Method and device for constructing lung function characteristics during sleep

Abstract

The present invention provides a method and device for constructing pulmonary function characteristics during sleep. The method is applicable to the field of pulmonary function data processing. The method comprises: acquiring a target subject's respiratory velocity waveform; determining the inhalation and exhalation phases within each respiratory cycle based on the respiratory velocity waveform; determining the duration of each phase based on the inhalation and exhalation phases, obtaining the duration of the inhalation sub-phase and the duration of the exhalation sub-phase; and calculating basic features, a stability measurement feature group, and a comprehensive feature group based on the duration of the inhalation and exhalation sub-phases. The present invention achieves burden-free acquisition of respiratory velocity waveforms and constructs a comprehensive pulmonary function assessment feature group applicable to radar respiratory waveforms.

Description

Technical Field

[0001] The present invention relates to the field of lung function data processing, and in particular to a method and device for constructing lung function characteristics during sleep. Background Art

[0002] Pulmonary function assessment has important clinical value in the diagnosis and treatment of respiratory diseases. It can objectively measure the ventilation and gas exchange functions of the lungs, providing a key basis for disease diagnosis, condition assessment, formulation of treatment plans and prognosis judgment.

[0003] Under active breathing, traditional spirometry uses the ratio of the subject's forced expiratory volume in one second to the forced vital capacity to measure the strength of their lung function; or uses sensors to monitor the subject's respiratory movements during sleep and determines whether the subject's lung function is normal by analyzing the pattern of the respiratory waveform in a specific sleep stage.

[0004] However, both traditional spirometry and contact sensor monitoring methods for assessing lung function have limitations. Traditional spirometry estimates a subject's lung function by measuring the ratio of their forced expiratory volume in one second to their forced vital capacity. This requires the subject to actively cooperate with forced breathing, limiting its application in groups such as the elderly and those with severe illnesses. Furthermore, imprecise manual control during active breathing can easily lead to measurement bias. Contact sensors monitor a subject's nocturnal breathing patterns to assess lung function, but these sensors can interfere with the subject's natural sleep, causing measurement bias. Summary of the Invention

[0005] In view of this, on the one hand, the present invention provides a method for constructing lung function characteristics during sleep, including: collecting the respiratory rate waveform of the target object; determining the inhalation stage and the exhalation stage in each respiratory cycle based on the respiratory rate waveform; determining the duration of each stage based on the inhalation stage and the exhalation stage, and obtaining the inhalation sub-stage duration and the exhalation sub-stage duration; calculating basic features, a stability measurement feature group, and a comprehensive feature group based on the inhalation sub-stage duration and the exhalation sub-stage duration.

[0006] Optionally, determining the inhalation phase and exhalation phase in each respiratory cycle based on the respiratory rate waveform includes: determining the maximum respiratory rate and the minimum respiratory rate in the respiratory rate waveform based on the respiratory rate waveform; removing a preset proportion of numerical points at the maximum respiratory rate end and the minimum respiratory rate end in the respiratory rate waveform to obtain a first respiratory rate waveform; calculating a first respiratory rate threshold based on the maximum respiratory rate of the first respiratory rate waveform; calculating a second respiratory rate threshold based on the minimum respiratory rate of the first respiratory rate waveform; determining each respiratory cycle based on the first respiratory rate threshold and the second respiratory rate threshold, as well as the inhalation phase and exhalation phase in each respiratory cycle, the inhalation phase including the inhalation phase sub-phase and the inhalation plateau sub-phase, and the exhalation phase including the exhalation phase sub-phase and the exhalation plateau sub-phase.

[0007] Optionally, the duration of each stage is determined based on the inhalation stage and the exhalation stage to obtain the inhalation sub-stage duration and the exhalation sub-stage duration, including: determining the duration of the inhalation phase sub-stage and the exhalation phase sub-stage based on the respiratory rate waveform respectively to obtain the inhalation phase sub-stage duration and the exhalation phase sub-stage duration; dividing the inhalation phase sub-stage duration based on the extreme point of the respiratory rate waveform of the inhalation phase sub-stage to obtain the first inhalation phase sub-stage duration and the second inhalation phase sub-stage duration; determining the duration of the inhalation plateau sub-stage based on the respiratory rate waveform to obtain the inhalation plateau sub-stage duration; dividing the expiratory phase sub-stage duration based on the extreme point of the respiratory rate waveform of the expiratory phase sub-stage to obtain the first expiratory phase sub-stage duration and the second expiratory phase sub-stage duration; determining the duration of the expiratory plateau sub-stage based on the respiratory rate waveform to obtain the expiratory plateau sub-stage duration.

[0008] Optionally, basic features are calculated based on the inspiratory sub-stage duration and the expiratory sub-stage duration, including: calculating the duration of each respiratory cycle based on the first inspiratory phase sub-stage duration, the second inspiratory phase sub-stage duration, the inspiratory plateau sub-stage duration, the first expiratory phase sub-stage duration, the second expiratory phase sub-stage duration, and the expiratory plateau sub-stage duration to obtain the total duration of the respiratory cycle; calculating the proportion of the expiratory phase sub-stage duration and the expiratory plateau sub-stage duration in the total duration of the respiratory cycle based on the expiratory phase sub-stage duration, the expiratory plateau sub-stage duration, and the total duration of the respiratory cycle to obtain the expiratory phase duration ratio; calculating the proportion of the expiratory plateau sub-stage duration in the expiratory phase sub-stage duration based on the expiratory plateau sub-stage duration and the expiratory phase sub-stage duration to obtain the expiratory plateau index; calculating the integrated area based on the respiratory velocity waveform of the inspiratory phase sub-stage within the respiratory cycle to obtain the inspiratory effort; calculating the number of time points where the first-order derivative is zero based on the respiratory velocity waveform within the respiratory cycle to obtain the inspiratory phase jitter index.

[0009] Optionally, a smoothness measurement feature group is calculated based on the duration of the inhalation sub-stage and the duration of the exhalation sub-stage, including: calculating the standard deviation and the average value based on all respiratory cycle durations of the target object; calculating the proportion of the standard deviation to the average value based on the standard deviation and the average value to obtain a respiratory rhythm disorder index; calculating the difference in the time-integrated area of ​​the respiratory speed waveform of each respiratory cycle and the respiratory speed waveform after low-pass filtering based on the respiratory speed waveform of each respiratory cycle; performing smoothing calculation based on the difference and the maximum value of the respiratory speed waveform of each respiratory cycle to obtain the smoothness of the respiratory speed waveform; calculating the number of events in which the absolute value of the time-integrated area of ​​the respiratory speed waveform of each respiratory cycle within a preset time is greater than twice the average value of the time-integrated area of ​​the respiratory speed waveform of each respiratory cycle based on the respiratory speed waveform of each respiratory cycle to obtain a paroxysmal respiratory enhancement index during sleep.

[0010] Optionally, a comprehensive feature group is calculated based on the duration of the inhalation sub-phase and the duration of the exhalation sub-phase, including: based on the respiratory velocity waveform of each respiratory cycle, calculating the energy of the Fourier transformed respiratory velocity waveform of each respiratory cycle within a first preset frequency range to obtain the second harmonic energy; based on the respiratory velocity waveform of each respiratory cycle, calculating the energy of the Fourier transformed respiratory velocity waveform of each respiratory cycle within a second preset frequency range to obtain the fundamental harmonic energy; based on the second harmonic energy and the fundamental harmonic energy, calculating the ratio of the second harmonic energy to the fundamental harmonic energy to obtain the harmonic energy proportion.

[0011] Optionally, collecting the respiratory speed waveform of the target object includes: collecting a first radar echo signal and a second radar echo signal of the movement of a first target part and a second radar echo signal of the movement of a second target part of the target object within a preset time period through a millimeter wave radar; extracting waveforms representing the respiratory movement from the first radar echo signal and the second radar echo signal respectively to obtain a first respiratory movement waveform and a second respiratory movement waveform; and performing weighted summation on the first respiratory movement waveform and the second respiratory movement waveform to obtain a respiratory speed waveform.

[0012] Optionally, the present invention provides a method for constructing lung function characteristics during sleep, further comprising: calculating the respiratory dominance of the second target part and the respiratory contradiction index of the two target parts based on the first respiratory motion waveform and the second respiratory motion waveform.

[0013] Optionally, the respiratory dominance of the second target part and the respiratory contradiction index of the two target parts are calculated based on the first respiratory motion waveform and the second respiratory motion waveform, including: calculating the total energy within a preset time length based on the first respiratory motion waveform to obtain the total energy of the first target part; calculating the total energy within a preset time length based on the second respiratory motion waveform to obtain the total energy of the second target part; calculating the ratio of the total energy of the second target part to the total energy of the first target part based on the total energy of the first target part and the total energy of the second target part to obtain the respiratory dominance of the second target part; calculating the absolute value of the difference between the first respiratory motion waveform and the second respiratory motion waveform based on the first respiratory motion waveform and the second respiratory motion waveform; calculating the proportion of the absolute value of the difference to the preset time length based on the absolute value of the difference and the preset time length to obtain the respiratory contradiction index of the two target parts.

[0014] The second aspect of the present invention provides a device for constructing lung function characteristics during sleep, which includes: a processor and a memory connected to the processor; wherein the memory stores instructions that can be executed by the processor, and the instructions are executed by the processor to enable the processor to execute the above-mentioned method for constructing lung function characteristics during sleep.

[0015] The present invention collects the respiratory velocity waveform of the target object throughout the night, and then determines the inhalation and exhalation stages in each respiratory cycle based on the waveform, and then calculates the duration of each stage, obtains the duration of the inhalation sub-stage and the duration of the exhalation sub-stage, and finally calculates the basic features, the stability measurement feature group and the comprehensive feature group based on these durations. This method of collecting respiratory velocity waveforms using millimeter wave radar can create a natural and undisturbed detection environment for the target object, so that it does not need to actively cooperate during the detection process, which significantly improves the comfort and convenience of the detection process. The lung function of the target object is evaluated in a burden-free manner, which reduces the difficulty of lung function evaluation and is particularly suitable for target objects that cannot achieve deep breathing; the measurement error caused by active cooperation is reduced, and the respiratory state can be detected more objectively and a large amount of reference data can be obtained; the respiratory phase can be accurately divided, and a comprehensive lung function evaluation feature group suitable for radar respiratory waveforms can be constructed to evaluate lung respiratory function from multiple aspects such as the characteristics of the inhalation and exhalation phases, respiratory stability, and chest-abdomen relationship, which is comprehensive and practical.

[0016] The present invention determines the maximum value of the respiratory velocity waveform, removes the preset proportional numerical points at both ends of the maximum value, and obtains a first respiratory velocity waveform. Thresholds are calculated based on these maximum values. The thresholds are then used to determine the respiratory cycle and the inhalation and exhalation phases of each respiratory cycle, as well as their subphases, facilitating accurate analysis of respiratory characteristics. Using the two-line method to divide respiratory phases helps effectively address signal fluctuations caused by noise or body vibration during the respiratory-inhalation alternation process, allowing for more accurate division of respiratory phases. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are 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.

[0018] Figure 1 Flowchart of a method for constructing lung function characteristics during sleep in an embodiment of the present invention;

[0019] Figure 2 A respiratory velocity waveform diagram of one respiratory cycle in the respiratory velocity waveform in an embodiment of the present invention;

[0020] Figure 3 is a time distribution diagram of each sub-phase of a respiratory cycle in an embodiment of the present invention;

[0021] Figure 4 4 is a respiratory motion waveform diagram of the chest and abdomen in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0023] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0024] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; internal connections between two components; wireless connections or wired connections. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0025] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0026] like Figure 1 As shown, an embodiment of the present invention provides a method for constructing lung function characteristics during sleep, which is executed by an electronic device such as a computer or a server, and specifically includes:

[0027] S1, collect the respiratory rate waveform of the target subject.

[0028] Data is collected from the target subject's breathing process to detect the target subject's respiratory velocity waveform during sleep. For example, millimeter-wave radar can be used for overnight data collection. The radar can be placed 1 meter above the bedside to collect data. The respiratory velocity waveform is a waveform that relates time and respiratory velocity. In this embodiment, the target subject can be a human subject, and the subject's age, gender, body shape, etc. are not limited.

[0029] S2, determining the inhalation phase and the exhalation phase in each respiratory cycle based on the respiratory velocity waveform.

[0030] The target subject's breathing process throughout the night is divided into several breathing cycles, and the inhalation phase and exhalation phase of each breathing cycle need to be determined.

[0031] S3, determining the duration of each phase based on the inhalation phase and the exhalation phase, and obtaining the duration of the inhalation sub-phase and the duration of the exhalation sub-phase.

[0032] Based on the determined inhalation phase and exhalation phase of each respiratory cycle, the duration of each of the two phases is calculated respectively, thereby obtaining the duration of the inhalation sub-phase and the duration of the exhalation sub-phase.

[0033] S4: Calculate basic features, a stability measurement feature group, and a comprehensive feature group based on the duration of the inhalation sub-phase and the duration of the exhalation sub-phase.

[0034] Using the previously obtained duration of the inhalation sub-phase and the exhalation sub-phase of each respiratory cycle, the basic features used to describe the respiratory characteristics, the smoothness measurement feature group for measuring the stability of the respiratory process, and the comprehensive feature group for comprehensively measuring the target subject's lung breathing capacity are calculated respectively.

[0035] This embodiment collects the respiratory velocity waveform of the target object throughout the night, and then determines the inhalation and exhalation phases in each respiratory cycle based on the waveform, and then calculates the duration of each phase to obtain the duration of the inhalation sub-phase and the duration of the exhalation sub-phase. Finally, based on these durations, the basic features, the stability measurement feature group, and the comprehensive feature group are calculated. This method of collecting respiratory velocity waveforms using millimeter wave radar can create a natural and undisturbed detection environment for the target object, so that it does not need to actively cooperate during the detection process, significantly improving the comfort and convenience of the detection process. It assesses the lung function of the target object in a burden-free manner, reduces the difficulty of lung function assessment, and is particularly suitable for target objects that cannot achieve deep breathing; reduces the measurement error caused by active cooperation, can more objectively detect the respiratory state and obtain a large amount of reference data; has a strong anti-noise effect and can accurately divide the respiratory phase; the comprehensive lung function assessment feature group constructed for radar respiratory waveforms assesses lung respiratory function from multiple aspects such as the characteristics of the inhalation and exhalation phases, respiratory stability, and chest-abdomen relationship, which is comprehensive and practical.

[0036] In some optional implementations of this embodiment, collecting the respiratory velocity waveform of the target object in step S1 specifically includes:

[0037] S11 , collecting a first radar echo signal and a second radar echo signal of a first target part and a second target part of a target object during a preset time period by monitoring the target object through a millimeter wave radar.

[0038] For example, the preset duration can be set based on the target subject's sleep duration, ensuring that the collected radar echo signals cover the entire sleep stage and more comprehensively and accurately reflect the target subject's breathing characteristics during sleep. The first target site and the second target site both refer to sites that characterize the target subject's breathing, such as the chest and abdomen. The chest and abdomen experience significant ups and downs during human respiration. By monitoring the radar echo signals generated by the movement of the chest and abdomen using millimeter-wave radar, respiration-related information can be effectively obtained.

[0039] S12 , respectively extracting waveforms representing respiratory motion from the first radar echo signal and the second radar echo signal to obtain a first respiratory motion waveform and a second respiratory motion waveform.

[0040] A respiratory motion waveform for characterizing respiratory motion is extracted from radar echo signals at two locations. In addition to the respiratory motion waveform, other waveforms for characterizing respiratory motion can also be extracted for subsequent feature construction, such as a phase waveform, a displacement waveform, and the like.

[0041] S13 , performing weighted summation on the first respiratory motion waveform and the second respiratory motion waveform to obtain a respiratory velocity waveform.

[0042] The first respiratory motion waveform corresponding to the movement of the first target area (such as the chest) extracted from the radar echo signal and the second respiratory motion waveform corresponding to the movement of the second target area (such as the abdomen) are added together according to a certain weighting coefficient to ultimately obtain a respiratory velocity waveform that can represent the target subject's respiratory velocity changes. This weighted summation method considers the combined impact of the movement of different respiratory-related areas on the overall respiratory velocity, thereby obtaining more representative respiratory velocity characteristic data.

[0043] This embodiment uses millimeter-wave radar to monitor radar echo signals from the movement of first and second target parts of a target subject for a preset duration, which is set based on sleep duration. This allows for comprehensive and accurate reflection of sleep breathing characteristics. The first and second respiratory motion waveforms are extracted from the echo signals, and finally, a weighted summation of the first and second respiratory motion waveforms is performed to obtain a respiratory velocity waveform. This comprehensively considers the impact of movement of different parts on respiratory velocity, resulting in more representative respiratory velocity characteristic data, which facilitates accurate analysis of the target subject's breathing.

[0044] In some optional implementations of this embodiment, determining the inhalation phase and the exhalation phase in each respiratory cycle based on the respiratory velocity waveform in step S2 specifically includes:

[0045] S21 , determining a maximum respiratory rate value and a minimum respiratory rate value in the respiratory rate waveform based on the respiratory rate waveform.

[0046] Compare and analyze the respiratory speed values ​​represented by each point on the respiratory speed waveform, and find the respiratory speed corresponding to the point with the largest value as the maximum respiratory speed, and the respiratory speed corresponding to the point with the smallest value as the minimum respiratory speed.

[0047] S22 , removing a preset proportion of numerical points at the maximum respiratory velocity end and the minimum respiratory velocity end in the respiratory velocity waveform to obtain a first respiratory velocity waveform.

[0048] In the respiratory velocity waveform, the numerical points corresponding to the maximum respiratory velocity and the minimum respiratory velocity according to a preset ratio are removed respectively, and the waveform formed by the remaining numerical points is the first respiratory velocity waveform. The preset ratio can be set to 10%.

[0049] S23: Calculate a first respiratory speed threshold based on the maximum respiratory speed value of the first respiratory speed waveform.

[0050] Exemplarily, the first respiratory rate threshold is calculated as follows:

[0051] ,

[0052] in, represents the first respiratory rate threshold, represents the first respiratory velocity waveform, Indicates the maximum respiratory velocity of the first respiratory velocity waveform.

[0053] S24: Calculate a second respiratory speed threshold based on the minimum respiratory speed value of the first respiratory speed waveform.

[0054] ,

[0055] in, represents the second respiratory rate threshold, Indicates the minimum respiratory velocity value of the first respiratory velocity waveform.

[0056] S25, determining each respiratory cycle, and an inhalation phase and an exhalation phase in each respiratory cycle based on the first respiratory rate threshold and the second respiratory rate threshold, wherein the inhalation phase includes an inhalation phase sub-phase and an inhalation plateau sub-phase, and the exhalation phase includes an exhalation phase sub-phase and an exhalation plateau sub-phase.

[0057] The respiratory cycle is divided into two parts using the double-line method. Figure 2 For example, the respiratory rate waveform The respiratory rate waveform of one respiratory cycle in - is a breathing cycle, in which and The interval is the inhalation phase, and The interval is the inhalation platform sub-stage, and The interval is the exhalation phase. and The interval is the expiratory plateau subphase.

[0058] This embodiment determines the maximum value of the respiratory velocity waveform, removes a preset proportional number of points at either end of the maximum value, and generates a first respiratory velocity waveform. Thresholds are then calculated based on these maximum values. The thresholds are then used to determine the respiratory cycle and the inhalation and exhalation phases, as well as their subphases, within each respiratory cycle. This facilitates accurate analysis of respiratory characteristics. Using the two-line method to delineate respiratory phases helps mitigate signal fluctuations caused by noise or body movement during the respiratory-inhalation cycle, allowing for more precise delineation of respiratory phases.

[0059] In some optional implementations of this embodiment, determining the duration of each phase based on the inhalation phase and the exhalation phase in step S3 to obtain the duration of the inhalation sub-phase and the duration of the exhalation sub-phase specifically includes:

[0060] S31 , determining the duration of the inhalation phase sub-stage and the exhalation phase sub-stage based on the respiratory velocity waveform, respectively, to obtain the inhalation phase sub-stage duration and the exhalation phase sub-stage duration.

[0061] Taking one of the respiratory cycles as an example, the respiratory velocity waveform is analyzed to determine the duration of each of the inspiratory phase sub-stage and the expiratory phase sub-stage, thereby obtaining the duration of the inspiratory phase sub-stage and the duration of the expiratory phase sub-stage.

[0062] S32 , dividing the inspiratory phase sub-phase duration based on the extreme value points of the respiratory velocity waveform in the inspiratory phase sub-phase to obtain a first inspiratory phase sub-phase duration and a second inspiratory phase sub-phase duration.

[0063] The duration of the inspiratory phase sub-stage is divided based on the extreme point (maximum value) on the respiratory velocity waveform of the inspiratory phase sub-stage, thereby obtaining the duration of the first inspiratory phase sub-stage and the duration of the second inspiratory phase sub-stage.

[0064] S33: Determine the duration of the inspiratory plateau sub-phase based on the respiratory velocity waveform to obtain the duration of the inspiratory plateau sub-phase.

[0065] By analyzing and processing the respiratory velocity waveform, the time spent in the inspiratory plateau sub-phase is determined, thereby obtaining the duration of the inspiratory plateau sub-phase.

[0066] S34 , dividing the expiratory phase sub-phase duration based on the extreme value points of the respiratory velocity waveform in the expiratory phase sub-phase to obtain a first expiratory phase sub-phase duration and a second expiratory phase sub-phase duration.

[0067] The duration of the expiratory phase sub-stage is divided according to the extreme point (minimum value) on the respiratory velocity waveform of the expiratory phase sub-stage, and finally the duration of the first expiratory phase sub-stage and the duration of the second expiratory phase sub-stage are obtained.

[0068] S35 , determining the duration of the exhalation plateau sub-phase based on the respiratory velocity waveform to obtain the duration of the exhalation plateau sub-phase.

[0069] The duration of the expiratory plateau sub-phase is determined according to the respiratory velocity waveform, and then the duration of the expiratory plateau sub-phase is obtained.

[0070] like Figure 3 As shown, it is the duration distribution of each sub-phase of a respiratory cycle, where is the duration of the first inhalation phase, is the duration of the second inhalation phase, is the duration of the inhalation platform sub-phase, is the duration of the first expiratory phase, is the duration of the second expiratory phase, The duration of the remaining breathing cycles is the same as that of steps S31-S35.

[0071] This embodiment analyzes and processes the respiratory velocity waveform, divides the duration of the inspiratory phase sub-stage and the duration of the expiratory phase sub-stage based on the waveform extreme points, and obtains two inspiratory phase sub-stage durations and two expiratory phase sub-stage durations. At the same time, the duration of the inspiratory plateau sub-stage and the expiratory plateau sub-stage are determined based on the respiratory velocity waveform, providing more detailed and accurate time parameters for respiratory characteristic analysis.

[0072] In some optional implementations of this embodiment, the basic features are calculated based on the duration of the inhalation sub-phase and the duration of the exhalation sub-phase in step S4, specifically including:

[0073] S41a, based on the duration of the first inspiratory phase sub-stage, the duration of the second inspiratory phase sub-stage, the duration of the inspiratory plateau sub-stage, the duration of the first expiratory phase sub-stage, the duration of the second expiratory phase sub-stage, and the duration of the expiratory plateau sub-stage, the duration of each respiratory cycle is calculated to obtain the total duration of the respiratory cycle.

[0074] Exemplarily, the total duration of each respiratory cycle is calculated using the following method:

[0075] ,

[0076] in, Indicates the total duration of each respiratory cycle, Indicates the duration of each sub-stage.

[0077] Under normal circumstances, the human respiratory cycle is typically between 3 and 5 seconds. However, patients with impaired lung function often experience elevated respiratory rates, which can cause their respiratory cycles to exhibit characteristics different from those of normal individuals. To more accurately measure the respiratory cycles of these subjects, the duration of each of the six sub-phases within a respiratory cycle is accumulated to determine the total duration of the respiratory cycle, resulting in a more accurate calculation of the respiratory cycle.

[0078] S42a, based on the duration of the expiratory phase sub-phase, the duration of the expiratory plateau sub-phase, and the total duration of the respiratory cycle, calculate the proportion of the duration of the expiratory phase sub-phase and the duration of the expiratory plateau sub-phase to the total duration of the respiratory cycle to obtain the expiratory phase duration ratio.

[0079] For example, the expiratory phase duration ratio is calculated as follows:

[0080] ,

[0081] in, Indicates the proportion of expiratory phase duration.

[0082] This feature can be used to assess respiratory function and increased expiratory resistance in subjects with chronic obstructive pulmonary disease (COPD). For subjects with increased expiratory resistance, the duration of exhalation during sleep accounts for a larger proportion of the respiratory cycle. Calculating the expiratory phase duration ratio provides a visual reflection of the expiratory proportion.

[0083] S43a, based on the duration of the expiratory plateau sub-phase and the duration of the expiratory phase sub-phase, calculating the proportion of the duration of the expiratory plateau sub-phase to the duration of the expiratory phase sub-phase, to obtain an expiratory plateau index.

[0084] Exemplarily, the expiratory plateau index is calculated as follows:

[0085] ,

[0086] in, Indicates expiratory plateau index.

[0087] This feature is used to measure the ratio of the period when the exhalation velocity is less than the threshold (i.e., the duration of the exhalation plateau sub-stage) to the duration of the exhalation phase sub-stage during the target subject's sleep breathing at night.

[0088] S44a, based on the respiratory velocity waveform of the inspiratory phase within the respiratory cycle, calculate the integrated area to obtain the inspiratory effort.

[0089] Exemplarily, the inspiratory effort is calculated as follows:

[0090] ,

[0091] in, Indicates the inhalation effort.

[0092] This feature is used to assess inspiratory effort in subjects with muscle weakness and diaphragmatic paralysis, as inspiratory effort is significantly reduced in these subjects. The integral of the inspiratory subphase represents the displacement of the chest and abdomen during inspiration, and this displacement is used to measure inspiratory effort.

[0093] S45a, based on the respiratory velocity waveform in the respiratory cycle, calculate the number of time points where the first-order derivative is zero to obtain an inspiratory phase jitter index.

[0094] Exemplarily, the inspiratory jitter index is calculated as follows:

[0095] ,

[0096] in, Indicates the inspiratory phase jitter index, Respiratory rate waveform The first derivative of express The number of extreme points.

[0097] Alternatively, it can be expressed as:

[0098] ,

[0099] This feature is used to evaluate the jitter index of a target subject with pulmonary fibrosis during inhalation. The target subject with pulmonary fibrosis has uneven elastic recoil in the lungs, resulting in inhalation jitter. Therefore, the jitter index of the target subject during inhalation is determined by detecting the number of extreme points in the respiratory velocity waveform.

[0100] This embodiment effectively improves the accuracy of the calculation of respiratory cycle-related parameters by calculating multiple basic features based on the duration of the inhalation sub-stage and the duration of the exhalation sub-stage. Specifically, by calculating the total duration of the respiratory cycle, the various respiratory cycles of the target object can be measured more accurately; the proportion of the expiratory phase duration can intuitively reflect the proportion of the expiratory duration in the respiratory cycle; the expiratory platform index can measure the ratio of the expiratory platform sub-stage duration to the expiratory phase sub-stage duration; the inhalation effort can be used to evaluate the degree of effort during inhalation; and the inhalation phase jitter index can determine the jitter during inhalation. These features combined provide strong support for a comprehensive and accurate analysis of the respiratory process, and help to gain a deeper understanding of the target object's respiratory state.

[0101] In some optional implementations of this embodiment, the calculation of the stationary measurement feature group based on the duration of the inhalation sub-phase and the duration of the exhalation sub-phase in step S4 specifically includes:

[0102] S41b, based on the duration of all breathing cycles of the target object, respectively calculate the standard deviation and the average value.

[0103] Calculate the standard deviation and mean of all respiratory cycle durations.

[0104] S42b, based on the standard deviation and the mean, calculate the ratio of the standard deviation to the mean to obtain the respiratory rhythm disorder index.

[0105] Exemplarily, the respiratory rhythm disorder index is calculated using the following method:

[0106] ,

[0107] in, Respiratory rhythm disorder index, Represents the breathing duration of the i-th breathing cycle, which can be expressed as , Indicates calculating the standard deviation of all respiratory cycle durations, Calculates the average duration of all respiratory cycles.

[0108] This feature is used to assess patients with heart failure, who often experience Cheyne-Stokes respiration, an unstable respiratory cycle, and rhythmic fluctuations. The respiratory rhythm disturbance index is measured by measuring the variability of the respiratory rate waveform within a certain time range.

[0109] S43b, based on the respiratory velocity waveform of each respiratory cycle, calculating the difference in time-integrated area between the respiratory velocity waveform of each respiratory cycle and the respiratory velocity waveform after low-pass filtering.

[0110] For the respiratory velocity waveform of each respiratory cycle, the respiratory velocity waveform is first low-pass filtered to obtain the filtered waveform, and then the integral area of ​​the original respiratory velocity waveform and the low-pass filtered waveform is calculated in the time dimension, and finally the difference between the two integral areas is calculated.

[0111] S44b, performing smoothing calculation based on the difference and the maximum value of the respiratory velocity waveform of each respiratory cycle to obtain the respiratory velocity waveform smoothness.

[0112] Exemplarily, the respiratory velocity waveform smoothness is calculated as follows:

[0113] ,

[0114] in, Indicates the smoothness of the respiratory velocity waveform, Respiratory rate waveform The respiratory rate waveform after low-pass filtering, Indicates the maximum respiratory rate of the respiratory rate waveform.

[0115] A normal respiratory waveform should be smooth and free of noticeable changes. However, irregularities or sudden changes in the respiratory waveform may indicate respiratory problems. Therefore, the smoothness or continuity of the target subject's respiratory waveform is measured by calculating the difference between the respiratory waveform and the smoothed waveform.

[0116] S45b, based on the respiratory velocity waveform of each respiratory cycle, calculate the number of events in which the absolute value of the time-integrated area of ​​the respiratory velocity waveform of each respiratory cycle within the preset time is greater than twice the mean value of the time-integrated area of ​​the respiratory velocity waveform of each respiratory cycle, and obtain the paroxysmal respiratory enhancement index during sleep.

[0117] Exemplarily, the paroxysmal hyperpnea index during sleep is calculated using the following method:

[0118] ,

[0119] in, Indicates the index of paroxysmal increased breathing during sleep, Indicates the breathing duration of the i-th breathing cycle within the preset time, Indicates a sudden increase in tidal volume within the preset time. Indicates the average of the tidal volume surges corresponding to the respiratory cycle within the preset time.

[0120] By counting the number of events in which tidal volume suddenly increases by more than 2 times the baseline within a preset time period (e.g., 1 hour), an indicator of nocturnal paroxysmal increased breathing can be obtained, which is also an early warning indicator of cardiogenic pulmonary edema.

[0121] This embodiment calculates a stability measurement feature group based on the duration of the inhalation sub-stage and the exhalation sub-stage, and has many beneficial effects. By calculating the standard deviation and the average value of all respiratory cycle durations, and obtaining the proportion of the standard deviation to the average value, that is, the respiratory rhythm disorder index, the variability of the respiratory cycle can be measured; the difference in the time integral area of ​​the original respiratory velocity waveform and the waveform after low-pass filtering of each respiratory cycle is calculated, and based on this and the maximum value of the respiratory velocity waveform, a smoothing calculation is performed to obtain the smoothness of the respiratory velocity waveform, which can evaluate the smoothness or continuity of the respiratory velocity waveform; the number of events in which the absolute value of the integral area of ​​the respiratory velocity waveform within a preset time is greater than twice the average value of the integral area is counted to obtain the paroxysmal respiratory enhancement index during sleep, which can reflect the sudden increase in tidal volume during the breathing process. These features taken together help to comprehensively and accurately analyze the stability of breathing.

[0122] In some optional implementations of this embodiment, calculating the comprehensive feature group based on the duration of the inhalation sub-phase and the duration of the exhalation sub-phase in step S4 specifically includes:

[0123] S41c, based on the respiratory velocity waveform of each respiratory cycle, calculating the energy of the respiratory velocity waveform of each respiratory cycle after Fourier transformation within a first preset frequency range to obtain second harmonic energy.

[0124] Exemplarily, the second harmonic energy is calculated as follows:

[0125] ,

[0126] in, represents the second harmonic energy, Respiratory rate waveform The first preset frequency range of the Fourier-transformed respiratory velocity waveform is 0.15-0.35 Hz.

[0127] S42c, based on the respiratory velocity waveform of each respiratory cycle, calculating the energy of the respiratory velocity waveform of each respiratory cycle after Fourier transformation within a second preset frequency range to obtain fundamental frequency harmonic energy.

[0128] Exemplarily, the fundamental frequency harmonic energy is calculated as follows:

[0129] ,

[0130] in, Indicates the fundamental frequency harmonic energy, and the second preset frequency range is 0.3-0.7 Hz.

[0131] S43c, based on the second harmonic energy and the fundamental frequency harmonic energy, calculate the ratio of the second harmonic energy to the fundamental frequency harmonic energy to obtain the harmonic energy ratio.

[0132] Exemplarily, the harmonic energy ratio is calculated using the following method:

[0133] ,

[0134] in, Indicates the proportion of harmonic energy.

[0135] The fundamental frequency of the respiratory signal is concentrated in the 0.15-0.35 Hz range. This feature is used to assess subjects with pulmonary fibrosis. Due to decreased respiratory compliance, subjects with pulmonary fibrosis have abnormal harmonic distribution in the respiratory signal. By performing a Fourier transform on the respiratory velocity waveform and calculating the ratio of the second harmonic energy to the fundamental frequency energy, the smoothness of the subject's breathing can be measured.

[0136] This embodiment calculates a comprehensive feature set based on the duration of the inspiratory and expiratory subphases. Specifically, by performing a Fourier transform on the respiratory velocity waveform of each respiratory cycle, the energy within a first preset frequency range is calculated to obtain the second harmonic energy, and the energy within a second preset frequency range is calculated to obtain the fundamental harmonic energy. The ratio of these two values ​​is then calculated to obtain the harmonic energy percentage. This operation comprehensively reflects the energy distribution of the respiratory velocity waveform within different frequency ranges, helps to measure the smoothness of breathing, and provides an effective method for comprehensive and in-depth analysis of respiratory characteristics.

[0137] In some optional implementations of this embodiment, the embodiment of the present invention provides a method for constructing lung function characteristics during sleep, further comprising:

[0138] The respiratory dominance of the first target site and the respiratory contradiction index of the two target sites are calculated based on the first respiratory motion waveform and the second respiratory motion waveform.

[0139] The respiratory dominance of the second target site and the respiratory contradiction index of the two target sites are calculated according to the first respiratory motion waveform and the second respiratory motion waveform in step S12.

[0140] Specifically, the respiratory dominance of the first target site and the respiratory contradiction index of the two target sites are calculated based on the first respiratory motion waveform and the second respiratory motion waveform, including:

[0141] The total energy within a preset time period is calculated based on the first respiratory motion waveform to obtain the total energy of the first target part.

[0142] Figure 4 The first and second respiratory motion waveforms are extracted, such as the respiratory motion waveforms of the chest and abdomen. The total energy of the first respiratory motion waveform (such as the respiratory waveform of the chest motion) within a preset time period is calculated to obtain the total energy of the first target area, such as the chest.

[0143] The total energy within a preset time period is calculated based on the second respiratory motion waveform to obtain the total energy of the second target part.

[0144] The total energy within a preset time period is calculated according to the second respiratory motion waveform (such as the respiratory waveform of the abdominal motion) to obtain the total energy of the second target part such as the abdomen.

[0145] Based on the energy sum of the first target part and the energy sum of the second target part, a ratio of the energy sum of the second target part to the energy sum of the first target part is calculated to obtain the respiratory dominance of the second target part.

[0146] Exemplarily, the second target site respiratory dominance is calculated in the following manner:

[0147] ,

[0148] in, Indicates the respiratory dominance of the second target site, represents the total energy of the second target part, Represents the total energy of the first target site.

[0149] This feature can be used to assess subjects with lung damage (e.g., pneumonia). Such subjects rely more heavily on abdominal breathing, resulting in stronger echo motion signal energy in the abdomen. Therefore, by comparing the abdominal signal energy to the chest signal energy, we can measure the dominance of abdominal breathing during the subject's breathing.

[0150] Based on the first respiratory motion waveform and the second respiratory motion waveform, an absolute value of a difference between the first respiratory motion waveform and the second respiratory motion waveform is calculated.

[0151] The values ​​of the first respiratory motion waveform and the second respiratory motion waveform at the same time point are subtracted, and then the absolute value of the obtained difference is obtained.

[0152] Based on the absolute value of the difference and the preset time length, the proportion of the absolute value of the difference to the preset time length is calculated to obtain the respiratory contradiction index of the two target parts.

[0153] Exemplarily, the respiratory paradox index of the two target sites is calculated using the following method:

[0154] ,

[0155] in, Represents the respiratory contradiction index of the two target parts, Indicates the absolute value of the difference between the first respiratory motion waveform and the second respiratory motion waveform.

[0156] Taking chest and abdominal breathing as an example, the absolute value of the difference between the chest and abdominal respiratory waveforms is accumulated over a preset duration. The integrated result is divided by the preset duration T to average the accumulated asynchrony effect, thereby obtaining a feature that reflects the average degree of asynchrony between chest and abdominal respiratory movements throughout the entire monitoring period. This feature can be used to assess subjects with diaphragmatic dysfunction or chronic obstructive pulmonary disease, who experience asynchrony in breathing. By dividing the monitoring area, calculating the respiratory waveforms for the chest and abdomen separately, and comparing their synchrony, the chest-abdomen disparity index can be calculated.

[0157] The above-mentioned respiratory dominance of the second target part and the respiratory contradiction index of the two target parts can also be used as part of the comprehensive feature group to comprehensively measure the lung respiratory capacity of the target subject.

[0158] This embodiment calculates the respiratory dominance of the first target site, the respiratory dominance of the second target site, and the respiratory contradiction index of the two target sites based on the first respiratory motion waveform and the second respiratory motion waveform, respectively. By calculating the total energy of the first respiratory motion waveform and the total energy of the second respiratory motion waveform over a preset duration, the total energy of the corresponding target site is obtained, and then the respiratory dominance of the second target site is calculated, which can measure the degree of dominance of the second target site during the target subject's breathing. By calculating the absolute value of the difference between the first respiratory motion waveform and the second respiratory motion waveform, and calculating their ratio based on the preset duration, the respiratory contradiction index of the two target sites is obtained, which can reflect the average degree of asynchrony of the respiratory motion of the two target sites and help to establish a comprehensive characterization of the target subject's lung breathing capacity during sleep.

[0159] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0160] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0161] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0162] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0163] Obviously, the above embodiments are merely examples for clarity of explanation and are not intended to limit the implementation methods. Those skilled in the art will readily appreciate that other variations or modifications based on the above descriptions are possible. It is not necessary and impossible to enumerate all implementation methods here. Obvious variations or modifications arising therefrom remain within the scope of protection of the present invention.

Claims

1. A method for constructing lung function characteristics during sleep, characterized in that: include: Acquiring a first radar echo signal and a second radar echo signal of a first target part and a second target part of a target object during sleep by monitoring the movement of the first radar echo signal and the second radar echo signal; extracting waveforms representing respiratory motion from the first radar echo signal and the second radar echo signal, respectively, to obtain a first respiratory motion waveform and a second respiratory motion waveform; and performing weighted summation of the first respiratory motion waveform and the second respiratory motion waveform to obtain a respiratory velocity waveform; determining a maximum respiratory rate value and a minimum respiratory rate value in the respiratory rate waveform based on the respiratory rate waveform; Removing a preset proportion of numerical points at the maximum respiratory velocity end and the minimum respiratory velocity end of the respiratory velocity waveform respectively to obtain a first respiratory velocity waveform; Calculating a first respiratory rate threshold based on the maximum respiratory rate of the first respiratory rate waveform; Calculating a second respiratory rate threshold based on the minimum respiratory rate value of the first respiratory rate waveform; Determining each respiratory cycle, and an inhalation phase and an exhalation phase in each respiratory cycle based on the first respiratory rate threshold and the second respiratory rate threshold, wherein the inhalation phase includes an inhalation phase sub-phase and an inhalation plateau sub-phase, and the exhalation phase includes an expiratory phase sub-phase and an expiratory plateau sub-phase; Determining the duration of each phase based on the inhalation phase and the exhalation phase to obtain an inhalation sub-phase duration and an exhalation sub-phase duration; Basic features, a stationarity measurement feature group, and a comprehensive feature group are calculated based on the duration of the inhalation sub-phase and the duration of the exhalation sub-phase.

2. The method according to claim 1, characterized in that The determining of the duration of each phase based on the inhalation phase and the exhalation phase to obtain the duration of the inhalation sub-phase and the duration of the exhalation sub-phase includes: Determining the duration of the inspiratory phase sub-stage and the expiratory phase sub-stage based on the respiratory velocity waveform, respectively, to obtain the inspiratory phase sub-stage duration and the expiratory phase sub-stage duration; Dividing the duration of the inspiratory phase sub-stage based on the extreme point of the respiratory velocity waveform of the inspiratory phase sub-stage to obtain the first inspiratory phase sub-stage duration and the second inspiratory phase sub-stage duration; Determining the duration of the inspiratory plateau sub-phase based on the respiratory velocity waveform to obtain the duration of the inspiratory plateau sub-phase; Dividing the duration of the expiratory phase sub-stage based on the extreme value point of the respiratory velocity waveform of the expiratory phase sub-stage to obtain the first expiratory phase sub-stage duration and the second expiratory phase sub-stage duration; The duration of the exhalation plateau sub-phase is determined based on the respiratory velocity waveform to obtain the exhalation plateau sub-phase duration.

3. The method according to claim 2, characterized in that The calculating of basic features based on the duration of the inhalation sub-phase and the duration of the exhalation sub-phase includes: Calculating the duration of each respiratory cycle based on the duration of the first inspiratory phase sub-stage, the duration of the second inspiratory phase sub-stage, the duration of the inspiratory plateau sub-stage, the duration of the first expiratory phase sub-stage, the duration of the second expiratory phase sub-stage, and the duration of the expiratory plateau sub-stage to obtain a total respiratory cycle duration; Based on the duration of the expiratory phase sub-stage, the duration of the expiratory plateau sub-stage, and the total duration of the respiratory cycle, calculating the proportion of the duration of the expiratory phase sub-stage and the duration of the expiratory plateau sub-stage to the total duration of the respiratory cycle to obtain the expiratory phase duration ratio; Based on the duration of the expiratory plateau sub-stage and the duration of the expiratory phase sub-stage, calculating the proportion of the expiratory plateau sub-stage duration to the expiratory phase sub-stage duration to obtain an expiratory plateau index; Calculating the integrated area based on the respiratory velocity waveform of the inspiratory phase in the respiratory cycle to obtain the inspiratory effort; Based on the respiratory velocity waveform in the respiratory cycle, the number of time points at which the first-order derivative is zero is calculated to obtain the inspiratory phase jitter index.

4. The method according to claim 1, wherein Calculating a stationarity measurement feature group based on the duration of the inhalation sub-phase and the duration of the exhalation sub-phase includes: Calculate the standard deviation and the average value based on the duration of all breathing cycles of the target object; Based on the standard deviation and the average value, calculating the proportion of the standard deviation to the average value to obtain a respiratory rhythm disorder index; Based on the respiratory velocity waveform of each respiratory cycle, calculating the difference between the time-integrated area of ​​the respiratory velocity waveform of each respiratory cycle and the respiratory velocity waveform after low-pass filtering; Performing smoothing calculation based on the difference and the maximum value of the respiratory velocity waveform of each respiratory cycle to obtain respiratory velocity waveform smoothness; Based on the respiratory velocity waveform of each respiratory cycle, the number of events in which the absolute value of the time-integrated area of ​​the respiratory velocity waveform of each respiratory cycle within a preset time is greater than twice the mean value of the time-integrated area of ​​the respiratory velocity waveform of each respiratory cycle is calculated to obtain the paroxysmal respiratory enhancement index during sleep.

5. The method according to claim 1, wherein Calculating a comprehensive feature group based on the duration of the inhalation sub-phase and the duration of the exhalation sub-phase includes: Based on the respiratory velocity waveform of each respiratory cycle, calculating the energy of the respiratory velocity waveform of each respiratory cycle after Fourier transformation within a first preset frequency range to obtain second harmonic energy; Based on the respiratory velocity waveform of each respiratory cycle, calculating the energy of the respiratory velocity waveform of each respiratory cycle after Fourier transformation within a second preset frequency range to obtain fundamental frequency harmonic energy; Based on the second harmonic energy and the fundamental frequency harmonic energy, a ratio of the second harmonic energy to the fundamental frequency harmonic energy is calculated to obtain a harmonic energy ratio.

6. The method according to claim 1, wherein Also includes: The respiratory dominance of the second target site and the respiratory contradiction index of the two target sites are calculated based on the first respiratory motion waveform and the second respiratory motion waveform.

7. The method according to claim 6, characterized in that The calculating of the second target site respiratory dominance and the two target site respiratory contradiction index based on the first respiratory motion waveform and the second respiratory motion waveform includes: Calculating the total energy within a preset time period based on the first respiratory motion waveform to obtain the total energy of the first target part; Calculating the total energy within the preset time period based on the second respiratory motion waveform to obtain the total energy of the second target part; Based on the first target part energy sum and the second target part energy sum, calculating a ratio of the second target part energy sum to the first target part energy sum to obtain the second target part respiratory dominance; Calculating an absolute value of a difference between the first respiratory motion waveform and the second respiratory motion waveform based on the first respiratory motion waveform and the second respiratory motion waveform; Based on the absolute value of the difference and the preset time length, the proportion of the absolute value of the difference to the preset time length is calculated to obtain the respiratory contradiction index of the two target parts.

8. A device for constructing lung function characteristics during sleep, characterized in that: include: A processor and a memory connected to the processor; wherein the memory stores instructions that can be executed by the processor, and the instructions are executed by the processor to enable the processor to execute the method for constructing lung function characteristics during sleep as described in any one of claims 1-7.

Images