oscillating airflow, it determines the impedance parameter representing the user's respiratory system obstruction status, thereby achieving automatic adjustment of the airway clearance method according to the user's real-time respiratory status to improve the sputum expectoration effect. Attached Figure Description

[0048] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0049] Figure 1 This application provides an illustration of the application scenario.

[0050] Figure 2 A flowchart illustrating a mode switching method provided in this application;

[0051] Figure 3 A schematic diagram of a time-domain pressure signal and a time-domain flow signal acquired according to this application;

[0052] Figure 4 A graph showing the viscous resistance and respiratory reactance of a user in the absence of obstruction or restriction, provided in this application;

[0053] Figure 5 A graph showing the viscous resistance and respiratory reactance of a user when there is obstruction or restriction in the peripheral small airways, provided in this application;

[0054] Figure 6 A schematic diagram of a deterministic logistic regression model provided in this application;

[0055] Figure 7 A schematic diagram of the structure of a mode switching device 70 provided in this application;

[0056] Figure 8 This is a schematic diagram of the structure of a controller provided in this application.

[0057] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0058] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0059] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0060] Existing airway clearance devices typically operate in a single mode to clear sputum. Even if an airway clearance device has two operating modes, the user usually selects the desired mode based on their operation. It cannot automatically adjust the operating mode according to the patient's real-time respiratory status, thus affecting the sputum clearance effect.

[0061] Optionally, the airway clearance device is connected to the user's face via tubing and a mask. The airflow generated by the airway clearance device is used to clear secretions from the user's peripheral small airways and main airways.

[0062] Figure 1 The application scenario diagram provided in this application is as follows: Figure 1 As shown, an airway clearance device can consist of a controller, a pressure sensor, a flow sensor, an oscillating reversing valve, and a blower mechanism.

[0063] Based on the above issues, the controller can determine the user's impedance parameters based on the response information collected by the pressure and flow sensors, thereby determining the degree of obstruction in the user's respiratory system. Different operating modes can be adopted when the degree of obstruction varies to promote sputum expectoration. After determining the operating mode, switching between modes can be achieved by controlling the reversing oscillating valve and the blower.

[0064] Figure 2 This is a flowchart illustrating a mode switching method provided in an embodiment of the present invention, applied to a controller in an airway clearance device. The method includes steps S201 to S204:

[0065] Step S201: After running for a preset time in airway oscillation mode or mechanical inhalation and exhalation mode, output oscillating airflow at different oscillation frequencies.

[0066] The initial operating mode of the airway clearance device can be either airway oscillation mode or mechanical inhalation and exhalation mode; this application does not make any specific limitation.

[0067] Optionally, the airway oscillation mode corresponds to the high-frequency chest wall oscillation method, the intra-airway oscillation ventilation method, or the OLE method. When the airway clearance device operates in airway oscillation mode, it is mainly used to loosen and liquefy secretions in the peripheral small airways.

[0068] Optionally, the mechanical inspiratory-expiratory mode corresponds to the MIE method. When the airway clearance device is operating in this mode, it is primarily used to assist coughing in order to expel secretions from the main airway.

[0069] Optionally, the airway clearance device can first operate in airway oscillation mode to expel secretions from the peripheral small airways into the main airway, and then operate in mechanical inspiratory and expiratory mode to expel secretions from the main airway.

[0070] For any operating mode, after the preset duration of operation in that mode, the user's breathing status can be detected to determine the operating mode for the next moment.

[0071] Optionally, when detecting a user's breathing status, an oscillating airflow at different oscillation frequencies can be output to determine the user's breathing status.

[0072] Optionally, when outputting oscillating airflow at different oscillation frequencies, oscillating airflow can be continuously output for a certain duration for any given oscillation frequency. For example, the oscillation frequency can range from 1Hz to 20Hz. Specifically, the controller can generate an oscillation excitation signal ranging from 1Hz to 20Hz to produce oscillating airflow. This application does not specifically limit the oscillation frequency.

[0073] Step S202: For any oscillation frequency, collect the user's response information to the oscillating airflow at the oscillation frequency.

[0074] Different users have different lung mechanics (such as airway resistance), so different users will respond differently to the same frequency of oscillating airflow.

[0075] For any oscillating airflow at any given frequency, the user can generate response information. This response information can be collected by sensors and analyzed to determine the user's breathing status.

[0076] Step S203: Determine the user's impedance parameters based on the response information at each oscillation frequency; the impedance parameters are used to represent the obstruction status of the user's respiratory system.

[0077] After obtaining the response information at various oscillation frequencies, the impedance parameter can be determined. This impedance parameter directly reflects the obstruction status of the user's respiratory system.

[0078] Optionally, by applying pressure oscillations of different amplitudes and frequencies to the respiratory system, oscillating airflows are generated. These oscillating airflows are superimposed on normal breathing. By measuring the respiratory system's response to these oscillating airflows, the total respiratory system impedance Zrs (Respiratory System Impedance) can be obtained. Zrs consists of viscous resistance Rrs and respiratory reactance Xrs. Based on the total respiratory system impedance at different frequencies, impedance parameters can be obtained.

[0079] Step S204: Determine the operating mode for the next moment based on the impedance parameters, and execute the operating mode.

[0080] After determining the impedance parameters, which can indicate the degree of obstruction in the user's respiratory system, the operating mode of the airway clearance device can be determined based on the obstruction status. Optionally, after running for a preset time based on the determined operating mode, the user's breathing status is detected again to determine the next operating mode, and this process is repeated until the user manually turns off the airway clearance device; or, the airway clearance device is automatically turned off when the shutdown conditions are met; or, the airway clearance device is turned off when it reaches its maximum operating time.

[0081] For example, when the obstruction is severe, it means that there is a lot of secretion in the main airway. Mechanical inhalation and exhalation can be used to expel the secretion from the main airway. When the obstruction is not severe, the secretion may still be in the peripheral small airways. In this case, airway oscillation can be used first to expel the secretion from the peripheral small airways into the main airway, and then mechanical inhalation and exhalation can be used to expel the secretion from the body, thereby improving the expectoration effect.

[0082] The mode switching method provided in this application involves running an airway oscillation mode or a mechanical inhalation and exhalation mode for a preset time, then outputting oscillating airflow at different oscillation frequencies. For any given oscillation frequency, the method collects the user's response information to the oscillating airflow at that frequency. Based on the response information at each oscillation frequency, the method determines the user's impedance parameter, which represents the obstruction status of the user's respiratory system. The method then determines the operating mode for the next moment based on the impedance parameter and executes the operating mode. By acquiring the user's response information under the oscillating airflow, the method determines the impedance parameter representing the obstruction status of the user's respiratory system, thereby automatically adjusting the airway clearance method according to the user's real-time respiratory status to improve the expectoration effect.

[0083] Optionally, the response information includes: a time-domain pressure signal and a time-domain flow signal; based on the response information at each oscillation frequency, the impedance parameters of the user are determined, including:

[0084] For any oscillation frequency, the viscous resistance and respiratory reactance at the oscillation frequency are determined based on the corresponding time-domain pressure signal and the time-domain flow signal.

[0085] The impedance parameters are determined based on the viscous resistance and respiratory reactance at each oscillation frequency.

[0086] Optionally, the acquired response information can be time-domain pressure signals and time-domain flow signals. The time-domain pressure signal can be acquired based on a pressure sensor, and the time-domain flow signal can be acquired based on a flow sensor. Specifically, the acquired time-domain pressure and time-domain flow signals represent the pressure and flow rate in the user's airway.

[0087] Optionally, the pressure sensor can be a MEMS (Micro-Electro-Mechanical Systems) gas pressure sensor. The flow sensor can be a MEMS (Micro-Electro-Mechanical Systems) gas flow meter. For example, a MEMS gas pressure sensor is used to acquire the pressure of oscillating airflow at a sampling rate of 1 kHz. For example, a MEMS gas flow meter is used to monitor instantaneous peak expiratory flow rate with a range of 0-600 L / min. Peak expiratory flow rate refers to the highest instantaneous flow rate reached by the airflow during forced exhalation; it is a key indicator of the respiratory system, especially airway patency.

[0088] For a given oscillation frequency, after acquiring the time-domain pressure signal and the time-domain flow signal, the time-domain pressure signal and the time-domain flow signal can be analyzed to determine the viscous resistance and respiratory reactance at that oscillation frequency.

[0089] Once the viscous resistance and respiratory reactance at each oscillation frequency are determined, the impedance parameters can be determined. Optionally, the impedance parameters can represent the variation characteristics of the viscous resistance at each oscillation frequency, as well as the variation characteristics of the respiratory reactance at each oscillation frequency.

[0090] Viscous resistance and respiratory reactance can reflect the mechanical properties of the respiratory system.

[0091] For example, viscous resistance can reflect the patency of the main airway, respiratory reactance can reflect the function of the small airways, and the resilience of the respiratory system.

[0092] By determining viscous resistance and respiratory reactance based on response information, impedance parameters can be effectively calculated to accurately determine the operating mode of the airway clearance device.

[0093] Optionally, based on the corresponding time-domain pressure signal and the time-domain flow signal, the viscous resistance and respiratory reactance at the oscillation frequency are determined, including:

[0094] The time-domain pressure signal is expanded using a Fourier series to obtain the first Fourier series coefficients;

[0095] The time-domain flow signal is expanded using a Fourier series to obtain the second Fourier series coefficients;

[0096] The pressure fundamental amplitude is determined based on the first Fourier series coefficient, and the flow fundamental amplitude is determined based on the second Fourier series coefficient.

[0097] The phase difference is determined based on the first Fourier series coefficients and the second Fourier series coefficients; the phase difference is the phase difference between the curve corresponding to the time-domain pressure signal and the curve corresponding to the time-domain flow rate signal.

[0098] Based on the pressure fundamental amplitude, the flow fundamental amplitude, and the phase difference, the viscous resistance and respiratory reactance at the oscillation frequency are determined.

[0099] The total respiratory system impedance Zrs can be obtained by linear approximation of the pressure-flow rate changes during the oscillatory flow into and out of the lungs, i.e.:

[0100]

[0101] The total impedance vector of the respiratory system can also be represented in polar coordinates by the magnitude and phase angle of the total impedance of the respiratory system:

[0102]

[0103] Among them, angular frequency , It is a function of pressure and oscillation frequency. It is a function of flow rate and oscillation frequency. For viscous resistance, For respiratory reactance, imaginary unit The phase angle is the phase difference between the curve corresponding to the time-domain pressure signal and the curve corresponding to the time-domain flow signal.

[0104] Because the sensor collects a time-domain pressure signal at an oscillation frequency. and time-domain flow signal However, when calculating viscous resistance and respiratory reactance, frequency domain information of the time-domain pressure signal and the time-domain flow signal with one oscillation period is required. Since both signals are periodic signals, and the time-domain flow signal is the response caused by the excitation of the time-domain pressure signal with a known frequency, Fourier series expansions can be performed on the time-domain pressure signal and the time-domain flow signal respectively, and their fundamental components can be used as approximate estimates to simplify the calculation, i.e.:

[0105]

[0106]

[0107] because and Since it was measured by a sensor, the coefficients of the first Fourier series can be calculated. , And, the coefficients of the second Fourier series , :

[0108]

[0109]

[0110]

[0111]

[0112] Within this oscillation cycle, the fundamental amplitudes of the pressure wave and the fundamental amplitudes of the flow wave are respectively:

[0113]

[0114]

[0115] Then, within this oscillation cycle, the phases of pressure and flow rate are respectively:

[0116]

[0117]

[0118] The phase difference between pressure and flow rate within this oscillation cycle is:

[0119]

[0120] The magnitude of the total impedance of the respiratory system can be obtained from the formula for calculating the total impedance of the respiratory system:

[0121]

[0122] Therefore, the viscous resistance under this oscillation period can be calculated. and respiratory impedance ,Right now:

[0123]

[0124]

[0125] Figure 3This application provides a schematic diagram of a time-domain pressure signal and a time-domain flow signal that have been acquired. The diagram shows the pressure fundamental amplitude, the flow fundamental amplitude, and the phase difference.

[0126] Through the above calculation process, the viscous resistance and respiratory reactance at each oscillation frequency can be accurately calculated.

[0127] Optionally, the impedance parameter is determined based on the viscous resistance and respiratory reactance at each oscillation frequency, including:

[0128] Linear fitting is performed on the viscous resistance at each oscillation frequency, and the corresponding fitting coefficients are determined as the first set of impedance parameters.

[0129] The respiratory reactance at each oscillation frequency is linearly fitted, and the corresponding fitting coefficients are determined as the second set of impedance parameters.

[0130] After determining the viscous resistance at each oscillation frequency, linear fitting can be performed to obtain the fitting coefficients, which are the first set of impedance parameters.

[0131] After determining the respiratory reactance at each frequency, linear fitting can be performed to obtain the fitting coefficients, which are the second set of impedance parameters.

[0132] Optionally, the least squares method can be used for linear fitting.

[0133] For example, the user's viscous resistance can be fitted using the least squares method. Relationship with oscillation frequency And, the user's respiratory impedance Relationship with oscillation frequency :

[0134]

[0135]

[0136] in, , for The fitting coefficients, which are the first set of impedance parameters; , for The fitting coefficients are the second set of impedance parameters.

[0137] Optionally, determining the operating mode at the next moment based on the impedance parameters includes:

[0138] Based on the impedance parameters, determine the probability of obstruction in the user's respiratory system;

[0139] The operating mode for the next moment is determined based on the blocking probability.

[0140] After determining the impedance parameters, the probability of obstruction of the respiratory system can be further determined. The obstruction probability can intuitively reflect the state of the user's respiratory system, thereby enabling accurate determination of the operating mode at the next moment.

[0141] Optionally, a higher probability of obstruction indicates a greater likelihood of main airway obstruction for the user; conversely, a lower probability of obstruction indicates a lower likelihood of main airway obstruction for the user. Based on the obstruction probability, the operating mode for the next moment can be determined.

[0142] Optionally, determining the probability of obstruction of the user's respiratory system based on the impedance parameter includes:

[0143] The impedance parameters are input into a logistic regression model to obtain the probability of obstruction in the user's respiratory system.

[0144] The probability of obstruction can be determined based on a neural network model. Alternatively, a pre-trained logistic regression model can be used, deployed on the airway clearance device, and the obstruction probability can be determined based on the pre-trained logistic regression model after the user's impedance parameters are determined in real time.

[0145] By inputting impedance parameters into a logistic regression model, accurate prediction of the blockage probability can be achieved.

[0146] Optionally, the impedance parameters include a first set of impedance parameters and a second set of impedance parameters; the first set of impedance parameters is related to the viscous resistance at each oscillation frequency; the second set of impedance parameters is related to the respiratory reactance at each oscillation frequency; the impedance parameters are input into a logistic regression model to obtain the obstruction probability of the user's respiratory system, including:

[0147] By inputting at least some of the impedance parameters from the first set of impedance parameters and the second set of impedance parameters, as well as the viscous resistance and respiratory reactance at at least some oscillation frequencies, into a logistic regression model, the obstruction probability of the user's respiratory system can be obtained.

[0148] Optionally, the first set of impedance parameters can be... , Second set of impedance parameters , The at least partial impedance parameters, and the viscous resistance and respiratory reactance input logistic regression model at at least partial oscillation frequencies.

[0149] Optional, typically viscous resistance at an oscillation frequency of 5 Hz. This can reflect the total viscous resistance of the respiratory system; while the viscous resistance at an oscillation frequency of 20Hz... It can reflect the resistance of the main airway (central airway or central airway).

[0150] Figure 4 This application provides a graph showing the viscous resistance and respiratory reactance of a user in the absence of obstruction or restriction. The horizontal axis represents the oscillation frequency, and the vertical axis represents the viscous resistance. or respiratory reactance Normal viscous resistance The viscous resistance remains largely unchanged with the oscillation frequency, meaning it is frequency-independent. This also implies that the resistance in the main and small airways of healthy individuals is very low, resulting in a low fitting coefficient. Approaching 0.

[0151] When main airway obstruction occurs, viscous resistance Viscous resistance increases at all oscillation frequencies, and when peripheral small airway obstruction occurs, the viscous resistance at an oscillation frequency of 5 Hz increases. It will increase, while the viscous resistance at an oscillation frequency of 20Hz No significant increase.

[0152] Figure 5 This application provides a graph showing the viscous resistance and respiratory reactance of a user when there is obstruction or restriction in the peripheral small airways. The horizontal axis represents the oscillation frequency, and the vertical axis represents the viscous resistance. or respiratory reactance . Figure 5 Viscous resistance at an oscillation frequency of 5Hz Greater than Figure 4 Viscous resistance at an oscillation frequency of 5Hz .

[0153] Typical respiratory reactance at an oscillation frequency of 5 Hz It can reflect the total elastic resistance of the respiratory system; while the respiratory reactance at an oscillation frequency of 20Hz It can reflect the inertial resistance of the main airway. Normally, respiratory reactance in a healthy person... The respiratory reactance increases with increasing frequency, showing a positive dependence. When obstruction occurs, the respiratory reactance... There is a decrease at all frequencies.

[0154] Based on the above analysis, we can (Viscous resistance at an oscillation frequency of 5Hz) (Viscous resistance at an oscillation frequency of 20Hz) (Respiratory reactance at an oscillation frequency of 5Hz) , , These six dimensions of data serve as input to the logistic regression model, and the output of the logistic regression model is determined as the probability of respiratory obstruction.

[0155] Figure 6 This application provides a schematic diagram of a logistic regression model. An input feature vector is determined and fed into the logistic regression model to obtain predicted values. The model is then trained based on these predicted values ​​to update its parameters. After a preset number of training iterations, the model is validated. If validation is successful, the model is deployed. When detecting a user's breathing state, the current input feature vector can be determined, and based on the deployed logistic regression model, the probability of obstruction in the user's respiratory system can be output.

[0156] Optionally, the logistic regression model can be pre-trained, as follows:

[0157] First, oscillating airflows with different oscillation frequencies are generated to sample response information. The response information is then filtered, and the collected data is temporarily stored in the controller.

[0158] The collected data is processed to obtain the data in the above six dimensions, and the input feature vector is then obtained. Meanwhile, these sample data are labeled, and these sample sets are divided into training sets and test sets. The data in the training set is used to train the model.

[0159] Optionally, the output of the logistic regression model is:

[0160]

[0161] in, For the sigmoid function, , These are the parameters of the model.

[0162] The loss function can be expressed as:

[0163]

[0164] in, For the number of samples, Is the logistic regression model for the first The predicted value for each sample.

[0165] Using gradient descent through continuous iteration and The values ​​of the parameters make the loss function Minimize, and ultimately a set of optimal solutions can be found. and Parameters. The trained logistic regression model is validated using data from the test set. If the accuracy exceeds a certain value, the trained logistic regression model is considered to be effective and can be deployed; otherwise, more data needs to be collected for training. This logistic regression model can predict the probability of respiratory obstruction.

[0166] By inputting some impedance parameters from two sets of impedance parameters, along with viscous resistance and respiratory reactance at at least some oscillation frequencies, into a logistic regression model, accurate prediction of the probability of obstruction can be achieved.

[0167] Optionally, determining the operating mode for the next moment based on the blocking probability includes:

[0168] When the obstruction probability is greater than or equal to the expectoration threshold, the mechanical inhalation and exhalation mode is determined as the operating mode for the next moment.

[0169] When the blocking probability is less than or equal to the normal threshold, the operation stops.

[0170] When the obstruction probability is greater than the normal threshold and less than the cough threshold, the airway oscillation mode is determined as the operating mode for the next moment.

[0171] Once the obstruction probability is determined, the operating mode for the next moment can be determined based on this probability. Optionally, a cough threshold and a normal threshold can be set first. When the obstruction probability is greater than or equal to the cough threshold, it indicates that the main airway secretions have reached a certain amount, and the sputum can be expelled through coughing. When the obstruction probability is less than or equal to the normal threshold, it indicates that the main airway secretions are less, the respiratory system is relatively smooth, there is less sputum in the airways, and the airway clearance device does not need to operate.

[0172] Therefore, after obtaining the obstruction probability, it is compared with the expectoration threshold and the normal threshold. When the obstruction probability is greater than or equal to the expectoration threshold, it indicates that there is a lot of sputum in the main airway, and a mechanical inspiratory-expiratory mode can be used to promote the expectoration of sputum in the main airway. When the obstruction probability is less than or equal to the normal threshold, the airway clearance device can be stopped. When the obstruction probability is between the normal threshold and the expectoration threshold, an airway oscillation mode can be used to expel secretions from the peripheral small airways into the main airway, thereby allowing the sputum in the main airway to be expelled based on the mechanical inspiratory-expiratory mode.

[0173] By determining the operating mode in the above manner, the operating mode can be dynamically adjusted according to the user's breathing state, so as to automatically select the operating mode corresponding to the user's breathing state and improve the sputum expectoration effect.

[0174] In the user's clinical trials, CT (Computed Tomography) imaging of treated patients provided a direct visual representation of their respiratory obstruction. Based on this imaging validation, the accuracy of the system's respiratory obstruction probability was determined, and the expectoration threshold and normal threshold were identified. Since imaging examinations are not real-time and involve ionizing radiation, the solution provided in this application allows for timely switching, ensuring both accuracy and safety.

[0175] In the clinical trial, 100 users were randomly divided into an observation group and a control group, with 50 patients in each group. The control group received conventional MIE (mechanical inhalation and exhalation) treatment, while the observation group received the method of dynamic triggering mode switching based on airway resistance as described in this application. The sputum volume and respiratory function data (FEV1, FEV1 / FVC) (volume of air exhaled in the first second of maximal exhalation and volume of air exhaled in the first second of maximal exhalation / forced vital capacity) were compared between the two groups at 3 and 5 days of treatment. The table below shows the results for both groups. As can be seen from the table, at both 3 and 5 days of treatment, the sputum volume in the observation group was greater than that in the control group.

[0176]

[0177] When restrictive or obstructive ventilatory dysfunction occurs, FEV1 / FVC(%) and FEV1 will decrease significantly. Typically, FEV1 / FVC(%) will decrease to below 70%. FEV1 reflects airway resistance and the ability of the lungs to rapidly empty. The higher the value, the better the lung function. Experimental data show that the protocol proposed in this application is superior to the conventional protocol.

[0178] This application provides an airway clearance device that dynamically triggers mode switching based on a machine learning logistic regression binary classification model, through real-time airway impedance and respiratory data monitoring. The airway clearance device includes sensors, a controller, and an execution system. The device is connected to the user's face via tubing and a mask, and the airflow generated by the device clears secretions from the user's peripheral airways (small airways) and main airways (large airways).

[0179] Figure 7 This application provides a schematic diagram of the structure of a mode switching device 70, which includes:

[0180] The output module 701 is used to output oscillating airflow at different oscillation frequencies after running for a preset time in airway oscillation mode or mechanical inhalation and exhalation mode.

[0181] The acquisition module 702 is used to acquire the user's response information to the oscillating airflow at any given oscillating frequency.

[0182] The determining module 703 is used to determine the user's impedance parameters based on the response information at each oscillation frequency; the impedance parameters are used to represent the obstruction status of the user's respiratory system.

[0183] The processing module 704 is used to determine the operating mode at the next moment based on the impedance parameters, and to execute the operating mode.

[0184] Optionally, when determining the operating mode for the next moment based on the impedance parameters, the processing module 704 is specifically used for:

[0185] Based on the impedance parameters, determine the probability of obstruction in the user's respiratory system;

[0186] The operating mode for the next moment is determined based on the blocking probability.

[0187] Optionally, when determining the probability of obstruction of the user's respiratory system based on the impedance parameters, the processing module 704 is specifically used for:

[0188] The impedance parameters are input into a logistic regression model to obtain the probability of obstruction in the user's respiratory system.

[0189] Optionally, the impedance parameters include a first set of impedance parameters and a second set of impedance parameters; the first set of impedance parameters is related to the viscous resistance at each oscillation frequency; the second set of impedance parameters is related to the respiratory reactance at each oscillation frequency; when the processing module 704 inputs the impedance parameters into the logistic regression model to obtain the obstruction probability of the user's respiratory system, it is specifically used for:

[0190] By inputting at least some of the impedance parameters from the first set of impedance parameters and the second set of impedance parameters, as well as the viscous resistance and respiratory reactance at at least some oscillation frequencies, into a logistic regression model, the obstruction probability of the user's respiratory system can be obtained.

[0191] Optionally, when determining the operating mode for the next moment based on the blocking probability, the processing module 704 is specifically used for:

[0192] When the obstruction probability is greater than or equal to the expectoration threshold, the mechanical inhalation and exhalation mode is determined as the operating mode for the next moment.

[0193] When the blocking probability is less than or equal to the normal threshold, the operation stops.

[0194] When the obstruction probability is greater than the normal threshold and less than the cough threshold, the airway oscillation mode is determined as the operating mode for the next moment.

[0195] Optionally, the response information includes: a time-domain pressure signal and a time-domain flow signal; when determining the user's impedance parameters based on the response information at each oscillation frequency, the determining module 703 is specifically used for:

[0196] For any oscillation frequency, the viscous resistance and respiratory reactance at the oscillation frequency are determined based on the corresponding time-domain pressure signal and the time-domain flow signal.

[0197] The impedance parameters are determined based on the viscous resistance and respiratory reactance at each oscillation frequency.

[0198] Optionally, when determining the viscous resistance and respiratory reactance at the oscillation frequency based on the corresponding time-domain pressure signal and the time-domain flow signal, the determining module 703 is specifically used for:

[0199] The time-domain pressure signal is expanded using a Fourier series to obtain the first Fourier series coefficients;

[0200] The time-domain flow signal is expanded using a Fourier series to obtain the second Fourier series coefficients;

[0201] The pressure fundamental amplitude is determined based on the first Fourier series coefficient, and the flow fundamental amplitude is determined based on the second Fourier series coefficient.

[0202] The phase difference is determined based on the first Fourier series coefficients and the second Fourier series coefficients; the phase difference is the phase difference between the curve corresponding to the time-domain pressure signal and the curve corresponding to the time-domain flow rate signal.

[0203] Based on the pressure fundamental amplitude, the flow fundamental amplitude, and the phase difference, the viscous resistance and respiratory reactance at the oscillation frequency are determined.

[0204] Optionally, when determining the impedance parameter based on the viscous resistance and respiratory reactance at each oscillation frequency, the determining module 703 is specifically used for:

[0205] Linear fitting is performed on the viscous resistance at each oscillation frequency, and the corresponding fitting coefficients are determined as the first set of impedance parameters.

[0206] The respiratory reactance at each oscillation frequency is linearly fitted, and the corresponding fitting coefficients are determined as the second set of impedance parameters.

[0207] The mode switching device 70 provided in this embodiment of the invention can achieve the above-mentioned... Figure 2 The mode switching shown is implemented in a similar way and with similar technical effects, so it will not be described in detail here.

[0208] Figure 8This is a schematic diagram of the controller provided in this application. Figure 8 As shown, the controller 80 provided in this embodiment includes at least one processor 801 and a memory 802. Optionally, the controller 80 further includes a communication component 803. The processor 801, memory 802, and communication component 803 are connected via a bus 804.

[0209] In a specific implementation, at least one processor 801 executes computer execution instructions stored in memory 802, causing at least one processor 801 to perform the above-described method.

[0210] The specific implementation process of processor 801 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0211] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0212] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0213] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0214] This application also provides an airway clearance device, including a controller, sensor, and execution system as described in the foregoing embodiments;

[0215] The sensor is used to: collect user response information to the oscillating airflow at any given oscillating frequency;

[0216] The execution system is used to: switch modes under the control of the controller, or to control the airway clearance device to stop operating.

[0217] Optionally, the actuation system may include a blower and an oscillating directional valve.

[0218] Optionally, the airway clearance device can be a cough device.

[0219] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0220] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0221] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0222] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0223] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0224] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0225] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0226] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0227] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0228] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A mode switching method, characterized in that, include: After running for a preset time in airway oscillation mode or mechanical inhalation and exhalation mode, it outputs oscillating airflow at different oscillation frequencies; For any given oscillation frequency, collect the user's response information to the oscillating airflow at that oscillation frequency; Based on the response information at each oscillation frequency, the user's impedance parameters are determined; the impedance parameters are used to indicate the obstruction status of the user's respiratory system. The operating mode for the next moment is determined based on the impedance parameters, and the operating mode is executed.

2. The method according to claim 1, characterized in that, Determining the operating mode at the next moment based on the impedance parameters includes: Based on the impedance parameters, determine the probability of obstruction in the user's respiratory system; The operating mode for the next moment is determined based on the blocking probability.

3. The method according to claim 2, characterized in that, Determining the probability of airway obstruction in the user based on the impedance parameters includes: The impedance parameters are input into a logistic regression model to obtain the probability of obstruction in the user's respiratory system.

4. The method according to claim 3, characterized in that, The impedance parameters include a first set of impedance parameters and a second set of impedance parameters; the first set of impedance parameters is related to the viscous resistance at each oscillation frequency; the second set of impedance parameters is related to the respiratory reactance at each oscillation frequency. The impedance parameters are input into a logistic regression model to obtain the probability of obstruction in the user's respiratory system, including: By inputting at least some of the impedance parameters from the first set of impedance parameters and the second set of impedance parameters, as well as the viscous resistance and respiratory reactance at at least some oscillation frequencies, into a logistic regression model, the obstruction probability of the user's respiratory system can be obtained.

5. The method according to claim 2, characterized in that, Determining the operating mode for the next moment based on the blocking probability includes: When the obstruction probability is greater than or equal to the expectoration threshold, the mechanical inhalation and exhalation mode is determined as the operating mode for the next moment. When the blocking probability is less than or equal to the normal threshold, the operation stops. When the obstruction probability is greater than the normal threshold and less than the cough threshold, the airway oscillation mode is determined as the operating mode for the next moment.

6. The method according to claim 1, characterized in that, The response information includes: a time-domain pressure signal and a time-domain flow signal; based on the response information at each oscillation frequency, the user's impedance parameters are determined, including: For any oscillation frequency, the viscous resistance and respiratory reactance at the oscillation frequency are determined based on the corresponding time-domain pressure signal and the time-domain flow signal. The impedance parameters are determined based on the viscous resistance and respiratory reactance at each oscillation frequency.

7. The method according to claim 6, characterized in that, Based on the corresponding time-domain pressure signal and time-domain flow signal, determine the viscous resistance and respiratory reactance at the oscillation frequency, including: The time-domain pressure signal is expanded using a Fourier series to obtain the first Fourier series coefficients; The time-domain flow signal is expanded using a Fourier series to obtain the second Fourier series coefficients; The pressure fundamental amplitude is determined based on the first Fourier series coefficient, and the flow fundamental amplitude is determined based on the second Fourier series coefficient. The phase difference is determined based on the first Fourier series coefficients and the second Fourier series coefficients; the phase difference is the phase difference between the curve corresponding to the time-domain pressure signal and the curve corresponding to the time-domain flow rate signal. Based on the pressure fundamental amplitude, the flow fundamental amplitude, and the phase difference, the viscous resistance and respiratory reactance at the oscillation frequency are determined.

8. The method according to claim 6, characterized in that, The impedance parameters are determined based on the viscous resistance and respiratory reactance at each oscillation frequency, including: Linear fitting is performed on the viscous resistance at each oscillation frequency, and the corresponding fitting coefficients are determined as the first set of impedance parameters. The respiratory reactance at each oscillation frequency is linearly fitted, and the corresponding fitting coefficients are determined as the second set of impedance parameters.

9. A mode switching device, characterized in that, include: The output module is used to output oscillating airflow at different oscillation frequencies after running for a preset time in airway oscillation mode or mechanical inhalation and exhalation mode; The acquisition module is used to acquire the user's response information to the oscillating airflow at any given oscillation frequency. The determining module is used to determine the user's impedance parameters based on the response information at each oscillation frequency; the impedance parameters are used to represent the obstruction status of the user's respiratory system. The processing module is used to determine the operating mode at the next moment based on the impedance parameters, and execute the operating mode.

10. A controller, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-8.

11. An airway clearance device, characterized in that, Includes the controller, sensor, and execution system as described in claim 10; The sensor is used to: collect user response information to the oscillating airflow at any given oscillating frequency; The execution system is used to: switch modes under the control of the controller, or to control the airway clearance device to stop operating.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-8.

13. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-8.

Images