Method and device for measuring lung function index, electronic device and storage medium

Abstract

The present invention discloses a method for measuring a lung function index and a device, an electronic device and a storage medium, wherein the method comprises: based on a preset radar device, collecting echo data when a target user performs a breath test in a specified manner, processing the echo data to obtain a breathing signal, calculating a first lung function index based on the breathing signal, and correcting the first lung function index based on a preset correction function to obtain a corrected first lung function index. The present invention solves the technical problem that the user's lung function index can only be measured in a contact manner in the related art, resulting in inconvenience in use.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method for measuring lung function indicators and a device thereof, an electronic device and a storage medium. Background Art

[0002] Pulmonary function test is one of the important tests for evaluating chest and lung diseases and respiratory physiology. It has important guiding significance for the examination of lung and airway lesions and the location of lesions, identification of the causes of dyspnea, assessment of disease severity, prognosis and tolerance to surgery. An important indicator in pulmonary function test is the percentage of forced expiratory volume in one second (FEV1) to forced vital capacity (FVC), referred to as the one-second rate (FEV1 / FVC). This indicator is mainly used to diagnose chronic obstructive pulmonary disease.

[0003] In the related art, most of the pulmonary function testers are used to detect the lung function of the user. However, the pulmonary function testers are all contact type, requiring the subject to blow close to the mouthpiece for measurement, which is very inconvenient to use.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method for measuring lung function indicators and a device thereof, an electronic device and a storage medium, so as to at least solve the technical problem in the related art that the lung function indicators of users can only be measured in a contact manner, resulting in inconvenience in use.

[0006] According to one aspect of an embodiment of the present invention, a method for measuring a lung function index is provided, comprising: based on a preset radar device, collecting echo data when a target user performs a breath test in a specified manner, wherein the preset radar device does not need to contact the target user when collecting the echo data; processing the echo data to obtain a breathing signal; based on the breathing signal, calculating a first lung function index; based on a preset correction function, correcting the first lung function index to obtain a corrected first lung function index.

[0007] Optionally, based on a preset radar device, the step of collecting echo data of a target user performing a breath test in a specified manner includes: upon confirming that the preset radar device is located at a preset distance value from the target user and is flush with the chest of the target user, issuing a normal breathing instruction; upon the target user's normal breathing reaches a preset time limit, issuing a deep inhalation followed by a quick exhalation instruction, and collecting radar echo data of the target user, wherein the radar echo data is at least data lasting for a first preset time period; and characterizing the radar echo data as the echo data.

[0008] Optionally, the step of processing the echo data to obtain a breathing signal includes: transforming the echo data into a range-dimensional complex signal; determining a range gate where the chest of the target user is located in the range-dimensional complex signal, wherein the range gate represents the distance range of the user's chest relative to the radar; extracting the original phase signal based on the range gate; performing a preset unwrapping operation on the original phase signal to obtain an unwrapped phase signal; and characterizing the phase signal as the breathing signal.

[0009] Optionally, the step of calculating the first lung function index based on the breathing signal includes: smoothing the breathing signal to obtain a target breathing signal, and determining the exhalation starting point based on the target breathing signal; determining the maximum value point of the target breathing signal within a second preset time period based on the exhalation starting point; calculating a first relative value based on the exhalation starting point and the maximum value point; determining all sampling points within a third preset time period in the target breathing signal based on the exhalation starting point; calculating the amplitude difference between each sampling point among all the sampling points and the sampling point delayed by a preset time to obtain an amplitude difference set; determining the maximum amplitude difference based on the amplitude difference set; characterizing the maximum amplitude difference as a second relative value; and calculating the first lung function index based on the first relative value and the second relative value.

[0010] Optionally, the step of determining the exhalation starting point based on the target breathing signal includes: determining all minimum points within a fourth preset time period based on the target breathing signal; determining all maximum points in the target breathing signal; calculating the amplitude difference of the signal amplitude between each minimum point among all the minimum points and its subsequent nearest maximum point to obtain an amplitude difference set; based on the amplitude difference set, determining the target minimum point indicated by the maximum amplitude difference; and characterizing the target minimum point as the exhalation starting point.

[0011] Optionally, before correcting the first pulmonary function index based on a preset correction function to obtain a corrected first pulmonary function index, it also includes: calculating the first pulmonary function index and the second pulmonary function index based on historical samples within a fifth preset time period; performing linear fitting on the first pulmonary function index and the second pulmonary function index to obtain a linear fitting expression; calculating the linear fit between the first pulmonary function index and the second pulmonary function index; and establishing the preset correction function based on the linear fitting expression and the linear fit.

[0012] Optionally, after correcting the first pulmonary function index based on a preset correction function to obtain a corrected first pulmonary function index, it also includes: characterizing the comparison result of the second pulmonary function index with a preset threshold as a true result; characterizing the comparison result of the first pulmonary function index with the preset threshold as a predicted result; based on the true result and the predicted result, calculating the index value of the performance index for pulmonary function determination using the corrected first pulmonary function index, wherein the performance index includes at least: accuracy, sensitivity, and specificity.

[0013] Optionally, the preset radar device is a millimeter wave radar.

[0014] According to another aspect of an embodiment of the present invention, a device for measuring a lung function index is also provided, including: an acquisition unit, for acquiring, based on a preset radar device, echo data when a target user performs a breath test in a specified manner, wherein the preset radar device does not need to contact the target user when acquiring the echo data; a processing unit, for processing the echo data to obtain a breathing signal; a calculation unit, for calculating a first lung function index based on the breathing signal; and a correction unit, for correcting the first lung function index based on a preset correction function to obtain a corrected first lung function index.

[0015] Optionally, the acquisition unit includes: a first issuing module, used to issue a normal breathing instruction when it is confirmed that the preset radar device is located at a preset distance value from the target user and is flush with the chest of the target user; a second issuing module, used to issue a deep inhalation followed by a quick exhalation instruction when the normal breathing of the target user reaches a preset time limit, and collect radar echo data of the target user, wherein the radar echo data is at least data lasting for a first preset time period; a first characterization module, used to characterize the radar echo data as the echo data.

[0016] Optionally, the processing unit includes: a first transformation module, used to transform the echo data into a range-dimensional complex signal; a first determination module, used to determine the range gate where the chest of the target user in the range-dimensional complex signal is located, wherein the range gate represents the distance range of the user's chest relative to the radar; a first extraction module, used to extract the original phase signal based on the range gate; a first unwrapping module, used to perform a preset unwrapping operation on the original phase signal to obtain the unwrapped phase signal; and a second characterization module, used to characterize the phase signal as the breathing signal.

[0017] Optionally, the calculation unit includes: a second determination module, used to smooth the respiratory signal to obtain a target respiratory signal, and determine the exhalation starting point based on the target respiratory signal; a third determination module, used to determine the maximum value point of the target respiratory signal within a second preset time period based on the exhalation starting point; a first calculation module, used to calculate a first relative value based on the exhalation starting point and the maximum value point; a fourth determination module, used to determine all sampling points within a third preset time period in the target respiratory signal based on the exhalation starting point; a second calculation module, used to calculate the amplitude difference between each sampling point among all the sampling points and the sampling point after it is delayed by a preset time to obtain an amplitude difference set; a fifth determination module, used to determine the maximum amplitude difference based on the amplitude difference set; a third characterization module, used to characterize the maximum amplitude difference as a second relative value; and a third calculation module, used to calculate the first lung function index based on the first relative value and the second relative value.

[0018] Optionally, the second determination module includes: a first determination submodule, used to determine all minimum points within a fourth preset time period based on the target breathing signal; a second determination submodule, used to determine all maximum points in the target breathing signal; a first calculation submodule, used to calculate the amplitude difference of the signal amplitude between each minimum point among all the minimum points and its subsequent nearest maximum point to obtain an amplitude difference set; a third determination submodule, used to determine the target minimum point indicated by the maximum amplitude difference based on the amplitude difference set; and a first characterization submodule, used to characterize the target minimum point as the exhalation start point.

[0019] Optionally, the measuring device also includes: a fourth calculation module, used to calculate the first pulmonary function index and the second pulmonary function index based on historical samples within a fifth preset time period before correcting the first pulmonary function index based on a preset correction function to obtain the corrected first pulmonary function index; a first fitting module, used to perform linear fitting on the first pulmonary function index and the second pulmonary function index to obtain a linear fitting expression; a fifth calculation module, used to calculate the linear fit between the first pulmonary function index and the second pulmonary function index; and a first establishment module, used to establish the preset correction function based on the linear fitting expression and the linear fit.

[0020] Optionally, the measuring device also includes: a fourth characterization module, used to characterize the comparison result of the second pulmonary function index with a preset threshold as a true result after correcting the first pulmonary function index based on a preset correction function to obtain the corrected first pulmonary function index; a fifth characterization module, used to characterize the comparison result of the first pulmonary function index with the preset threshold as a predicted result; and a sixth calculation module, used to calculate the index value of the performance index for pulmonary function determination using the corrected first pulmonary function index based on the true result and the predicted result, wherein the performance index includes at least: accuracy, sensitivity, and specificity.

[0021] Optionally, the preset radar device is a millimeter wave radar.

[0022] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned method for measuring lung function indicators.

[0023] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned method for measuring lung function indicators.

[0024] In the present disclosure, based on a preset radar device, echo data is collected when the target user performs a breath test in a specified manner, the echo data is processed to obtain a breathing signal, based on the breathing signal, a first lung function index is calculated, based on a preset correction function, the first lung function index is corrected to obtain a corrected first lung function index. In the present application, by using a preset radar device, the echo data of the user during the breath test can be directly collected without contacting the user, a breathing signal is obtained after processing, and then, the lung function index is calculated by the breathing signal, and the lung function index is corrected by the correction function, thereby realizing the detection of the movement of the user's chest without contacting the user, and obtaining the user's lung function index, thereby solving the technical problem in the related art that the user's lung function index can only be measured by contact, resulting in inconvenience in use. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0026] Figure 1 is a flow chart of an optional method for measuring lung function indicators according to an embodiment of the present invention;

[0027] Figure 2 is a schematic diagram of an optional data collection scenario according to an embodiment of the present invention;

[0028] Figure 3 is a schematic diagram of an optional radar exhalation signal according to an embodiment of the present invention;

[0029] Figure 4 is a schematic diagram of an optional fitting result of a radar one-second rate indicator and a pulmonary function meter one-second rate indicator according to an embodiment of the present invention;

[0030] Figure 5 is a schematic diagram of an optional modified radar one-second rate index and a pulmonary function meter one-second rate index fitting result according to an embodiment of the present invention;

[0031] Figure 6 is a flowchart of an optional non-contact lung function index measurement method based on millimeter wave radar according to an embodiment of the present invention;

[0032] Figure 7 Schematic diagram of an optional device for measuring lung function indicators according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] The following embodiments of the present invention can be applied to the scenario of lung function index calculation, and provide a non-contact lung function index measurement method based on millimeter wave radar. The present invention can collect radar echo data when the user exhales in a specified manner through millimeter wave radar, process the data to extract the respiratory signal, and then use the extracted respiratory signal to calculate the radar one-second rate index, and then use the linear fitting method to obtain the correction function of the radar one-second rate index on a small batch data set, and provide the accuracy, sensitivity, and specificity indicators of obstructive ventilation disorder judgment using millimeter wave radar on a small batch data set.

[0036] The present invention is described in detail below in conjunction with various embodiments.

[0037] Embodiment 1

[0038] According to an embodiment of the present invention, an embodiment of a method for measuring a lung function index is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0039] Figure 1 is a flow chart of an optional method for measuring lung function indicators according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0040] Step S101 , based on a preset radar device, collecting echo data when a target user performs a breath test in a specified manner, wherein the preset radar device does not need to contact the target user when collecting the echo data.

[0041] Step S102: Process the echo data to obtain a breathing signal.

[0042] Step S103, calculating a first lung function index based on the respiratory signal.

[0043] Step S104: correcting the first lung function index based on a preset correction function to obtain a corrected first lung function index.

[0044] Through the above steps, based on the preset radar device, the echo data of the target user performing the breath test in the specified manner can be collected, the echo data can be processed to obtain a breathing signal, based on the breathing signal, the first lung function index can be calculated, based on the preset correction function, the first lung function index can be corrected to obtain the corrected first lung function index. In an embodiment of the present invention, through the preset radar device, the echo data of the user during the breath test can be directly collected without contacting the user, and the breathing signal can be obtained after processing. Then, the lung function index can be calculated through the breathing signal, and the lung function index can be corrected through the correction function, thereby realizing the detection of the movement of the user's chest without contacting the user, and obtaining the user's lung function index, thereby solving the technical problem that the user's lung function index can only be measured by contact in the related art, resulting in inconvenience in use.

[0045] The embodiment of the present invention is described in detail below in combination with the above steps.

[0046] Step S101, based on a preset radar device, collecting echo data when a target user performs a breath test in a specified manner, wherein the preset radar device does not need to contact the target user when collecting the echo data. Optionally, the preset radar device is a millimeter wave radar.

[0047] In an embodiment of the present invention, the preset radar device may be a millimeter wave radar, which can receive electromagnetic waves reflected by the user, detect the movement of the user's chest without contacting the user, and further analyze the lung function of the subject. In this embodiment, the millimeter wave radar can collect echo data when the target user performs a breath test in a specified manner, and when collecting the echo data, the millimeter wave radar does not need to contact the user, which is convenient for the user to use.

[0048] Optionally, based on a preset radar device, the step of collecting echo data of a target user performing a breath test in a specified manner includes: upon confirming that the preset radar device is located at a preset distance value from the target user and is flush with the chest of the target user, issuing a normal breathing instruction; when the target user's normal breathing reaches a preset time limit, issuing a deep inhalation followed by a quick exhalation instruction, and collecting radar echo data of the target user, wherein the radar echo data is at least data lasting for a first preset time period; and characterizing the radar echo data as echo data.

[0049] In an embodiment of the present invention, Figure 2 is a schematic diagram of an optional data collection scenario according to an embodiment of the present invention, such as Figure 2 As shown, the subject (i.e., the target user) can sit on a chair with a backrest and press his back against the backrest, put his hands on the back of the body, and place the millimeter-wave radar at a preset distance value (e.g., about 75 cm) in front of the subject's chest. The height of the radar is adjusted to be flush with the subject's chest, and ensure that the radar transmitting and receiving antennas are facing the subject's chest.

[0050] In an embodiment of the present invention, the breath test process is as follows: after confirming that the preset radar device is located at a preset distance value from the target user and is flush with the target user's chest, a normal breathing instruction is issued (for example, a voice of "please breathe normally for 15 seconds" is issued), and the subject can breathe normally for a period of time after hearing the instruction (that is, the target user breathes normally within the preset time limit first), and when the target user's normal breathing reaches the preset time limit, a deep inhalation and then a quick exhalation instruction is issued (for example, a voice of "please take a deep breath with the fastest speed and maximum force, and after taking enough breaths, take a deep breath with the fastest speed and maximum force and hold for 6 seconds"), and radar echo data of the target user is collected (the radar echo data is at least data lasting for the first preset time period (for example, 10 seconds)), and then the user can breathe normally for several times. In the entire breath test process of this embodiment, the subject keeps other parts of the body stable, and the millimeter wave radar is used to collect the radar echo data of the subject during the above breath test process (that is, the radar echo data can be characterized as echo data).

[0051] Alternatively, the radar can transmit a frequency modulated continuous wave (FMCW) signal. A FMCW signal within one cycle is called a chirp signal (i.e., a swept cosine signal). The signal modulation mode can be set to a sawtooth wave, and the Chirp period can be set to T. chirp seconds, N Chirps transmitted continuously form a frame, and the frame period is T frame The radar receives the echo signal and mixes it with the transmitted signal to get the difference frequency signal, which is processed by high-pass filtering, low-noise amplification, ADC (analog-to-digital converter) sampling, and other processes to get the digital echo data.

[0052] Step S102: Process the echo data to obtain a breathing signal.

[0053] In the embodiment of the present invention, the original echo data collected by the radar can be processed to extract the breathing signal of the subject.

[0054] Optionally, the step of processing the echo data to obtain a breathing signal includes: transforming the echo data into a range-dimensional complex signal; determining a range gate where the chest of the target user in the range-dimensional complex signal is located, wherein the range gate represents the distance range of the user's chest relative to the radar; extracting the original phase signal based on the range gate; performing a preset unwrapping operation on the original phase signal to obtain an unwrapped phase signal; and characterizing the phase signal as a breathing signal.

[0055] In an embodiment of the present invention, fast time processing can be performed first to transform the original radar echo data into the distance dimension (that is, the echo data is transformed into a distance dimension complex signal), and then the range gate where the user's chest is located in the radar echo data is determined (that is, the range gate where the chest of the target user in the distance dimension complex signal is located is determined, and the range gate represents the distance range of the user's chest relative to the radar), the distance resolution represents the minimum distance between two targets that can be separated in the radar echo (which can also be converted into a time interval), and then the original phase signal is extracted along the range gate (that is, based on the range gate, the original phase signal is extracted), and the extracted original phase signal is unwrapped to obtain an unwrapped phase signal, and the unwrapped phase signal is the breathing signal (that is, the original phase signal is subjected to a preset unwrapping operation to obtain an unwrapped phase signal, and the phase signal is characterized as a breathing signal), and the breathing signal includes information related to the breathing movement of the subject, as follows:

[0056] First, the echo signal received in each Chirp is processed by removing DC and performing FFT transformation (i.e., fast Fourier transform) to obtain a distance-dimensional complex signal. The distance-dimensional complex signal corresponding to the first Chirp in each frame is used to extract the original phase signal containing the respiratory movement information of the subject. Specifically, the static clutter in the distance-dimensional complex signal is first removed along the frame time dimension, and then the point with the strongest power within the limited distance range is found along the distance dimension. The corresponding range gate is used as the candidate range gate for extracting the respiratory signal. In order to ensure the reliability of the selected respiratory signal extraction range gate, the median of all candidate range gates within the entire acquisition time is calculated and used as the final respiratory signal extraction range gate. Next, the phase angle of the selected range gate in the distance-dimensional complex signal corresponding to the first Chirp in each frame is extracted to obtain the original phase signal containing the respiratory movement of the subject, and the original phase signal is unwrapped to obtain the respiratory signal.

[0057] Step S103, calculating a first lung function index based on the respiratory signal.

[0058] Optionally, the step of calculating the first lung function index based on the respiratory signal includes: smoothing the respiratory signal to obtain a target respiratory signal, and determining the exhalation starting point based on the target respiratory signal; determining the maximum value point of the target respiratory signal within a second preset time period based on the exhalation starting point; calculating a first relative value based on the exhalation starting point and the maximum value point; determining all sampling points within a third preset time period in the target respiratory signal based on the exhalation starting point; calculating the amplitude difference between each sampling point among all sampling points and the sampling point delayed by a preset time to obtain an amplitude difference set; determining the maximum amplitude difference based on the amplitude difference set; characterizing the maximum amplitude difference as a second relative value; and calculating the first lung function index based on the first relative value and the second relative value.

[0059] In an embodiment of the present invention, the exhalation start point can be first determined in the target breathing signal. Figure 3 is a schematic diagram of an optional radar breath signal according to an embodiment of the present invention, such as Figure 3 As shown, the radar breath test signal is a line with time t / s as the horizontal axis (such as Figure 3 The horizontal axis is from 0 to 10, with the interval unit set to 1), and the vertical axis is the distance d / cm (such as Figure 3 The curve is from -1 to 3, with the vertical coordinate interval set to 0.5.

[0060] In this embodiment, the radar FEV1 relative value (i.e., the second relative value) and the radar FVC relative value (i.e., the first relative value) can be calculated according to the exhalation starting point, and then the radar one-second rate estimation value (i.e., the radar FEV1 / FVC index, which can be called the first lung function index in this embodiment) can be obtained, as follows:

[0061] The relative value of radar FVC can be calculated first, based on the obtained exhalation starting point t start , find the maximum value point s(t top ), the relative value of radar FVC is calculated by the following formula (1):

[0062] FVC REL =s(t top )-s(t start ) (1);

[0063] To calculate the relative value of radar FEV1, we can assume that the number of sampling points of the respiratory signal in 1 second is f s , based on the exhalation start point t start , the amplitude difference between the point after the preset delay time (which can be set to 1 second in this embodiment) is calculated by the following formula (2):

[0064] Δ0=s(t start +f s )-s(t start ) (2);

[0065] Similarly, for the exhalation start point t start The same operation is performed for all points within the third preset time period (e.g., 1 second), and the calculation is performed using the following formula (3):

[0066] Δ k =s(t start +k+f s )-s(t start + k), k = 0, 1, ..., f s -1 (3);

[0067] The largest amplitude difference is selected as the relative value of radar FEV1, that is,

[0068] where a = arg max k Δ k , k = 0, 1, ..., f s -1.

[0069] The radar one-second rate index can be obtained through the following formula (4):

[0070]

[0071] Optionally, the step of determining the exhalation starting point based on the target breathing signal includes: determining all minimum points within a fourth preset time period based on the target breathing signal; determining all maximum points in the target breathing signal; calculating the amplitude difference of the signal amplitude between each minimum point among all minimum points and its subsequent nearest maximum point to obtain an amplitude difference set; based on the amplitude difference set, determining the target minimum point indicated by the maximum amplitude difference; and characterizing the target minimum point as the exhalation starting point.

[0072] In the embodiment of the present invention, the exhalation signal in the first preset time period can be Gaussian smoothed to obtain a smoothed signal s(t) (i.e., the target respiratory signal), wherein t represents a discrete time point index, and all the minimum points in the preset time period before the signal s(t) (e.g., the first 4 seconds) are found, and then all the maximum points in the signal s(t) are found. For each minimum point s(t min，i ), find the nearest maximum point s(t max，i ), the difference between the signal amplitudes of the two points is calculated by the following formula (5) (i.e., the difference between the signal amplitudes of each minimum point among all the minimum points and the maximum point closest to it is calculated):

[0073] Δhi =s(t max，i )-s(t min，i ) (5);

[0074] Select the minimum point corresponding to the index i that maximizes the amplitude difference as the starting point of exhalation t start ,Right now,

[0075] t start =t min，m , where m = argmax i Δh i .

[0076] Optionally, before correcting the first pulmonary function index based on a preset correction function to obtain the corrected first pulmonary function index, it also includes: calculating the first pulmonary function index and the second pulmonary function index based on historical samples within a fifth preset time period; performing linear fitting on the first pulmonary function index and the second pulmonary function index to obtain a linear fitting expression; calculating the linear fitting degree between the first pulmonary function index and the second pulmonary function index; and establishing a preset correction function based on the linear fitting expression and the linear fitting degree.

[0077] In the embodiment of the present invention, the radar one-second rate index (FEV1 / FVC) obtained for the small batch samples (i.e., the historical samples within the fifth preset time period) is RADAR (i.e. the first lung function index) and the one-second rate index of the spirometer (FEV1 / FVC) TRUE (i.e. the second lung function index) for linear fitting and calculate the linear fitting degree R 2 , which is used as a criterion for evaluating the linear correlation between the two and the accuracy of radar measurement, specifically:

[0078] According to the small batch data set, the linear fitting expression is obtained as follows:

[0079] (FEV1 / FVC) RADAR =1.018*(FEV1 / FVC) TRUE -0.0806;

[0080] The calculated linear fit R 2 =0.8645.

[0081] According to the linear fitting results, the correction function of the radar one-second rate index (i.e., the preset correction function) is:

[0082] (FEV1 / FVC) REV =[(FEV1 / FVC) RADAR +0.0806] / 1.018;

[0083] Among them, (FEV1 / FVC) REVis the revised radar one-second rate index (ie, the revised first lung function index). In this embodiment, when the revised radar one-second rate index exceeds 100%, it can be recorded as 100%.

[0084] Figure 4 is a schematic diagram of an optional radar one-second rate indicator and a pulmonary function meter one-second rate indicator fitting result according to an embodiment of the present invention, such as Figure 4 As shown, FEV1 / FVC byLungInstrument (i.e., the one-second rate index of the lung function instrument) is used as the horizontal axis (such as Figure 4 The horizontal axis is from 0 to 100, with the interval unit set to 20), and the vertical axis is FEV1 / FVCbyRadar (i.e., radar rate per second index) (e.g. Figure 4 The vertical axis in the figure ranges from 0 to 100, with the interval unit set to 10), and the FEV1 / FVC radar-pulmonary function instrument comparison curve is fitted, where the asterisk represents DataPoint, the horizontal line represents FittedCurve, and the dot represents Radar=LungInstrument.

[0085] Figure 5 is a schematic diagram of an optional modified radar one-second rate index and a pulmonary function meter one-second rate index fitting result according to an embodiment of the present invention, such as Figure 5 As shown, FEV1 / FVC byLungInstrument (i.e., the one-second rate index of the lung function instrument) is used as the horizontal axis (such as Figure 5 The horizontal axis is from 0 to 100, with the interval unit set to 20), and the vertical axis is FEV1 / FVC byRadar (i.e., radar rate per second index) (e.g. Figure 5 The vertical axis in the figure ranges from 0 to 100, with the interval unit set to 10), and the FEV1 / FVC radar-pulmonary function instrument comparison curve (after correction) is fitted, where the asterisk represents DataPoint, the horizontal line represents FittedCurve, and the dot represents Radar=LungInstrument.

[0086] Step S104: correcting the first lung function index based on a preset correction function to obtain a corrected first lung function index.

[0087] In the embodiment of the present invention, the first lung function index can be corrected by using the obtained correction function to obtain the corrected first lung function index.

[0088] Optionally, after correcting the first pulmonary function index based on a preset correction function to obtain a corrected first pulmonary function index, it also includes: characterizing the comparison result of the second pulmonary function index with the preset threshold as a true result; characterizing the comparison result of the first pulmonary function index with the preset threshold as a predicted result; based on the true result and the predicted result, calculating the index value of the performance index for pulmonary function determination using the corrected first pulmonary function index, wherein the performance index includes at least: accuracy, sensitivity, and specificity.

[0089] In the embodiment of the present invention, the comparison result of the second lung function index and the preset threshold value can be characterized as a true result, and the comparison result of the first lung function index and the preset threshold value can be characterized as a predicted result. When the preset threshold value is 70%, obstructive ventilation disorder can be judged, specifically: the case where the spirometry one-second rate index FEV1 / FVC is less than 70% is judged as obstructive ventilation disorder, and the modified radar one-second rate index (FEV1 / FVC) is used as the prediction result. REV The result of obstructive ventilation disorder was used as the prediction result, and the forced expiratory volume in one second (FEV1 / FVC) was used as the index. TRUE The result of obstructive ventilation disorder was determined as the true result, and the accuracy, sensitivity and specificity indicators were calculated.

[0090] Table 1 is an optional classification of obstructive ventilation disorder determination results in this embodiment, as shown in Table 1:

[0091] Table 1

[0092]

[0093]

[0094] Among them, TP represents the number of cases that are actually barrier-free and predicted to be barrier-free, FP represents the number of cases that are actually with obstacles and predicted to be barrier-free, TN represents the number of cases that are actually barrier-free and predicted to be with obstacles, and FN represents the number of cases that are actually with obstacles and predicted to be barrier-free.

[0095] Based on the actual results and the predicted results, the specific calculation formula for calculating the index value of the performance index for lung function determination using the modified first lung function index is as follows:

[0096] Accuracy:

[0097] Sensitivity (Accessibility Recall):

[0098] Specificity (recall with impairments):

[0099] Another optional specific implementation is described in detail below.

[0100] Figure 6 is a flowchart of an optional non-contact lung function index measurement method based on millimeter wave radar according to an embodiment of the present invention, such as Figure 6 As shown, the following steps are included:

[0101] (1) Use millimeter wave radar to collect radar echo data when a person performs a breath test in a specified manner.

[0102] The subject sits on a chair with a backrest and puts his back against the backrest, with his hands on the back of his body. The millimeter-wave radar is placed about 75 cm in front of the subject's chest. The radar height is adjusted to make it flush with the subject's chest, and the radar transmitting and receiving antennas are ensured to be facing the subject's chest. The breath test process is as follows: after hearing the "normal breathing" command, the subject breathes normally for a while, and then after hearing the "deep breath and quick exhalation" command, the subject breathes deeply at the fastest speed and with the greatest force, and after inhaling enough, breathes deeply at the fastest speed and with the greatest force and holds for 6 seconds (called 6-second exhalation), and then breathes normally several times. During the entire breath test, the subject keeps other parts of the body stable, and the millimeter-wave radar is used to collect the radar echo data of the subject within 10 seconds after the "deep breath and quick exhalation" command is issued.

[0103] (2) Extract breathing signal from radar echo data.

[0104] The original echo data collected by the radar is processed to extract the breathing signal of the subject.

[0105] (3) Calculate the radar one-second rate index using the extracted breathing signal.

[0106] The first step is to perform Gaussian smoothing on the original 10-second respiratory signal to obtain the smoothed signal s(t), where t represents the discrete time point index. Find all the minimum points in the first 4 seconds of the signal s(t), and then find all the maximum points in the signal s(t). For each minimum point s(t min，i ), find the nearest maximum point s(t max，i ), calculate the difference between the signal amplitudes at two points, that is,

[0107] Δh i =s(t max，i )-s(t min，i ).

[0108] Select the minimum point corresponding to the index i that maximizes the amplitude difference as the starting point t of the 6-second exhalation start ,Right now,

[0109] tstart =t min，m , where m = arg max i Δh i .

[0110] The second step is to calculate the radar FEV1 / FVC index. First, calculate the relative value of the radar FVC, and then calculate the relative value of the radar FVC. start , find the maximum value point s(t top ), we can get the relative value of radar FVC, that is,

[0111] FVC REL =s(t top )-s(t start );

[0112] Secondly, calculate the relative value of radar FEV1, assuming that the number of respiratory signal sampling points in 1 second is f s , for the 6-second exhalation starting point t in the first step start , calculate the amplitude difference between it and the point 1 second later, that is,

[0113] Δ0=s(t start +f s )-s(t start );

[0114] Similarly, for the 6-second exhalation starting point t start The same operation is performed on all points within the next second. The calculation formula is as follows:

[0115] Δ k =s(t start +k+f s )-s(t start + k), k = 0, 1, ..., f s -1;

[0116] The largest 1-second amplitude difference is selected as the relative value of radar FEV1, that is,

[0117] where a = arg max k Δ k , k = 0, 1, ..., f s -1.

[0118] At this point, we can get the radar one-second rate indicator:

[0119]

[0120] (4) Calculate the correction function of the radar one-second rate index based on the one-second rate index of the pulmonary function instrument.

[0121] Radar rate per second index (FEV1 / FVC) obtained for a small batch of samples RADAR and spirometry one-second rate index (FEV1 / FVC) TRUE Perform linear fitting and calculate the linear fitting degree R 2 , which is used as a criterion for evaluating the linear correlation between the two and the accuracy of radar measurement.

[0122] According to the small batch data set, the linear fitting expression is obtained as follows:

[0123] (FEV1 / FVC) RADAR =1.018*(FEV1 / FVC) TRUE -0.0806, R 2 =0.8645;

[0124] According to the linear fitting results, the correction function of the radar one-second rate index is:

[0125] (FEV1 / FVC) REV =[(FEV1 / FVC) RADAR +0.0806] / 1.018;

[0126] Among them, (FEV1 / FVC) REV It is the corrected radar one-second rate indicator.

[0127] In this embodiment, the situation where the spirometry one-second rate index FEV1 / FVC < 70% can be determined as obstructive ventilation disorder, and the corrected radar one-second rate index (FEV1 / FVC) can be used to determine whether the spirometry one-second rate index FEV1 / FVC is less than 70%. REV The result of obstructive ventilation disorder was used as the prediction result, and the forced expiratory volume in one second (FEV1 / FVC) was used as the index. TRUE The result of the obstructive ventilation disorder determination was the true result, and the accuracy, sensitivity, specificity and other index values ​​were calculated.

[0128] In an embodiment of the present invention, a millimeter-wave radar can be used to collect radar echo data when a user performs a breath test in a specified manner, and the data can be processed to extract a breathing signal. The extracted breathing signal is then used to calculate a radar one-second rate index. A linear fitting method is then used to obtain a correction function for the radar one-second rate index. Accuracy, sensitivity, and specificity indicators for determining obstructive ventilation disorders using a millimeter-wave radar are also provided, which can detect the movement of a user's chest without contacting the user and obtain the user's lung function indicators.

[0129] Embodiment 2

[0130] A lung function index measuring device provided in this embodiment includes multiple implementation units, each of which corresponds to each implementation step in the above-mentioned embodiment 1.

[0131] Figure 7 is a schematic diagram of an optional device for measuring lung function indicators according to an embodiment of the present invention, such as Figure 7 As shown, the measuring device may include: a collection unit 70, a processing unit 71, a calculation unit 72, and a correction unit 73, wherein:

[0132] The collection unit 70 is used to collect the echo data of the target user when the breath test is performed in a specified manner based on the preset radar device, wherein the preset radar device does not need to contact the target user when collecting the echo data;

[0133] A processing unit 71 is used to process the echo data to obtain a respiratory signal;

[0134] A calculation unit 72, configured to calculate a first lung function index based on the respiratory signal;

[0135] The correction unit 73 is used to correct the first lung function index based on a preset correction function to obtain a corrected first lung function index.

[0136] The above-mentioned measuring device can collect echo data when the target user performs a breath test in a specified manner through the collection unit 70 based on the preset radar device, process the echo data through the processing unit 71 to obtain a breathing signal, calculate the first lung function index based on the breathing signal through the calculation unit 72, and correct the first lung function index based on the preset correction function through the correction unit 73 to obtain the corrected first lung function index. In an embodiment of the present invention, the preset radar device can directly collect the echo data of the user during the breath test without contacting the user, and obtain the breathing signal after processing. Then, the lung function index is calculated through the breathing signal, and the lung function index is corrected through the correction function, thereby realizing the detection of the user's chest movement without contacting the user, and obtaining the user's lung function index, thereby solving the technical problem that the user's lung function index can only be measured by contact in the related art, resulting in inconvenience in use.

[0137] Optionally, the collection unit includes: a first sending module, used to issue a normal breathing instruction when it is confirmed that the preset radar device is located at a preset distance value from the target user and is flush with the chest of the target user; a second sending module, used to issue a deep inhalation followed by a quick exhalation instruction when the normal breathing of the target user reaches a preset time limit, and collect radar echo data of the target user, wherein the radar echo data is at least data lasting for a first preset time period; a first characterization module, used to characterize the radar echo data as echo data.

[0138] Optionally, the processing unit includes: a first transformation module, used to transform the echo data into a range-dimensional complex signal; a first determination module, used to determine the range gate where the chest of the target user in the range-dimensional complex signal is located, wherein the range gate represents the distance range of the user's chest relative to the radar; a first extraction module, used to extract the original phase signal based on the range gate; a first unwrapping module, used to perform a preset unwrapping operation on the original phase signal to obtain an unwrapped phase signal; and a second characterization module, used to characterize the phase signal as a breathing signal.

[0139] Optionally, the calculation unit includes: a second determination module, which is used to smooth the respiratory signal to obtain a target respiratory signal, and determine the exhalation starting point based on the target respiratory signal; a third determination module, which is used to determine the maximum value point of the target respiratory signal within a second preset time period based on the exhalation starting point; a first calculation module, which is used to calculate the first relative value based on the exhalation starting point and the maximum value point; a fourth determination module, which is used to determine all sampling points within the third preset time period in the target respiratory signal based on the exhalation starting point; a second calculation module, which is used to calculate the amplitude difference between each sampling point among all sampling points and the sampling point after it is delayed by a preset time to obtain an amplitude difference set; a fifth determination module, which is used to determine the maximum amplitude difference based on the amplitude difference set; a third characterization module, which is used to characterize the maximum amplitude difference as a second relative value; and a third calculation module, which is used to calculate the first lung function index based on the first relative value and the second relative value.

[0140] Optionally, the second determination module includes: a first determination submodule, used to determine all minimum points within a fourth preset time period based on the target breathing signal; a second determination submodule, used to determine all maximum points in the target breathing signal; a first calculation submodule, used to calculate the amplitude difference of the signal amplitude between each minimum point among all minimum points and its subsequent nearest maximum point to obtain an amplitude difference set; a third determination submodule, used to determine the target minimum point indicated by the maximum amplitude difference based on the amplitude difference set; and a first characterization submodule, used to characterize the target minimum point as the start point of exhalation.

[0141] Optionally, the measuring device also includes: a fourth calculation module, used to calculate the first pulmonary function index and the second pulmonary function index based on historical samples within a fifth preset time period before correcting the first pulmonary function index based on a preset correction function to obtain the corrected first pulmonary function index; a first fitting module, used to perform linear fitting on the first pulmonary function index and the second pulmonary function index to obtain a linear fitting expression; a fifth calculation module, used to calculate the linear fit between the first pulmonary function index and the second pulmonary function index; and a first establishment module, used to establish a preset correction function based on the linear fitting expression and the linear fit.

[0142] Optionally, the measuring device also includes: a fourth characterization module, used to characterize the comparison result of the second pulmonary function index with the preset threshold as a true result after correcting the first pulmonary function index based on a preset correction function to obtain the corrected first pulmonary function index; a fifth characterization module, used to characterize the comparison result of the first pulmonary function index with the preset threshold as a predicted result; and a sixth calculation module, used to calculate the index value of the performance index for pulmonary function determination using the corrected first pulmonary function index based on the true result and the predicted result, wherein the performance index includes at least: accuracy, sensitivity, and specificity.

[0143] Optionally, the preset radar device is a millimeter wave radar.

[0144] The above-mentioned measuring device may also include a processor and a memory. The above-mentioned acquisition unit 70, processing unit 71, calculation unit 72, correction unit 73, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0145] The processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be provided, and the first lung function index is corrected based on a preset correction function by adjusting kernel parameters to obtain the corrected first lung function index.

[0146] The above-mentioned memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0147] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: based on a preset radar device, collecting echo data when the target user performs a breath test in a specified manner, processing the echo data to obtain a breathing signal, calculating a first lung function index based on the breathing signal, and correcting the first lung function index based on a preset correction function to obtain a corrected first lung function index.

[0148] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned method for measuring lung function indicators.

[0149] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement the above-mentioned method for measuring lung function indicators.

[0150] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0151] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0152] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0153] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0154] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0155] If the integrated unit is implemented in the form of 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 the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0156] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for measuring lung function indexes, characterized in that: include: Based on a preset radar device, collecting echo data when a target user performs a breath test in a specified manner, wherein the preset radar device does not need to contact the target user when collecting the echo data; Processing the echo data to obtain a respiratory signal; Calculating a first lung function index based on the respiratory signal includes: determining an exhalation start point; calculating a first relative value based on the exhalation start point and a maximum value point of a target respiratory signal within a second preset time period; calculating an amplitude difference between each sampling point in all the sampling points and a sampling point delayed by a preset time based on the exhalation start point and all sampling points in the target respiratory signal within a third preset time period; characterizing the maximum amplitude difference as a second relative value; and calculating the first lung function index based on the first relative value and the second relative value; Based on a preset correction function, the first lung function index is corrected to obtain a corrected first lung function index.

2. The measuring method according to claim 1, characterized in that: The step of collecting echo data of a target user performing a breath test in a specified manner based on a preset radar device includes: When confirming that the preset radar device is located at a preset distance value from the target user and is flush with the chest of the target user, issuing a normal breathing instruction; When the target user breathes normally for a preset time limit, a deep inhalation followed by a quick exhalation instruction is issued, and radar echo data of the target user is collected, wherein the radar echo data is data that lasts for at least a first preset time period; The radar echo data is characterized as the echo data.

3. The measuring method according to claim 1, characterized in that: The step of processing the echo data to obtain a respiratory signal comprises: Converting the echo data into a range-dimensional complex signal; Determine a range gate where the chest of the target user in the range complex signal is located, wherein the range gate represents the distance range of the chest of the user relative to the radar; Based on the range gate, extracting the original phase signal; Performing a preset unwrapping operation on the original phase signal to obtain an unwrapped phase signal; The phase signal is characterized as the respiration signal.

4. The measuring method according to claim 1, characterized in that: The step of calculating a first lung function index based on the respiratory signal comprises: Smoothing the breathing signal to obtain a target breathing signal, and determining an exhalation start point based on the target breathing signal; Based on the exhalation starting point, determining a maximum point of the target breathing signal within a second preset time period; Calculating a first relative value based on the exhalation starting point and the maximum value point; Based on the exhalation start point, determining all sampling points within a third preset time period in the target respiratory signal; Calculating the amplitude difference between each sampling point among all the sampling points and the sampling point after being delayed by a preset time to obtain an amplitude difference set; Based on the set of amplitude differences, determining a maximum amplitude difference; characterizing the maximum amplitude difference as a second relative value; The first lung function index is calculated based on the first relative value and the second relative value.

5. The measuring method according to claim 4, characterized in that: The step of determining the exhalation start point based on the target breathing signal comprises: Based on the target breathing signal, determining all minimum points within a fourth preset time period; Determine all maximum points in the target respiratory signal; Calculating the amplitude difference of the signal amplitude between each minimum value point among all the minimum value points and the subsequent most adjacent maximum value point to obtain an amplitude difference set; Based on the amplitude difference set, determining a target minimum point indicated by a maximum amplitude difference; The target minimum point is characterized as the exhalation starting point.

6. The measuring method according to claim 1, characterized in that: Before correcting the first lung function index based on a preset correction function to obtain a corrected first lung function index, the method further includes: Calculating a first lung function index and a second lung function index based on historical samples within a fifth preset time period; Performing linear fitting on the first pulmonary function index and the second pulmonary function index to obtain a linear fitting expression; Calculating a linear fit between the first pulmonary function index and the second pulmonary function index; The preset correction function is established based on the linear fitting expression and the linear fitting degree.

7. The measuring method according to claim 6, characterized in that: After correcting the first lung function index based on a preset correction function to obtain a corrected first lung function index, the method further includes: characterizing a comparison result of the second lung function index and a preset threshold as a true result; characterizing a comparison result of the first lung function index and the preset threshold as a prediction result; Based on the actual result and the predicted result, the index value of the performance index for lung function determination using the corrected first lung function index is calculated, wherein the performance index at least includes: accuracy, sensitivity, and specificity.

8. The measuring method according to any one of claims 1 to 7, characterized in that: The preset radar device is a millimeter wave radar.

9. A device for measuring lung function indexes, characterized in that: include: A collection unit, configured to collect echo data when a target user performs a breath test in a specified manner based on a preset radar device, wherein the preset radar device does not need to contact the target user when collecting the echo data; A processing unit, used for processing the echo data to obtain a respiratory signal; A calculation unit, for calculating a first lung function index based on the respiratory signal, comprising: determining an exhalation start point; calculating a first relative value based on the exhalation start point and a maximum value point of a target respiratory signal within a second preset time period; calculating an amplitude difference between each sampling point in all the sampling points and a sampling point delayed by a preset time based on the exhalation start point and all sampling points in the target respiratory signal within a third preset time period; characterizing the maximum amplitude difference as a second relative value; and calculating the first lung function index based on the first relative value and the second relative value; The correction unit is used to correct the first lung function index based on a preset correction function to obtain a corrected first lung function index.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for measuring lung function indicators according to any one of claims 1 to 8.

11. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for measuring lung function indicators described in any one of claims 1 to 8.

Images