Pulmonary ventilation function detection device, method and system

Abstract

The present invention relates to the technical field of pulmonary function testing, and in particular to a pulmonary ventilation function testing device, method and system. The present invention quantifies the tension of a subject through waveform changes of an electrocardiogram (ECG) curve and amplitude fluctuations of an arm electromyography (EMG) curve to determine an initial tension level, and corrects the initial tension level based on the characteristic that the tension expressions presented by the ECG curve and the arm electromyography curve when the subject is nervous are consistent, thereby determining a corrected tension level that more accurately represents the tension level; and then corrects the initial pulmonary ventilation volume timing curve based on the corrected tension level, thereby solving the problem of inaccurate measurement of the pulmonary ventilation function of a subject by directly measuring the pulmonary ventilation volume timing curve of the subject in existing pulmonary ventilation tests, thereby improving the accuracy of pulmonary ventilation function testing based on the corrected pulmonary ventilation volume timing curve.

Description

Technical Field

[0001] The present invention relates to the technical field of pulmonary function testing, and in particular to a pulmonary ventilation function testing device, method and system. Background Art

[0002] Pulmonary ventilation function test mainly refers to forced vital capacity test, also known as timed vital capacity test. It is the most commonly used method to determine the subject's airflow limitation, evaluate his or her degree of cooperation and completion quality, and can measure the subject's respiratory system capacity to a certain extent.

[0003] Existing spirometry tests usually measure a subject's pulmonary ventilation function directly based on the subject's pulmonary ventilation volume timing curve. However, during the test, the subject is required to perform corresponding breathing movements according to instructions, and different subjects have different responses to the test. Subjects who are too nervous will have abnormal breathing states during the test, resulting in the final pulmonary ventilation volume timing curve to be inaccurate in measuring the subject's pulmonary ventilation function, thereby reducing the accuracy of pulmonary ventilation function testing. Summary of the Invention

[0004] The present application provides a pulmonary ventilation function detection device, method and system, which quantify the tension level of a subject by waveform changes of an electrocardiogram curve and amplitude fluctuations of an arm electromyography curve to determine an initial tension level, and correct the initial tension level based on the characteristic that the tension expressions presented by the electrocardiogram curve and the arm electromyography curve when the subject is nervous are consistent, thereby determining a corrected tension level that more accurately represents the tension level; and then correct the initial pulmonary ventilation volume timing curve based on the corrected tension level, thereby solving the problem of inaccurate measurement of the subject's pulmonary ventilation function by the existing pulmonary ventilation volume test directly based on the subject's pulmonary ventilation volume timing curve, thereby improving the accuracy of pulmonary ventilation function detection based on the corrected pulmonary ventilation volume timing curve.

[0005] In a first aspect, the present application provides a method for detecting pulmonary ventilation function, the method comprising:

[0006] Collecting an initial lung ventilation volume time series curve, an electrocardiogram curve, and an arm electromyography curve within a test time period corresponding to a lung ventilation test process of the subject; dividing the test time period into at least two cardiac cycle time periods according to a cardiac cycle in the electrocardiogram curve;

[0007] In the electrocardiogram curve, the heart rate mapping intensity of each cardiac cycle period is determined according to the waveform changes in each cardiac cycle period; in the arm electromyography curve, the myoelectric mapping intensity of each cardiac cycle period is determined according to the myoelectric signal amplitude fluctuations in each cardiac cycle period;

[0008] Determining the subject's initial stress level based on the overall magnitude of the stress level mapped by the electromyography and the overall magnitude of the stress level mapped by the heart rate in all cardiac cycle time periods; determining the stress level credibility based on the similarity between the stress level change trends mapped by the heart rate and the stress level changed by the electromyography corresponding to each cardiac cycle time period in chronological order; and correcting the initial stress level based on the stress level credibility to determine the subject's corrected stress level;

[0009] The initial pulmonary ventilation volume time series curve is corrected according to the corrected tension level to determine a corrected pulmonary ventilation volume time series curve; and pulmonary ventilation function detection is performed according to the corrected pulmonary ventilation volume time series curve.

[0010] Furthermore, the process of acquiring the cardiac cycle time period includes:

[0011] The electrocardiogram curve is input into a trained convolutional neural network to output each cardiac cycle; the time period of each cardiac cycle in the test time period is used as the corresponding cardiac cycle time period.

[0012] Furthermore, the process of obtaining the heart rate mapping stress level includes:

[0013] Inputting the local curve corresponding to each cardiac cycle time period in the electrocardiogram curve into the trained convolutional neural network, and outputting the P wave time period, QRS complex wave time period, ST wave time period and T wave time period in each cardiac cycle time period;

[0014] The center moment of the P wave time period in each cardiac cycle time period is used as the P wave representative moment of each cardiac cycle time period; the time interval between the P wave representative moment of each cardiac cycle time period and the P wave representative moment of the previous cardiac cycle time period is used as the P wave reference interval of each cardiac cycle time period;

[0015] Determining the QRS complex wave vibration amplitude of each cardiac cycle time period according to the ECG signal amplitude extreme difference corresponding to the QRS complex wave time period in each cardiac cycle time period on the ECG curve;

[0016] Determining the ST wave fluctuation degree of each cardiac cycle time period according to the ECG signal amplitude variance at all moments in the ST wave time period in each cardiac cycle time period;

[0017] performing negative correlation normalization on the mean values ​​of the electrocardiographic signal amplitudes of the T wave at all moments corresponding to the electrocardiographic curve in each cardiac cycle time period to determine the degree of T wave inversion in each cardiac cycle time period;

[0018] The product of the negative correlation mapping value of the P wave reference interval, the QRS complex wave vibration amplitude, the ST wave fluctuation degree and the T wave inversion degree is normalized to determine the heart rate mapping tension of each cardiac cycle time period.

[0019] Furthermore, the process of obtaining the tension level of electromyography mapping includes:

[0020] The myoelectric signal vibration amplitude extreme difference corresponding to each cardiac cycle time period on the arm electromyographic curve is normalized to determine the myoelectric mapping tension level of each cardiac cycle time period.

[0021] Furthermore, the process of obtaining the initial stress level includes:

[0022] The average of the heart rate mapping tension levels of all cardiac cycle time periods is taken as the overall heart rate tension level; the average of the electromyography mapping tension levels of all cardiac cycle time periods is taken as the overall electromyography tension level; and the product of the overall heart rate tension level and the overall electromyography tension level is taken as the subject's initial tension level.

[0023] Furthermore, the process of obtaining the credibility of the stress level includes:

[0024] After arranging the heart rate mapping tension levels of all periodic time periods in chronological order, a heart rate mapping tension level time series sequence is determined; after arranging the electromyography mapping tension levels of all periodic time periods in chronological order, a myoelectric mapping tension level time series sequence is determined; and the Pearson correlation coefficient between the heart rate mapping tension level time series sequence and the electromyography mapping tension level time series sequence is used as the tension level credibility.

[0025] Furthermore, the process of obtaining the corrected stress level includes:

[0026] The product of the stress level reliability and the initial stress level is normalized to determine the subject's revised stress level.

[0027] Furthermore, the process of obtaining the modified pulmonary ventilation volume time series curve includes:

[0028] The final air volume adjustment value is determined by multiplying the product of the corrected tension level and the preset standard air volume adjustment value; the horizontal axis of the initial pulmonary ventilation volume time series curve is time, and the vertical axis is pulmonary ventilation volume;

[0029] Obtaining the inspiratory phase time period and the expiratory phase time period of the initial pulmonary ventilation volume time series curve; taking the sum of the pulmonary ventilation volume at each moment in the inspiratory phase time period and the final air volume adjustment value as the corrected air volume value at each moment in the inspiratory phase time period;

[0030] The difference between the lung ventilation volume at each moment in the expiratory phase time period and the final air volume adjustment value is used as the corrected air volume value at each moment in the expiratory phase time period;

[0031] On the initial pulmonary ventilation volume time series curve, the corrected gas volume values ​​at all moments corresponding to the inspiration phase and the expiration phase are substituted for the corresponding pulmonary ventilation volume and then interpolated to determine the corrected pulmonary ventilation volume time series curve.

[0032] In a second aspect, the present application provides a pulmonary ventilation function detection system, the system comprising:

[0033] A data acquisition and preprocessing module is used to acquire the initial lung ventilation volume time series curve, electrocardiogram curve and arm electromyography curve within the test time period corresponding to the subject's lung ventilation test process; and divide the test time period into at least two cardiac cycle time periods according to the cardiac cycle in the electrocardiogram curve;

[0034] The first determination module is configured to determine the heart rate mapping intensity of each cardiac cycle time period based on the waveform changes in each cardiac cycle time period in the electrocardiogram curve; and to determine the myoelectric mapping intensity of each cardiac cycle time period based on the myoelectric signal amplitude fluctuations in each cardiac cycle time period in the arm electromyography curve;

[0035] The second determination module is configured to determine the subject's initial stress level based on the overall magnitude of the stress level mapped by the electromyography and the overall magnitude of the stress level mapped by the heart rate in all cardiac cycle time periods; determine the stress level credibility based on the similarity between the stress level change trends mapped by the heart rate and the stress level change trends mapped by the electromyography corresponding to each cardiac cycle time period in chronological order; and modify the initial stress level based on the stress level credibility to determine the modified stress level of the subject;

[0036] The pulmonary ventilation function detection module is used to correct the initial pulmonary ventilation volume time series curve according to the corrected tension level, determine the corrected pulmonary ventilation volume time series curve; and perform pulmonary ventilation function detection according to the corrected pulmonary ventilation volume time series curve.

[0037] In a third aspect, the present application provides a pulmonary ventilation function detection device, comprising a memory and a processor. The memory is configured to store computer program code, and the processor is configured to retrieve and execute the computer program code from the memory to perform the method according to the first aspect or any embodiment of the first aspect of the present application.

[0038] In a fourth aspect, the present application provides a computer program product, comprising a computer program code. When the computer program code is executed, the method of the first aspect or any embodiment of the first aspect of the present application is performed.

[0039] In a fifth aspect, the present application provides a computer-readable storage medium, which stores computer program code. When the computer program code is executed, it performs the method of the first aspect of the present application or any embodiment of the first aspect.

[0040] This application has the following beneficial effects:

[0041] First, when the subject is nervous, the nervousness is usually reflected in the waveform changes in each cardiac cycle on the ECG curve; and considering that the degree of nervousness needs to be reflected based on the synchronous changes of the electromyographic signal and the ECG signal, the test time period is first divided into each cardiac cycle to facilitate the analysis of the nervousness characteristics reflected by the ECG curve and reduce the computational complexity.

[0042] When the human body is tense, the waveforms corresponding to each cardiac cycle will be affected by the tension, resulting in specific changes. Therefore, the degree of tension in the heart rate mapping can be determined based on the waveform changes in each cardiac cycle time period. Similarly, during the pulmonary ventilation test, the subject's muscles are generally exerted through the diaphragm, intercostal muscles, and abdominal muscles, while other muscle groups are less exerted. Therefore, the muscles in the arms exert relatively less force, the muscle contraction force is smaller, and the electromyographic signal potential difference generated is smaller. Under the influence of tension, muscles usually contract abnormally, which causes the electromyographic signal amplitude on the corresponding arm electromyographic curve to fluctuate with certain characteristics. Therefore, the degree of tension in the electromyographic mapping can be determined based on the electromyographic signal amplitude fluctuations in each cardiac cycle time period.

[0043] The greater the subject's stress level reflected by the heart rate and electromyography in each cardiac cycle time period, the greater the subject's stress level as reflected by the ECG and EMG signals. Therefore, the initial stress level is determined by combining the overall magnitude of the EMG and heart rate stress levels across all cardiac cycle time periods. Furthermore, it is necessary to consider that stress can affect both the ECG and EMG signals. If the changes in stress reflected by the ECG and EMG signals are inconsistent, it indicates that the stress reflected by some ECG or EMG signals is not caused by stress. Therefore, the stress level credibility is further characterized based on the similarity between the stress level change trends in the heart rate and EMG corresponding to each cardiac cycle time period. The initial stress level is then corrected based on the stress credibility, resulting in a more accurate correction of the subject's stress level. Finally, based on the fact that stress can affect the subject's respiratory state, the initial pulmonary ventilation volume time series curve is corrected using the corrected stress level obtained by quantifying stress, resulting in a more accurate pulmonary ventilation function test based on the corrected pulmonary ventilation volume time series curve. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 A flow chart of a method for detecting pulmonary ventilation function provided by one embodiment of the present invention;

[0046] Figure 2 A time series curve diagram of initial lung ventilation volume provided by one embodiment of the present invention;

[0047] Figure 3 A structural diagram of a pulmonary ventilation function detection system provided by one embodiment of the present invention;

[0048] Figure 4 A schematic structural diagram of a pulmonary ventilation function detection device provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following, in combination with the accompanying drawings and preferred embodiments, describes in detail a pulmonary ventilation function detection device, method and system proposed in accordance with the present invention, its specific implementation, structure, features and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and the specific features, structures or characteristics in one or more embodiments may be combined in any suitable form. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0050] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0051] The specific scheme of a pulmonary ventilation function detection device, method and system provided by the present invention is described in detail below with reference to the accompanying drawings.

[0052] This application embodiment provides a method for detecting pulmonary ventilation function. Figure 1 , which shows a flow chart of a pulmonary ventilation function detection method provided by one embodiment of the present invention, the method comprising:

[0053] Step S101: collecting the initial lung ventilation volume time series curve, electrocardiogram curve and arm electromyography curve within the test time period corresponding to the subject's lung ventilation test process; dividing the test time period into at least two cardiac cycle time periods according to the cardiac cycle in the electrocardiogram curve.

[0054] First, use the pulmonary function tester to obtain the initial pulmonary ventilation volume time series curve during the entire test period according to the pulmonary ventilation test process; refer to Figure 2 , which shows an initial lung ventilation volume time series curve diagram provided by an embodiment of the present invention, Figure 2 In the initial lung ventilation volume time series curve, there are tidal phase, maximum inspiration phase, maximum exhalation phase a, and maximum inspiration phase b again; wherein, the tidal phase allows the subject to breathe evenly and calmly; the maximum inspiration phase allows the subject to inhale maximally and inhale deeply to the total lung volume position TLC; the maximum exhalation phase a allows the subject to exhale explosively and continuously to the residual volume position RV; the maximum inspiration phase b again is a rapid and deep inhalation from the residual volume position RV to the total lung volume position TLC. In a specific implementation of an embodiment of the present invention, the tidal phase time is set to 2 minutes, and the time for testing the maximum spontaneous ventilation is set to 30 seconds, both of which can be adjusted according to the specific implementation environment; and while testing, the tester's electrocardiogram is measured by an electrocardiograph, and the arm electromyogram is measured by an electromyograph; and the measurement frequency of the electrocardiogram and the arm electromyogram is set to 200Hz, which can be adjusted. It should be noted that the test time period is the time period from the start to the end of the subject's lung ventilation test, which depends on the total duration of the entire lung ventilation test process and needs to be obtained according to the specific implementation environment. No further details will be given here.

[0055] First, when the subject is nervous, the nervousness is usually reflected in the waveform changes in each cardiac cycle on the ECG curve; and considering that the degree of nervousness needs to be reflected based on the synchronous changes of the electromyographic signal and the ECG signal, the test time period is first divided into each cardiac cycle to facilitate the analysis of the nervousness characteristics reflected by the ECG curve and reduce the computational complexity.

[0056] Preferably, in some possible implementations of the embodiments of the present invention, the process of acquiring the cardiac cycle time period includes:

[0057] The ECG curve is input into a trained convolutional neural network, which outputs each cardiac cycle. The time period of each cardiac cycle within the test period is used as the corresponding cardiac cycle time period. The convolutional neural network's loss function uses the cross-entropy loss function. The cardiac cycle specifically refers to the period from the start of one heartbeat to the start of the next, exhibiting a cyclical nature. When stressed, tension affects the heartbeat process, resulting in specific changes in the ECG signal during each cardiac cycle. Therefore, the subject's stress level can be further quantified based on the corresponding specific changes in the ECG signal.

[0058] Step S102: In the electrocardiogram (ECG) curve, the heart rate mapping intensity of each cardiac cycle period is determined based on the waveform changes in each cardiac cycle period; in the arm electromyography (EMG) curve, the EMG mapping intensity of each cardiac cycle period is determined based on the EMG signal amplitude fluctuations in each cardiac cycle period.

[0059] When the human body is tense, the waveforms corresponding to each cardiac cycle will be affected by the tension, resulting in specific changes. Therefore, the degree of tension in the heart rate mapping can be determined based on the waveform changes in each cardiac cycle time period. Similarly, during the pulmonary ventilation test, the subject's muscles are generally exerted through the diaphragm, intercostal muscles, and abdominal muscles, while other muscle groups are less exerted. Therefore, the muscles in the arms exert relatively less force, the muscle contraction force is smaller, and the electromyographic signal potential difference generated is smaller. Under the influence of tension, muscles usually contract abnormally, which causes the electromyographic signal amplitude on the corresponding arm electromyographic curve to fluctuate with certain characteristics. Therefore, the degree of tension in the electromyographic mapping can be determined based on the electromyographic signal amplitude fluctuations in each cardiac cycle time period.

[0060] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the heart rate mapping stress level includes:

[0061] When the human body is nervous, the sympathetic nervous system will be activated, and the atria will contract faster accordingly, which is manifested in the electrocardiogram signal as an increase in the P wave frequency; and due to the release of adrenaline, the contractility of the ventricles is enhanced, and the amplitude of the QRS complex wave will increase; the T wave represents ventricular repolarization, and the sympathetic nerve excitement caused by tension may cause myocardial ischemia, resulting in T wave inversion; and the ST wave is the interval between ventricular depolarization and repolarization. When nervous, it will become irregular due to increased heart rate and increased myocardial load; therefore, the degree of tension can be characterized by the P wave, QRS complex wave, T wave and ST wave in each cardiac cycle time period on the electrocardiogram curve. Therefore, it is necessary to first determine the time period corresponding to the P wave, QRS complex wave, T wave and ST wave in each cardiac cycle. In this embodiment of the present invention, the local curve corresponding to each cardiac cycle time period in the electrocardiogram curve is input into the trained convolutional neural network, and the P wave time period, QRS complex wave time period, ST wave time period and T wave time period in each cardiac cycle time period are output. The loss function of the convolutional neural network adopts the cross entropy loss function. It should be noted that P wave, QRS complex wave, T wave and ST wave are all commonly used technical terms in electrocardiographic signals, which are well known to those skilled in the art and will not be further elaborated here.

[0062] The center of the P wave time segment within each cardiac cycle is used as the P wave representative moment for each cardiac cycle segment. The time interval between the P wave representative moment in each cardiac cycle segment and the P wave representative moment in the previous cardiac cycle segment is used as the P wave reference interval for each cardiac cycle segment. Because the P wave frequency increases when the human body is stressed, the shorter the P wave interval, the greater the degree of stress reflected in the P wave dimension. Therefore, the P wave reference interval is negatively correlated with the degree of stress.

[0063] The QRS complex wave amplitude for each cardiac cycle segment is determined based on the ECG signal amplitude range corresponding to each QRS complex wave segment on the ECG curve within each cardiac cycle segment. Because the amplitude of the QRS complex wave increases when the human body is stressed, appearing as a large amplitude difference on the ECG curve, the greater the ECG signal amplitude range corresponding to each QRS complex wave segment on the ECG curve, the greater the stress level reflected in the corresponding cardiac cycle segment. In other words, the QRS complex wave amplitude is positively correlated with the level of stress.

[0064] The ST wave fluctuation degree for each cardiac cycle segment is determined based on the ECG signal amplitude variance at all moments within the ST wave segment within each cardiac cycle segment. Because ST waves become irregular when the human body is stressed, the ST wave fluctuation degree for each cardiac cycle segment is determined by the ECG signal amplitude variance, which represents the degree of dispersion. The greater the ST wave fluctuation degree, the greater the stress level reflected in the corresponding cardiac cycle segment, indicating a positive correlation between ST wave fluctuation degree and stress level.

[0065] The mean value of the ECG signal amplitude of the T wave at all moments corresponding to the ECG curve in each cardiac cycle time period is negatively normalized to determine the degree of T wave inversion in each cardiac cycle time period; because the T wave will be inverted when the human body is nervous, the inversion will cause the ECG signal to be biased downward, making the ECG signal vibration amplitude relatively small, so after the mean value of the ECG signal amplitude of the T wave at all moments corresponding to the ECG curve in each cardiac cycle time period is negatively normalized, the greater the degree of T wave inversion, the greater the degree of tension reflected, that is, the degree of T wave inversion is positively correlated with the degree of tension. It should be noted that all vibration amplitudes appearing in the embodiments of the present invention are values ​​taken on the vertical axis of the corresponding curve, and no further details will be given later.

[0066] Furthermore, based on the fact that the P wave reference interval is negatively correlated with the stress level, and the QRS complex wave amplitude, ST wave fluctuation level, and T wave inversion level are all positively correlated with the stress level, the product of the negative correlation mapping value of the P wave reference interval, the QRS complex wave amplitude, the ST wave fluctuation level, and the T wave inversion level is normalized to determine the heart rate mapping stress level for each cardiac cycle time period. In a specific implementation of the embodiment of the present invention, the process of obtaining the heart rate mapping stress level is expressed by the formula: ;in, For the The heart rate maps stress levels during each cardiac cycle period; For the The time interval between the P wave representative moment of a cardiac cycle time period and the P wave representative moment of the previous cardiac cycle time period, that is, the time interval between the P wave representative moment of the first ... The P wave reference interval of a cardiac cycle time period; For the The maximum value of the ECG signal amplitude corresponding to the QRS complex wave time period on the ECG curve in each cardiac cycle time period; For the The minimum value of the ECG signal amplitude corresponding to the QRS complex wave time period in each cardiac cycle time period on the ECG curve; For the The amplitude difference of the ECG signal corresponding to the QRS complex wave time period in the ECG curve in each cardiac cycle time period, that is, the vibration amplitude of the QRS complex wave; For the The amplitude variance of the ECG signal at all moments in the ST wave time period in the cardiac cycle time period, that is, The degree of ST wave fluctuation in each cardiac cycle period; For the The mean amplitude of the ECG signal of the T wave at all moments corresponding to the ECG curve in a cardiac cycle period; For the The degree of T wave inversion during each cardiac cycle; is an exponential function with a natural constant as the base. Implementers can adopt other negative correlation mapping methods according to the specific implementation environment, such as 、 and the reciprocal, where is the hyperbolic tangent function, which will not be further described here; This is a linear normalization function. Implementers can adjust the normalization method according to the specific implementation environment. Normalization limits the value of the heart rate mapping stress level to between 0 and 1, facilitating subsequent comparative analysis.

[0067] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the tension level of electromyographic mapping includes:

[0068] Normalize the extreme difference of the vibration amplitude of the electromyographic signal corresponding to the electromyographic curve of the arm in each cardiac cycle time period to determine the tension level of the electromyographic mapping in each cardiac cycle time period. Because muscles usually experience abnormal contraction under the influence of tension, the larger the extreme difference of the vibration amplitude of the electromyographic signal corresponding to the electromyographic curve of the arm in each cardiac cycle time period, the more obvious the abnormal contraction of the muscles usually occurs, and the corresponding tension level is also greater. In a specific implementation of an embodiment of the present invention, the process of obtaining the tension level of the electromyographic mapping is expressed by the formula: ;in, For the The tension of electromyographic mapping during each cardiac cycle; For the The maximum value of the electromyographic signal vibration amplitude corresponding to each cardiac cycle period on the arm electromyographic curve; For the The minimum value of the vibration amplitude of the electromyographic signal corresponding to each cardiac cycle period on the electromyographic curve of the arm; For the The vibration amplitude of the electromyographic signal corresponding to each cardiac cycle period on the arm electromyographic curve is extremely poor; It is a linear normalization function. The implementer can adjust the normalization method according to the specific implementation environment. Through normalization, the value of the tension degree of the electromyographic mapping is limited to 0 to 1, which is convenient for subsequent comparative analysis.

[0069] Step S103: Determine the subject's initial stress level based on the overall magnitude of the myoelectric mapping stress level and the overall magnitude of the heart rate mapping stress level in all cardiac cycle time periods; determine the stress level credibility based on the similarity between the heart rate mapping stress level change trend and the electromyographic mapping stress level change trend corresponding to each cardiac cycle time period in chronological order; and correct the initial stress level based on the stress level credibility to determine the subject's corrected stress level.

[0070] The greater the subject's heart rate mapping and electromyography tension levels in each cardiac cycle time period, the greater the subject's tension level reflected by the ECG and EMG signals. Therefore, the initial tension level is determined by combining the overall magnitude of the EMG tension levels and the overall magnitude of the heart rate mapping tension levels across all cardiac cycle time periods. Furthermore, it is necessary to consider that tension can affect both the electrocardiogram and electromyography signals. If the changes in tension reflected by the electrocardiogram and electromyography signals are inconsistent, then the tension reflected by some ECG or EMG signals is not caused by tension. Therefore, the tension level credibility is further characterized based on the similarity between the trend of changes in the heart rate mapping and the trend of changes in the electromyography tension levels corresponding to each cardiac cycle time period in chronological order. The initial tension level is then corrected based on the tension credibility, resulting in a more accurate correction of the subject's tension level.

[0071] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the initial stress level includes:

[0072] The average of the heart rate-mapped tension levels across all cardiac cycle time periods was used as the overall heart rate tension level; the average of the myoelectricity-mapped tension levels across all cardiac cycle time periods was used as the overall myoelectricity tension level; and the product of the overall heart rate tension level and the overall myoelectricity tension level was used as the subject's initial tension level. The average value can characterize the overall magnitude of a set of data. Therefore, the greater the overall heart rate tension level and the overall myoelectricity tension level obtained from the average, the greater the overall heart rate tension level and myoelectricity tension level of the subject in each cardiac cycle time period, that is, the greater the subject's tension level as reflected by the ECG and EMG signals. Therefore, the subject's tension level was further measured by combining the overall heart rate tension level and the overall myoelectricity tension level through the product, which is also the initial tension level.

[0073] In a specific implementation of the embodiment of the present invention, the process of obtaining the initial stress level is expressed by the formula: ;in, is the subject's initial level of tension; The number of central dynamic cycle time periods in the test time period; For the The heart rate maps stress levels during each cardiac cycle period; For the The tension of electromyographic mapping during each cardiac cycle; It is the overall tension of heart rate; It is the overall tension of electromyography.

[0074] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the credibility of the stress level includes:

[0075] After arranging the heart rate-mapped stress levels across all time periods in chronological order, a time series of heart rate-mapped stress levels was determined. After arranging the electromyography-mapped stress levels across all time periods in chronological order, a time series of electromyography-mapped stress levels was determined. The Pearson correlation coefficient between the heart rate-mapped stress levels and the electromyography-mapped stress levels was used as the stress level reliability. Because stress affects both electrocardiogram and electromyography signals, ideally, the heart rate-mapped stress levels and the electromyography-mapped stress levels should exhibit a high degree of correlation in their temporal sequences to confirm that the initial stress level was entirely caused by stress. Therefore, the Pearson correlation coefficient was used to measure stress level reliability in terms of correlation. This reliability was then used to correct the initial stress level, resulting in a more accurate quantified stress level.

[0076] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the corrected stress level includes:

[0077] Since the greater the stress level reliability, the more accurately the corresponding initial stress level quantifies stress, the product of the stress level reliability and the initial stress level is normalized to determine the subject's revised stress level. In a specific implementation of the embodiment of the present invention, the process of obtaining the revised stress level is expressed as follows: ;in, is the subject's corrected tension level; is the subject's initial level of tension; = is the Pearson correlation coefficient between the stress level time series mapped by heart rate and the stress level time series mapped by electromyography, i.e., the stress level reliability. The greater the corresponding corrected stress level, the more stressed the subject is, and the greater the impact of stress on the initial pulmonary ventilation volume time series curve.

[0078] Step S104: Correcting the initial pulmonary ventilation volume time series curve according to the corrected tension level to determine a corrected pulmonary ventilation volume time series curve; and performing pulmonary ventilation function testing according to the corrected pulmonary ventilation volume time series curve.

[0079] Finally, based on the fact that tension affects the respiratory state of the subjects, the initial pulmonary ventilation volume time series curve is corrected by the corrected tension degree obtained by quantifying the tension emotion, so that the accuracy of pulmonary ventilation function detection based on the corrected pulmonary ventilation volume time series curve is higher.

[0080] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the modified pulmonary ventilation volume time series curve includes:

[0081] The final air volume adjustment value is determined by multiplying the product of the corrected tension level and the preset standard air volume adjustment value; the horizontal axis of the initial pulmonary ventilation volume time series curve is time, and the vertical axis is pulmonary ventilation volume; the inspiratory phase time period and the expiratory phase time period of the initial pulmonary ventilation volume time series curve are obtained; the sum of the pulmonary ventilation volume at each moment in the inspiratory phase time period and the final air volume adjustment value is used as the corrected air volume value at each moment in the inspiratory phase time period; the difference between the pulmonary ventilation volume at each moment in the expiratory phase time period and the final air volume adjustment value is used as the corrected air volume value at each moment in the expiratory phase time period. First, in terms of objective factors, the impact of tension on the subject is mainly reflected in the inability to reach the maximum inhalation level during the inhalation phase and the inability to reach the maximum exhalation level during the exhalation phase. Therefore, in the inhalation phase of the initial pulmonary ventilation volume time series curve, that is, the maximum inhalation phase and the second maximum inhalation phase b in the embodiment of the present invention, it is necessary to adjust it to be larger according to the correction tension level; conversely, in the exhalation phase, that is, the maximum exhalation phase a, it is necessary to adjust it to be smaller according to the correction tension level. Therefore, the inhalation phase time period and the exhalation phase time period need to be corrected in combination with different correction methods. In a specific implementation of the embodiment of the present invention, the preset standard gas volume adjustment value is set to half of the maximum gas volume in the tidal phase, which can be adjusted according to the specific implementation environment. It is essentially used for correction, and the tidal phase can reflect the breathing habits of the subject to a certain extent.

[0082] In a specific implementation of the embodiment of the present invention, the process of obtaining the corrected gas volume value during the inhalation phase is expressed as follows: ;in, The time during the inhalation phase Corrected gas volume value; The time during the inhalation phase The lung ventilation volume in the initial lung ventilation volume time series curve; is the subject's corrected tension level; It is the preset standard gas volume adjustment value; In a specific implementation of the embodiment of the present invention, the process of obtaining the corrected gas volume value during the exhalation phase is expressed as follows: ;in, The time during the exhalation phase Corrected gas volume value; The time during the exhalation phase The lung ventilation volume in the initial lung ventilation volume time series curve; is the subject's corrected tension level; It is the preset standard gas volume adjustment value; is the final gas volume adjustment value.

[0083] Considering that after the correction of the pulmonary ventilation volume in the inhalation phase and the exhalation phase, the corresponding corrected volume values ​​may be discontinuous in time series, the corrected volume values ​​at all moments corresponding to the inhalation phase and the exhalation phase are further replaced with the corresponding pulmonary ventilation volume on the initial pulmonary ventilation volume time series curve, and then interpolation processing is performed to determine the corrected pulmonary ventilation volume time series curve; the interpolation processing avoids the appearance of a piecewise function, making the corrected pulmonary ventilation volume time series curve smoother. After determining the corrected pulmonary ventilation volume time series curve, the pulmonary ventilation function test is performed in combination with the corrected pulmonary ventilation volume time series curve according to the conventional method in the pulmonary ventilation test. It should be noted that performing pulmonary ventilation testing based on the pulmonary ventilation volume time series curve is a technical means well known to those skilled in the art and will not be further elaborated here.

[0084] In summary, a pulmonary ventilation function detection method quantifies the tension level of the subject through the waveform change of the electrocardiogram curve and the amplitude fluctuation of the arm electromyography curve to determine the initial tension level, and corrects the initial tension level based on the characteristic that the tension expressions presented by the electrocardiogram curve and the arm electromyography curve when the subject is nervous are consistent, so as to determine the corrected tension level that more accurately represents the tension level; and then corrects the initial pulmonary ventilation volume time series curve based on the corrected tension level, thereby solving the problem of inaccurate measurement of the subject's pulmonary ventilation function by the existing pulmonary ventilation volume test directly based on the subject's pulmonary ventilation volume time series curve, and making the pulmonary ventilation function detection based on the corrected pulmonary ventilation volume time series curve more accurate.

[0085] This application also provides a pulmonary ventilation function detection system, please refer to Figure 3 , which shows a structural diagram of a pulmonary ventilation function detection system provided by an embodiment of the present invention, the system includes: a data acquisition and preprocessing module 301, a first determination module 302, a second determination module 303 and a pulmonary ventilation function detection module 304.

[0086] The data acquisition and preprocessing module 301 is used to acquire the initial lung ventilation volume time series curve, electrocardiogram curve, and arm electromyography curve during the test period corresponding to the subject's lung ventilation test process; and divide the test period into at least two cardiac cycle time periods according to the cardiac cycle in the electrocardiogram curve;

[0087] The first determining module 302 is configured to determine the heart rate mapping intensity of each cardiac cycle time period based on the waveform changes in each cardiac cycle time period in the electrocardiogram curve; and to determine the myoelectric mapping intensity of each cardiac cycle time period based on the myoelectric signal amplitude fluctuations in each cardiac cycle time period in the arm electromyography curve;

[0088] The second determination module 303 is configured to determine the subject's initial stress level based on the overall magnitude of the stress level mapped by the electromyography and the overall magnitude of the stress level mapped by the heart rate in all cardiac cycle time periods; determine the stress level credibility based on the similarity between the stress level change trends mapped by the heart rate and the stress level change trends mapped by the electromyography corresponding to each cardiac cycle time period in chronological order; and modify the initial stress level based on the stress level credibility to determine the modified stress level of the subject;

[0089] The pulmonary ventilation function detection module 304 is used to modify the initial pulmonary ventilation volume time series curve according to the modified tension level to determine a modified pulmonary ventilation volume time series curve; and perform pulmonary ventilation function detection according to the modified pulmonary ventilation volume time series curve.

[0090] It should be noted that the system provided in the above embodiment is merely illustrated by the division of the aforementioned functional modules. In actual applications, the aforementioned functions can be assigned to different functional modules as needed, i.e., the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the pulmonary ventilation function testing system and the pulmonary ventilation function testing method provided in the above embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0091] The present application also provides a pulmonary ventilation function detection device. Figure 4 , which shows a schematic structural diagram of a pulmonary ventilation function detection device provided by an embodiment of the present invention, the device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402, wherein when the processor 402 executes the computer program 403, the device can perform any one of the pulmonary ventilation function detection methods introduced above.

[0092] An embodiment of the present application also provides a computer program product. When the computer program product is run on a computer device, the computer device can execute any one of the pulmonary ventilation function detection methods introduced above.

[0093] An embodiment of the present application also provides a computer-readable storage medium, in which computer program code is stored. When the computer program code is run on a computer device, the computer device can execute any one of the pulmonary ventilation function detection methods introduced above.

[0094] In the embodiments provided in the present application, it should be understood that the provided computer devices, computer program products and computer-readable storage media are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the methods provided above and will not be repeated here.

[0095] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0096] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for detecting pulmonary ventilation function, characterized in that: The method comprises: Collecting an initial lung ventilation volume time series curve, an electrocardiogram curve, and an arm electromyography curve within a test time period corresponding to a lung ventilation test process of the subject; dividing the test time period into at least two cardiac cycle time periods according to a cardiac cycle in the electrocardiogram curve; In the electrocardiogram curve, the heart rate mapping intensity of each cardiac cycle period is determined according to the waveform changes in each cardiac cycle period; in the arm electromyography curve, the myoelectric mapping intensity of each cardiac cycle period is determined according to the myoelectric signal amplitude fluctuations in each cardiac cycle period; Determining the subject's initial stress level based on the overall magnitude of the stress level mapped by the electromyography and the overall magnitude of the stress level mapped by the heart rate in all cardiac cycle time periods; determining the stress level credibility based on the similarity between the stress level change trends mapped by the heart rate and the stress level changed by the electromyography corresponding to each cardiac cycle time period in chronological order; and correcting the initial stress level based on the stress level credibility to determine the subject's corrected stress level; The initial pulmonary ventilation volume time series curve is corrected according to the corrected tension level to determine a corrected pulmonary ventilation volume time series curve; and pulmonary ventilation function detection is performed according to the corrected pulmonary ventilation volume time series curve.

2. A method for detecting pulmonary ventilation function according to claim 1, characterized in that: The process of obtaining the cardiac cycle time period includes: The electrocardiogram curve is input into a trained convolutional neural network to output each cardiac cycle; the time period of each cardiac cycle in the test time period is used as the corresponding cardiac cycle time period.

3. A method for detecting pulmonary ventilation function according to claim 1, characterized in that: The process of obtaining the heart rate mapping stress level includes: Inputting the local curve corresponding to each cardiac cycle time period in the electrocardiogram curve into the trained convolutional neural network, and outputting the P wave time period, QRS complex wave time period, ST wave time period and T wave time period in each cardiac cycle time period; The center moment of the P wave time period in each cardiac cycle time period is used as the P wave representative moment of each cardiac cycle time period; the time interval between the P wave representative moment of each cardiac cycle time period and the P wave representative moment of the previous cardiac cycle time period is used as the P wave reference interval of each cardiac cycle time period; Determining the QRS complex wave vibration amplitude of each cardiac cycle time period according to the ECG signal amplitude extreme difference corresponding to the QRS complex wave time period in each cardiac cycle time period on the ECG curve; Determining the ST wave fluctuation degree of each cardiac cycle time period according to the ECG signal amplitude variance at all moments in the ST wave time period in each cardiac cycle time period; performing negative correlation normalization on the mean values ​​of the electrocardiographic signal amplitudes of the T wave at all moments corresponding to the electrocardiographic curve in each cardiac cycle time period to determine the degree of T wave inversion in each cardiac cycle time period; The product of the negative correlation mapping value of the P wave reference interval, the QRS complex wave vibration amplitude, the ST wave fluctuation degree and the T wave inversion degree is normalized to determine the heart rate mapping tension of each cardiac cycle time period.

4. A method for detecting pulmonary ventilation function according to claim 1, characterized in that: The process of obtaining the tension level of electromyography mapping includes: The myoelectric signal vibration amplitude extreme difference corresponding to each cardiac cycle time period on the arm electromyographic curve is normalized to determine the myoelectric mapping tension level of each cardiac cycle time period.

5. A method for detecting pulmonary ventilation function according to claim 1, characterized in that: The process of obtaining the initial tension level includes: The average of the heart rate mapping tension levels of all cardiac cycle time periods is taken as the overall heart rate tension level; the average of the electromyography mapping tension levels of all cardiac cycle time periods is taken as the overall electromyography tension level; and the product of the overall heart rate tension level and the overall electromyography tension level is taken as the subject's initial tension level.

6. A method for detecting pulmonary ventilation function according to claim 1, characterized in that: The process of obtaining the credibility of the tension level includes: After arranging the heart rate mapping tension levels of all periodic time periods in chronological order, a heart rate mapping tension level time series sequence is determined; after arranging the electromyography mapping tension levels of all periodic time periods in chronological order, a myoelectric mapping tension level time series sequence is determined; and the Pearson correlation coefficient between the heart rate mapping tension level time series sequence and the electromyography mapping tension level time series sequence is used as the tension level credibility.

7. A method for detecting pulmonary ventilation function according to claim 1, characterized in that: The process of obtaining the corrected tension level includes: The product of the stress level reliability and the initial stress level is normalized to determine the subject's revised stress level.

8. A method for detecting pulmonary ventilation function according to claim 1, characterized in that: The process of obtaining the modified pulmonary ventilation volume time series curve includes: The final air volume adjustment value is determined by multiplying the product of the corrected tension level and the preset standard air volume adjustment value; the horizontal axis of the initial pulmonary ventilation volume time series curve is time, and the vertical axis is pulmonary ventilation volume; Obtaining the inspiratory phase time period and the expiratory phase time period of the initial pulmonary ventilation volume time series curve; taking the sum of the pulmonary ventilation volume at each moment in the inspiratory phase time period and the final air volume adjustment value as the corrected air volume value at each moment in the inspiratory phase time period; The difference between the lung ventilation volume at each moment in the expiratory phase time period and the final air volume adjustment value is used as the corrected air volume value at each moment in the expiratory phase time period; On the initial pulmonary ventilation volume time series curve, the corrected gas volume values ​​at all moments corresponding to the inspiration phase and the expiration phase are substituted for the corresponding pulmonary ventilation volume and then interpolated to determine the corrected pulmonary ventilation volume time series curve.

9. A pulmonary ventilation function detection system, characterized in that: The system comprises: A data acquisition and preprocessing module is used to acquire the initial lung ventilation volume time series curve, electrocardiogram curve and arm electromyography curve within the test time period corresponding to the subject's lung ventilation test process; and divide the test time period into at least two cardiac cycle time periods according to the cardiac cycle in the electrocardiogram curve; The first determination module is configured to determine the heart rate mapping intensity of each cardiac cycle time period based on the waveform changes in each cardiac cycle time period in the electrocardiogram curve; and to determine the myoelectric mapping intensity of each cardiac cycle time period based on the myoelectric signal amplitude fluctuations in each cardiac cycle time period in the arm electromyography curve; The second determination module is configured to determine the subject's initial stress level based on the overall magnitude of the stress level mapped by the electromyography and the overall magnitude of the stress level mapped by the heart rate in all cardiac cycle time periods; determine the stress level credibility based on the similarity between the stress level change trends mapped by the heart rate and the stress level change trends mapped by the electromyography corresponding to each cardiac cycle time period in chronological order; and modify the initial stress level based on the stress level credibility to determine the modified stress level of the subject; The pulmonary ventilation function detection module is used to correct the initial pulmonary ventilation volume time series curve according to the corrected tension level, determine the corrected pulmonary ventilation volume time series curve; and perform pulmonary ventilation function detection according to the corrected pulmonary ventilation volume time series curve.

10. A pulmonary ventilation function detection device, characterized in that: It comprises a memory and a processor; wherein the memory is used to store computer program code that can be run on the processor; the processor is used to call and run the computer program code from the memory to implement the steps of a pulmonary ventilation function detection method as described in any one of claims 1 to 8.

Images