Method and device for constructing lung function characteristics during sleep

Abstract

The invention provides a method and equipment for constructing lung function characteristics during sleep. The method is applied to lung function data processing. The method comprises the following steps: collecting a breathing velocity waveform of a target object; determining an inspiration stage and an expiration stage in each respiratory cycle based on the respiratory velocity waveform; the duration of each stage is determined based on the inspiration stage and the expiration stage, and the duration of the inspiration sub-stage and the duration of the expiration sub-stage are obtained; basic features, a stability measurement feature group and a comprehensive feature group are calculated based on the inspiration sub-stage duration and the expiration sub-stage duration; according to the method, the breathing speed waveform is acquired without burden, and the comprehensive lung function evaluation feature group suitable for the radar breathing waveform is constructed.

Description

Technical Field

[0001] The present invention relates to the field of pulmonary function data processing, and in particular, to a method and device for constructing pulmonary 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 key evidence for disease diagnosis, condition assessment, treatment plan formulation, and prognosis judgment.

[0003] Under active breathing, the traditional spirometry method uses the ratio of the forced expiratory volume in the first second to the forced vital capacity of the subject to measure the strength of their pulmonary function; or a sensor is used to monitor the respiratory movement of the subject during sleep, and by analyzing the modality presented by the respiratory waveform in a specific sleep stage, to determine whether the pulmonary function of the subject is normal.

[0004] However, both the traditional spirometry method and the contact sensor monitoring method for evaluating pulmonary function have limitations. The traditional spirometry method estimates the pulmonary function ability of the subject by measuring the ratio of the forced expiratory volume in the first second to the forced vital capacity of the subject. It requires the subject to actively cooperate in performing forced breathing actions, which is limited in the elderly population, critically ill subjects and other groups. Moreover, inaccurate manual control during active breathing is likely to cause measurement deviation; using a contact sensor to monitor the nocturnal respiratory pattern of the subject to evaluate pulmonary function, but the sensor will interfere with the natural sleep of the subject, resulting in measurement result deviation. Summary of the Invention

[0005] In view of this, on the one hand, the present invention provides a method for constructing pulmonary function characteristics during sleep, including: collecting the respiratory speed waveform of a target object; determining the inhalation phase and exhalation phase within each respiratory cycle based on the respiratory speed waveform; determining the duration of each phase based on the inhalation phase and exhalation phase to obtain the inhalation sub-phase duration and exhalation sub-phase duration; calculating basic characteristics, a stability metric feature group, and a comprehensive feature group based on the inhalation sub-phase duration and exhalation sub-phase duration.

[0006] Optionally, determining the inhalation phase and the exhalation phase within 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; respectively removing a preset proportion of numerical points at the maximum respiratory rate end and the minimum respiratory rate end of 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, as well as the inhalation phase and the exhalation phase within each respiratory cycle based on the first respiratory rate threshold and the second respiratory rate threshold. The inhalation phase includes an inhalation sub-phase and an inhalation plateau sub-phase, and the exhalation phase includes an exhalation sub-phase and an exhalation plateau sub-phase.

[0007] Optionally, determining 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: respectively determining the duration of the inhalation sub-phase and the exhalation sub-phase based on the respiratory rate waveform to obtain the duration of the inhalation sub-phase and the duration of the exhalation sub-phase; dividing the duration of the inhalation sub-phase based on the extreme points of the respiratory rate waveform of the inhalation sub-phase to obtain a first duration of the inhalation sub-phase and a second duration of the inhalation sub-phase; determining the duration of the inhalation plateau sub-phase based on the respiratory rate waveform to obtain the duration of the inhalation plateau sub-phase; dividing the duration of the exhalation sub-phase based on the extreme points of the respiratory rate waveform of the exhalation sub-phase to obtain a first duration of the exhalation sub-phase and a second duration of the exhalation sub-phase; determining the duration of the exhalation plateau sub-phase based on the respiratory rate waveform to obtain the duration of the exhalation plateau sub-phase.

[0008] Optionally, calculating 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 first duration of the inhalation sub-phase, the second duration of the inhalation sub-phase, the duration of the inhalation plateau sub-phase, the first duration of the exhalation sub-phase, the second duration of the exhalation sub-phase, and the duration of the exhalation plateau sub-phase to obtain the total duration of the respiratory cycle; calculating the proportion of the duration of the exhalation sub-phase and the duration of the exhalation plateau sub-phase in the total duration of the respiratory cycle based on the duration of the exhalation sub-phase, the duration of the exhalation plateau sub-phase, and the total duration of the respiratory cycle to obtain the proportion of the exhalation duration; calculating the proportion of the duration of the exhalation plateau sub-phase in the duration of the exhalation sub-phase based on the duration of the exhalation plateau sub-phase and the duration of the exhalation sub-phase to obtain the exhalation plateau index; calculating the integral area based on the respiratory rate waveform of the inhalation sub-phase within the respiratory cycle to obtain the inspiratory effort; calculating the number of time points where the first derivative is zero based on the respiratory rate waveform within the respiratory cycle to obtain the inspiratory phase jitter index.

[0009] Optionally, calculate a group of stability metric features based on the inhalation sub-phase duration and the exhalation sub-phase duration, including: calculate the standard deviation and the average value respectively based on the durations of all respiratory cycles of the target object; calculate 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; calculate the difference between the integral area in time of the respiratory speed waveform of each respiratory cycle and the integral area in time of the low-pass filtered respiratory speed waveform based on the respiratory speed waveform of each respiratory cycle; perform 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; calculate the number of events in which the absolute value of the integral area in time of the respiratory speed waveform of each respiratory cycle within a preset time is greater than twice the average value of the double integral area in time of the respiratory speed waveform of each respiratory cycle based on the respiratory speed waveform of each respiratory cycle to obtain an index of paroxysmal respiratory enhancement during sleep.

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

[0011] Optionally, collect the respiratory speed waveform of the target object, including: collect a first 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 monitored by a millimeter-wave radar within a preset duration; respectively extract the waveforms representing respiratory movement from the first radar echo signal and the second radar echo signal to obtain a first respiratory movement waveform and a second respiratory movement waveform; perform weighted summation on the first respiratory movement waveform and the second respiratory movement waveform to obtain the respiratory speed waveform.

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

[0013] Optionally, calculating a second target site respiratory dominance degree and a 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 duration based on the first respiratory motion waveform to obtain the total energy of the first target site; calculating the total energy within a preset duration based on the second respiratory motion waveform to obtain the total energy of the second target site; calculating the ratio of the total energy of the second target site to the total energy of the first target site based on the total energy of the first target site and the total energy of the second target site to obtain the second target site respiratory dominance degree; 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 in the preset duration based on the absolute value of the difference and the preset duration to obtain the two-target site respiratory contradiction index.

[0014] In a second aspect of the present invention, there is provided a device for constructing pulmonary function characteristics during sleep, the device including: a processor and a memory connected to the processor; wherein, the memory stores instructions executable by the processor, and when the instructions are executed by the processor, the processor is caused to execute the above-mentioned method for constructing pulmonary function characteristics during sleep.

[0015] The present invention collects the respiratory speed waveform of a target object throughout the night, then determines the inhalation and exhalation phases within each respiratory cycle based on the waveform, and further calculates the duration of each phase to obtain the inhalation sub-phase duration and the exhalation sub-phase duration. Finally, basic characteristics, a group of stability measurement characteristics, and a group of comprehensive characteristics are calculated based on these durations. Using a millimeter-wave radar to collect the respiratory speed waveform can create a natural and non-intrusive detection environment for the target object, enabling it to not require active cooperation during the detection process, significantly improving the comfort and convenience of the detection process. Evaluating the pulmonary function of the target object in a burden-free manner reduces the difficulty of pulmonary function evaluation, especially suitable for target objects who cannot achieve deep breathing; reduces measurement errors caused by active cooperation, can more objectively detect the respiratory state and obtain a large amount of reference data; can accurately divide the respiratory phases and construct a comprehensive pulmonary function evaluation characteristic group applicable to the radar respiratory waveform, and evaluate the pulmonary respiratory function from multiple aspects such as the characteristics of the inhalation and exhalation phases, respiratory stability, and the relationship between the chest and abdomen, with comprehensiveness and practicality.

[0016] The present invention determines the maximum and minimum values of the respiratory speed waveform, removes the preset proportion of numerical points at both ends of the maximum and minimum values of the respiratory speed waveform to obtain the first respiratory speed waveform, calculates thresholds respectively based on its maximum and minimum values, and then determines the respiratory cycle and the inhalation and exhalation phases and sub-phases within each respiratory cycle according to the thresholds, which helps to accurately analyze the respiratory characteristics. Using the double-line method to divide the respiratory phase can help well cope with the signal fluctuations caused by noise or body jitter during the inhalation-exhalation alternation process and more accurately divide the respiratory phase stages. 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 will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a flowchart of the method for constructing the pulmonary function characteristics during sleep in the embodiments of the present invention; Figure 2 It is a respiratory rate waveform diagram of one respiratory cycle in the respiratory rate waveform in the embodiments of the present invention; Figure 3 It is a duration distribution diagram of each sub-stage of a certain respiratory cycle in the embodiments of the present invention; Figure 4 It is a respiratory movement waveform diagram of the chest and abdomen in the embodiments of the present invention. Specific Embodiments

[0019] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the drawings. Obviously, the described embodiments are some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0020] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0021] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "installed", "connected", "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can also be the communication inside two elements. It can be a wireless connection or a wired connection. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0022] In addition, the technical features involved in different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0023] As Figure 1 shown, an embodiment of the present invention provides a method for constructing pulmonary function characteristics during sleep, which is executed by an electronic device such as a computer or a server, and specifically includes: S1. Collect the breathing speed waveform of the target object.

[0024] Data collection is performed on the breathing process of the target object to detect the breathing speed waveform of the target object during sleep. Exemplarily, it can be collected throughout the night using a millimeter-wave radar. The millimeter-wave radar can be placed at a height of 1 m at the head of the bed to collect data. The breathing speed waveform is a waveform of time and breathing speed. In this embodiment, the target object can be a subject, and the age, gender, body shape, etc. of the subject are not limited.

[0025] S2. Determine the inhalation phase and exhalation phase within each breathing cycle based on the breathing speed waveform.

[0026] The breathing process of the target object throughout the night will be divided into several breathing cycles, and it is necessary to determine the inhalation phase and exhalation phase of each breathing cycle.

[0027] S3. Determine the duration of each phase based on the inhalation phase and exhalation phase to obtain the inhalation sub-phase duration and exhalation sub-phase duration.

[0028] Based on the inhalation phase and exhalation phase of each determined breathing cycle, calculate the duration of each of these two phases respectively, so as to obtain the inhalation sub-phase duration and exhalation sub-phase duration.

[0029] S4. Calculate the basic features, stability metric feature group, and comprehensive feature group based on the inhalation sub-phase duration and exhalation sub-phase duration.

[0030] Using the inhalation sub-phase duration and exhalation sub-phase duration of each breathing cycle obtained previously, calculate respectively the basic features for describing breathing characteristics, the stability metric feature group for measuring the stability of the breathing process, and the comprehensive feature group for comprehensively measuring the pulmonary breathing ability of the target object.

[0031] In this embodiment, by collecting the breathing speed waveform of the target object throughout the night, then determining the inhalation and exhalation phases within each breathing cycle based on this waveform, and further calculating the duration of each phase, the inhalation sub-phase duration and the exhalation sub-phase duration are obtained. Finally, the basic features, the stability metric feature group, and the comprehensive feature group are calculated based on these durations. Using a millimeter-wave radar to collect the breathing speed waveform can create a natural and non-intrusive detection environment for the target object, enabling it to avoid active cooperation during the detection process, significantly improving the comfort and convenience of the detection process. It evaluates the lung function of the target object in a burden-free manner, reducing the difficulty of lung function assessment, especially suitable for target objects who cannot perform deep breathing; reducing measurement errors caused by active cooperation, being able to detect the breathing state more objectively and obtain a large amount of reference data; having a strong anti-noise effect, being able to accurately divide the breathing phases; constructing a comprehensive lung function assessment feature group applicable to radar breathing waveforms, evaluating the lung breathing function from multiple aspects such as the characteristics of the inhalation and exhalation phases, breathing stability, and the relationship between the chest and abdomen, with comprehensiveness and practicality.

[0032] In some alternative embodiments of this embodiment, in step S1, collecting the breathing speed waveform of the target object specifically includes: S11, collecting a first radar echo signal of the movement of a first target part of the target object monitored by a millimeter-wave radar within a preset duration and a second radar echo signal of the movement of a second target part.

[0033] Exemplarily, the preset duration can be set according to the sleep duration of the target object, which can ensure that the collected radar echo signals cover the entire sleep stage, more comprehensively and accurately reflecting the breathing characteristics of the target object during sleep. Both the first target part and the second target part refer to the parts that represent the breathing of the target object, such as the chest and abdomen. The chest and abdomen will have obvious undulating movements during human breathing. By monitoring the radar echo signals generated by the movements of the chest and abdomen with a millimeter-wave radar, breathing-related information can be effectively obtained.

[0034] S12, respectively extracting the waveforms representing breathing movements from the first radar echo signal and the second radar echo signal to obtain a first breathing movement waveform and a second breathing movement waveform.

[0035] Extracting the breathing movement waveforms used to represent breathing movements from the radar echo signals of the two parts. In addition to the breathing movement waveforms, other waveforms used to represent breathing movements can also be extracted for subsequent feature construction, such as phase waveforms, displacement waveforms, etc.

[0036] S13, performing weighted summation on the first breathing movement waveform and the second breathing movement waveform to obtain a breathing speed waveform.

[0037] The first respiratory motion waveform corresponding to the motion of the first target part (such as the chest) extracted from the radar echo signal is added to the second respiratory motion waveform corresponding to the motion of the second target part (such as the abdomen) according to a certain weight coefficient, and finally a respiratory speed waveform that can characterize the change of the respiratory speed of the target object is obtained. This weighted summation method considers the comprehensive influence of the motions of different respiration-related parts on the overall respiratory speed, so as to obtain more representative respiratory speed characteristic data.

[0038] In this embodiment, the radar echo signals of the motions of the first and second target parts of the target object within a preset duration are monitored by a millimeter-wave radar. The preset duration is set according to the sleep duration, which can comprehensively and accurately reflect the sleep respiration characteristics. The first respiratory motion waveform and the second respiratory motion waveform are extracted from the echo signals, and finally the first respiratory motion waveform and the second respiratory motion waveform are weighted and summed to obtain a respiratory speed waveform, comprehensively considering the influence of the motions of different parts on the respiratory speed, and obtaining more representative respiratory speed characteristic data, which is helpful for accurately analyzing the respiration of the target object.

[0039] In some alternative embodiments of this embodiment, in step S2, determining the inhalation phase and the exhalation phase within each respiratory cycle based on the respiratory speed waveform specifically includes: S21, determining the maximum respiratory speed and the minimum respiratory speed in the respiratory speed waveform based on the respiratory speed waveform.

[0040] By comparing and analyzing the respiratory speed values represented by each point on the respiratory speed waveform, the respiratory speed corresponding to the point with the largest value is found as the maximum respiratory speed, and the respiratory speed corresponding to the point with the smallest value is found as the minimum respiratory speed.

[0041] S22, respectively removing the numerical points with a preset proportion at the maximum respiratory speed end and the minimum respiratory speed end of the respiratory speed waveform to obtain a first respiratory speed waveform.

[0042] In the respiratory speed waveform, the numerical points corresponding to the preset proportion at one end of the maximum respiratory speed and one end of the minimum respiratory speed are respectively removed, and the waveform formed by the remaining numerical points is the first respiratory speed waveform, and the preset proportion can be set to 10%.

[0043] S23, calculating a first respiratory speed threshold based on the maximum respiratory speed of the first respiratory speed waveform.

[0044] Exemplarily, the first respiratory speed threshold is calculated by the following method: , where, represents the first respiratory speed threshold, represents the first respiratory speed waveform, Represents the maximum respiratory rate value of the first respiratory rate waveform.

[0045] S24, calculate a second respiratory rate threshold based on the minimum respiratory rate value of the first respiratory rate waveform.

[0046] , Among them, Represents the second respiratory rate threshold, Represents the minimum respiratory rate value of the first respiratory rate waveform.

[0047] S25, determine each respiratory cycle and the inhalation phase and exhalation phase in each respiratory cycle based on the first respiratory rate threshold and the second respiratory rate threshold. The inhalation phase includes an inhalation sub-phase and an inhalation plateau sub-phase, and the exhalation phase includes an exhalation sub-phase and an exhalation plateau sub-phase.

[0048] Use the double-line method to divide the respiratory cycle. Taking Figure 2 as an example, it is the respiratory rate waveform of a respiratory cycle in the respiratory rate waveform . - is a respiratory cycle. Among them, and is the inhalation sub-phase, and is the inhalation plateau sub-phase, and is the exhalation sub-phase, and is the exhalation plateau sub-phase.

[0049] In this embodiment, by determining the maximum and minimum values of the respiratory rate waveform, removing the preset proportional numerical points at both ends of the maximum and minimum values of the respiratory rate waveform to obtain the first respiratory rate waveform, calculating the thresholds respectively based on its maximum and minimum values, and then determining the respiratory cycle and the inhalation and exhalation phases and the sub-phases therein according to the thresholds, it helps to accurately analyze the respiratory characteristics. Using the double-line method to divide the respiratory phase can help well deal with the signal fluctuations caused by noise or body jitter during the inhalation-exhalation alternation process and more accurately divide the respiratory phase stages.

[0050] In some alternative embodiments of this embodiment, in step S3, based on the inhalation phase and the exhalation phase, determine the duration of each phase to obtain the inhalation sub-phase duration and the exhalation sub-phase duration, specifically including: S31, respectively determine the duration of the inhalation sub-phase and the exhalation sub-phase based on the respiratory rate waveform to obtain the inhalation sub-phase duration and the exhalation sub-phase duration.

[0051] Taking one respiratory cycle as an example, analyze the respiratory rate waveform to determine the duration of each of the inhalation sub-phase and the exhalation sub-phase, thereby obtaining the duration of the inhalation sub-phase and the duration of the exhalation sub-phase.

[0052] S32. Based on the extreme points of the respiratory rate waveform of the inhalation sub-phase, divide the duration of the inhalation sub-phase to obtain the first inhalation sub-phase duration and the second inhalation sub-phase duration.

[0053] Based on the extreme point (maximum value) on the respiratory rate waveform of the inhalation sub-phase, divide the duration of the inhalation sub-phase, and further obtain the first inhalation sub-phase duration and the second inhalation sub-phase duration.

[0054] S33. Based on the respiratory rate waveform, determine the duration of the inhalation plateau sub-phase to obtain the inhalation plateau sub-phase duration.

[0055] By analyzing and processing the respiratory rate waveform, determine the time experienced by the inhalation plateau sub-phase, thereby obtaining the inhalation plateau sub-phase duration.

[0056] S34. Based on the extreme points of the respiratory rate waveform of the exhalation sub-phase, divide the duration of the exhalation sub-phase to obtain the first exhalation sub-phase duration and the second exhalation sub-phase duration.

[0057] Based on the extreme point (minimum value) on the respiratory rate waveform of the exhalation sub-phase, divide the duration of the exhalation sub-phase, and finally obtain the first exhalation sub-phase duration and the second exhalation sub-phase duration.

[0058] S35. Based on the respiratory rate waveform, determine the duration of the exhalation plateau sub-phase to obtain the exhalation plateau sub-phase duration.

[0059] According to the respiratory rate waveform, determine the time duration of the exhalation plateau sub-phase, and further obtain the exhalation plateau sub-phase duration.

[0060] As Figure 3 shown, it is the duration distribution of each sub-phase of a certain respiratory cycle, where is the first inhalation sub-phase duration, is the second inhalation sub-phase duration, is the inhalation plateau sub-phase duration, is the first exhalation sub-phase duration, is the second exhalation sub-phase duration, is the exhalation plateau sub-phase duration. The duration division of the remaining respiratory cycles is the same as that in steps S31 - S35.

[0061] In this embodiment, by analyzing and processing the respiratory rate waveform, the durations of the inspiratory sub-phase and the expiratory sub-phase are respectively divided based on the waveform extreme points, obtaining the durations of two inspiratory sub-phases and two expiratory sub-phases. Meanwhile, the durations of the inspiratory plateau sub-phase and the expiratory plateau sub-phase are determined based on the respiratory rate waveform, providing more detailed and accurate time parameters for respiratory feature analysis.

[0062] In some alternative embodiments of this embodiment, in step S4, calculating the basic features based on the durations of the inspiratory sub-phase and the expiratory sub-phase specifically includes: S41a, calculating the duration of each respiratory cycle based on the duration of the first inspiratory sub-phase, the duration of the second inspiratory sub-phase, the duration of the inspiratory plateau sub-phase, the duration of the first expiratory sub-phase, the duration of the second expiratory sub-phase, and the duration of the expiratory plateau sub-phase, obtaining the total duration of the respiratory cycle.

[0063] Exemplarily, the following method is used to calculate the total duration of each respiratory cycle: , where, represents the total duration of each respiratory cycle, represents the duration of each sub-phase.

[0064] Under normal circumstances, the human respiratory cycle usually ranges from 3 to 5 seconds. However, patients with impaired lung function often have an increased respiratory rate, which makes their respiratory cycle show different characteristics from normal people. In order to more accurately measure the respiratory cycle of such target objects, that is, to add up the durations of the 6 sub-phases within each respiratory cycle to obtain the total duration of the respiratory cycle, making the calculated respiratory cycle more accurate.

[0065] S42a, calculating the proportion of the duration of the expiratory sub-phase and the duration of the expiratory plateau sub-phase in the total duration of the respiratory cycle based on the duration of the expiratory sub-phase, the duration of the expiratory plateau sub-phase, and the total duration of the respiratory cycle, obtaining the proportion of the expiratory phase duration.

[0066] Exemplarily, the following method is used to calculate the proportion of the expiratory phase duration: , where, represents the proportion of the expiratory phase duration.

[0067] This feature can be used to evaluate the increased expiratory resistance of the respiratory function of target objects such as chronic obstructive pulmonary disease (COPD). For such target objects, the expiratory resistance increases, and the expiratory duration accounts for a larger proportion in the respiratory cycle during night sleep. By calculating the proportion of the expiratory phase duration, the expiratory proportion can be intuitively reflected.

[0068] S43a. Calculate the ratio of the duration of the expiratory plateau sub-phase to the duration of the expiratory phase sub-phase based on the duration of the expiratory plateau sub-phase and the duration of the expiratory phase sub-phase to obtain the expiratory plateau index.

[0069] Exemplarily, the expiratory plateau index is calculated in the following manner: , where, represents the expiratory plateau index.

[0070] This feature is used to measure the ratio of the period during which the expiratory speed is less than the threshold (i.e., the duration of the expiratory plateau sub-phase) to the duration of the expiratory phase sub-phase during the nocturnal sleep breathing of the target object.

[0071] S44a. Calculate the integral area based on the respiratory speed waveform of the inspiratory phase sub-phase within the respiratory cycle to obtain the inspiratory effort.

[0072] Exemplarily, the inspiratory effort is calculated in the following manner: , where, represents the inspiratory effort.

[0073] This feature is used to evaluate the inspiratory effort of target objects with myasthenia and diaphragmatic paralysis. The inspiratory effort of such target objects will be significantly reduced. The integral of the inspiratory phase sub-phase is used to represent the displacement of the chest and abdomen during inspiration, and this displacement is used to measure the inspiratory effort.

[0074] S45a. Calculate the number of time points where the first derivative is zero based on the respiratory speed waveform within the respiratory cycle to obtain the inspiratory phase jitter index.

[0075] Exemplarily, the inspiratory phase jitter index is calculated in the following manner: , where, represents the inspiratory phase jitter index, represents the respiratory speed waveform of the first derivative, represents the number of extreme points in

[0076] Alternatively, it can also be expressed as: , This feature is used to evaluate the jitter index of target objects with pulmonary fibrosis during inspiration. The uneven elastic recoil of the lungs in target objects with pulmonary fibrosis causes inspiratory jitter. Therefore, by detecting the number of extreme points in the respiratory speed waveform, the jitter index of the target object during inspiration is determined.

[0077] In this embodiment, by calculating a plurality of basic features based on the duration of the inhalation sub-phase and the duration of the exhalation sub-phase, the accuracy of calculating the respiratory cycle-related parameters is effectively improved. Specifically, by calculating the total duration of the respiratory cycle, the respiratory cycle conditions of the target object can be measured more accurately; the proportion of the exhalation phase duration can directly reflect the proportion of the exhalation duration in the respiratory cycle; the expiratory plateau index can measure the ratio of the duration of the expiratory plateau sub-phase to the duration of the exhalation sub-phase; the inspiratory effort can be used to evaluate the effort degree during inhalation; and the inspiratory phase jitter index can determine the jitter condition during inhalation. These features, when combined, provide strong support for comprehensively and accurately analyzing the respiratory process, and help to deeply understand the respiratory state of the target object.

[0078] In some alternative embodiments of this embodiment, in step S4, calculating the stability metric feature group based on the duration of the inhalation sub-phase and the duration of the exhalation sub-phase specifically includes: S41b, calculating the standard deviation and the average value respectively based on the durations of all respiratory cycles of the target object.

[0079] Calculate the standard deviation and the average value of the durations of all respiratory cycles.

[0080] S42b, calculating the proportion of the standard deviation to the average value based on the standard deviation and the average value to obtain the respiratory rhythm disorder index.

[0081] Exemplarily, the respiratory rhythm disorder index is calculated by the following method: , where, represents the respiratory rhythm disorder index, represents the respiratory duration of the i-th respiratory cycle, and can be expressed as , represents the standard deviation of calculating the durations of all respiratory cycles, represents the average value of calculating the durations of all respiratory cycles.

[0082] This feature is used to evaluate the target object with heart failure. The target object with heart failure often has Cheyne-Stokes respiration, the respiratory cycle is unstable, and there will be rhythm fluctuations. By measuring the variability of the cycles within a certain time length range in the respiratory speed waveform, the respiratory rhythm disorder index is measured.

[0083] S43b, calculating the difference between the integral area in time of the respiratory speed waveform of each respiratory cycle and the integral area in time of the respiratory speed waveform after low-pass filtering based on the respiratory speed waveforms of each respiratory cycle.

[0084] For the breathing rate waveform of each breathing cycle, first perform low-pass filtering on the breathing rate waveform to obtain the filtered waveform, then calculate the integral areas of the original breathing rate waveform and the low-pass filtered waveform respectively in the time dimension, and finally calculate the difference between these two integral areas.

[0085] S44b. Based on the difference and the maximum value of the breathing rate waveform of each breathing cycle, perform a smoothing calculation to obtain the smoothness of the breathing rate waveform.

[0086] Exemplarily, the smoothness of the breathing rate waveform is calculated in the following manner: , where, represents the smoothness of the breathing rate waveform, represents the breathing rate waveform the breathing rate waveform after low-pass filtering, represents the maximum breathing rate of the breathing rate waveform.

[0087] Since a normal breathing waveform should be smooth and without obvious mutations, and the irregularity or sharp change of the breathing waveform may be a sign of problems in the respiratory tract. Therefore, it is necessary to calculate the difference degree between the breathing waveform and the smoothed operation to measure the smoothness or continuity of the breathing waveform of the target object.

[0088] S45b. Based on the breathing rate waveform of each breathing cycle, calculate the number of events where the absolute value of the integral area of the breathing rate waveform of each breathing cycle in the preset time is greater than twice the mean value of the double integral area of the breathing rate waveform of each breathing cycle in the time, to obtain the index of paroxysmal breathing enhancement during sleep.

[0089] Exemplarily, the index of paroxysmal breathing enhancement during sleep is calculated in the following manner: , where, represents the index of paroxysmal breathing enhancement during sleep, represents the breathing duration of the i-th breathing cycle within the preset time, represents the sudden increase in tidal volume within the preset time, represents the mean value of the sudden increase in tidal volume corresponding to the breathing cycle within the preset time.

[0090] By counting the number of events where the sudden increase in tidal volume > 2 times the baseline occurs within the preset time (such as 1 hour), the index of paroxysmal nocturnal dyspnea can be obtained, and this index is also an early warning index for cardiogenic pulmonary edema.

[0091] This embodiment calculates a group of stability measurement features based on the durations of the inhalation sub-phase and the exhalation sub-phase, and has beneficial effects in multiple aspects. By calculating the standard deviation and the average value of the durations of all respiratory cycles, and obtaining the ratio of the standard deviation to the average value, i.e., the respiratory rhythm disorder index, the variability of the respiratory cycles can be measured; by calculating the difference in the integrated area over time between the original respiratory speed waveform and the waveform after low-pass filtering for each respiratory cycle, and performing a smoothing calculation based on this difference and the maximum value of the respiratory speed waveform to obtain the smoothness of the respiratory speed waveform, the smoothness or continuity of the respiratory speed waveform can be evaluated; by counting the number of events where the absolute value of the integrated area of the respiratory speed waveform is greater than twice the average integrated area within a preset time to obtain the paroxysmal respiratory enhancement index during sleep, the sudden increase in tidal volume during the respiratory process can be reflected. These features, combined together, help to comprehensively and accurately analyze the stability status of respiration.

[0092] In some alternative embodiments of this embodiment, in step S4, calculating the comprehensive feature group based on the durations of the inhalation sub-phase and the exhalation sub-phase specifically includes: S41c, based on the respiratory speed waveforms of each respiratory cycle, calculate the energy of the Fourier-transformed respiratory speed waveform of each respiratory cycle within the first preset frequency range to obtain the second harmonic energy.

[0093] Exemplarily, the second harmonic energy is calculated using the following method: , where, represents the second harmonic energy, represents the respiratory speed waveform the Fourier-transformed respiratory speed waveform, and the first preset frequency range is 0.15 - 0.35 hz.

[0094] S42c, based on the respiratory speed waveforms of each respiratory cycle, calculate the energy of the Fourier-transformed respiratory speed waveform of each respiratory cycle within the second preset frequency range to obtain the fundamental frequency harmonic energy.

[0095] Exemplarily, the fundamental frequency harmonic energy is calculated using the following method: , where, represents the fundamental frequency harmonic energy, and the second preset frequency range is 0.3 - 0.7 hz.

[0096] 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.

[0097] Exemplarily, the harmonic energy ratio is calculated using the following method; , where, Indicates the proportion of harmonic energy.

[0098] The fundamental frequency of the respiratory signal is concentrated in the range of 0.15 - 0.35 hz. This feature is used to evaluate the target object with pulmonary fibrosis. Due to the decreased compliance of breathing in the target object with pulmonary fibrosis, the harmonic distribution of the respiratory signal appears abnormal. By performing a Fourier transform on the respiratory velocity waveform, the ratio of the second harmonic energy to the fundamental frequency energy is calculated to measure the smoothness of the target object's breathing.

[0099] In this embodiment, a comprehensive feature group is calculated based on the inhalation sub - phase duration and the exhalation sub - phase duration. Specifically, by performing a Fourier transform on the respiratory velocity waveform of each respiratory cycle, the energy within the first preset frequency range is calculated to obtain the second harmonic energy, and the energy within the second preset frequency range is calculated to obtain the fundamental frequency harmonic energy. Then, the ratio of the two is calculated to obtain the proportion of harmonic energy. These operations can comprehensively reflect the energy distribution of the respiratory velocity waveform in different frequency ranges, help measure the smoothness of breathing, and provide an effective method for comprehensively and deeply analyzing respiratory characteristics.

[0100] In some alternative embodiments of this embodiment, the embodiment of the present invention provides a method for constructing pulmonary function characteristics during sleep, further including: Calculating the respiratory dominance of the first target site and the respiratory contradiction index between the two target sites based on the first respiratory motion waveform and the second respiratory motion waveform.

[0101] Calculating the respiratory dominance of the second target site and the respiratory contradiction index between the two target sites according to the first respiratory motion waveform and the second respiratory motion waveform in step S12.

[0102] Specifically, calculating the respiratory dominance of the first target site and the respiratory contradiction index between the two target sites based on the first respiratory motion waveform and the second respiratory motion waveform includes: Calculating the total energy within a preset duration based on the first respiratory motion waveform to obtain the total energy of the first target site.

[0103] Figure 4 are the extracted first respiratory motion waveform and the second respiratory motion waveform, such as the respiratory motion waveforms of the chest and abdomen. According to the first respiratory motion waveform (such as the respiratory waveform of chest movement), the total energy within a preset duration is calculated to obtain the total energy of the first target site such as the chest.

[0104] Calculating the total energy within a preset duration based on the second respiratory motion waveform to obtain the total energy of the second target site.

[0105] According to the second respiratory motion waveform (such as the respiratory waveform of abdominal movement), the total energy within a preset duration is calculated to obtain the total energy of the second target site such as the abdomen.

[0106] Calculate the ratio of the energy sum of the second target part to the energy sum of the first target part based on the energy sum of the first target part and the energy sum of the second target part, and obtain the respiratory dominance of the second target part.

[0107] Exemplarily, calculate the respiratory dominance of the second target part in the following manner; , where, represents the respiratory dominance of the second target part, represents the energy sum of the second target part, represents the energy sum of the first target part.

[0108] This feature can be used to evaluate a target object with lung damage (such as pneumonia). Such target objects rely more on abdominal breathing, resulting in a stronger echo motion signal energy at the abdominal position. Therefore, the ratio of the abdominal signal energy to the chest signal energy can be used to measure the abdominal respiratory dominance when the target object breathes.

[0109] Calculate 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.

[0110] Subtract the values of the first respiratory motion waveform and the second respiratory motion waveform at the same time point, and then take the absolute value of the obtained difference.

[0111] Calculate the proportion of the absolute value of the difference in the preset duration based on the absolute value of the difference and the preset duration, and obtain the respiratory contradiction index of the two target parts.

[0112] Exemplarily, calculate the respiratory contradiction index of the two target parts in the following manner: , where, represents the respiratory contradiction index of the two target parts, represents the absolute value of the difference between the first respiratory motion waveform and the second respiratory motion waveform.

[0113] Taking chest and abdominal breathing as an example, accumulate the absolute value of the difference in the chest and abdominal breathing waveforms over the entire preset duration, and divide the integral result by the preset duration T. This is to average the cumulative asynchrony effect, so as to obtain a feature that can reflect the average degree of asynchrony of chest and abdominal breathing movements during the entire monitoring period. This feature can be used to evaluate target objects with diaphragmatic dysfunction or chronic obstructive pulmonary disease. Such target objects will show asynchrony during breathing. By dividing according to the monitoring parts, obtaining the breathing waveforms of the chest and abdominal positions respectively, and comparing their synchrony, the thoracoabdominal contradiction index can be obtained.

[0114] The above-mentioned second target site respiration dominance and the respiration contradiction index of the two target sites can also be used as part of the comprehensive feature group to comprehensively measure the pulmonary respiration ability of the target object.

[0115] Based on the first respiration motion waveform and the second respiration motion waveform in this embodiment, the respiration dominance of the first target site, the respiration dominance of the second target site, and the respiration contradiction index of the two target sites are calculated respectively. By calculating the total energy of the first respiration motion waveform and the total energy of the second respiration motion waveform within a preset time period, the total energy of the corresponding target site is obtained, and then the respiration dominance of the second target site is calculated, which can measure the dominant degree of the second target site of the target object during respiration; by calculating the absolute value of the difference between the first respiration motion waveform and the second respiration motion waveform and combining the preset time period to calculate its proportion to obtain the respiration contradiction index of the two target sites, the average degree of asynchrony of the respiration motions of the two target sites can be reflected, which helps to construct a comprehensive feature of the pulmonary respiration ability of the target object during sleep.

[0116] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0118] These computer program instructions can 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 generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the functions specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps in one block or a plurality of blocks.

[0120] Obviously, the above-described embodiments are merely examples given for clear illustration and are not intended to limit the implementation. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. And the obvious changes or modifications derived therefrom still fall within the protection scope of the present invention.

Claims

1. A method for constructing pulmonary function characteristics during sleep, characterized in that, Including: Collecting the respiratory rate waveform of a target object; Determining the inhalation phase and exhalation phase within each respiratory cycle based on the respiratory rate waveform; Determining the duration of each phase based on the inhalation phase and the exhalation phase to obtain the inhalation sub-phase duration and the exhalation sub-phase duration; Calculating basic features, a group of stationarity metric features, and a group of comprehensive features based on the inhalation sub-phase duration and the exhalation sub-phase duration.

2. The method according to claim 1, characterized in that, The determining the inhalation phase and the exhalation phase within 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 of the respiratory rate waveform respectively 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, and the inhalation phase and the exhalation phase within each respiratory cycle based on the first respiratory rate threshold and the second respiratory rate threshold. 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.

3. The method according to claim 2, characterized in that, The determining the duration of each phase based on the inhalation phase and the exhalation phase to obtain the inhalation sub-phase duration and the exhalation sub-phase duration includes: Determining the duration of the inhalation phase sub-phase and the exhalation phase sub-phase respectively based on the respiratory rate waveform to obtain the inhalation phase sub-phase duration and the exhalation phase sub-phase duration; Dividing the duration of the inhalation phase sub-phase based on the extreme points of the respiratory rate waveform of the inhalation phase sub-phase to obtain a first inhalation phase sub-phase duration and a second inhalation phase sub-phase duration; Determining the duration of the inhalation plateau sub-phase based on the respiratory rate waveform to obtain the inhalation plateau sub-phase duration; Dividing the duration of the exhalation phase sub-phase based on the extreme points of the respiratory rate waveform of the exhalation phase sub-phase to obtain a first exhalation phase sub-phase duration and a second exhalation phase sub-phase duration; Determining the duration of the exhalation plateau sub-phase based on the respiratory rate waveform to obtain the exhalation plateau sub-phase duration.

4. The method according to claim 3, characterized in that, The calculating basic features based on the inhalation sub-phase duration and the exhalation sub-phase duration includes: Calculating the duration of each respiratory cycle based on the first inhalation phase sub-phase duration, the second inhalation phase sub-phase duration, the inhalation plateau sub-phase duration, the first exhalation phase sub-phase duration, the second exhalation phase sub-phase duration, and the exhalation plateau sub-phase duration to obtain the total respiratory cycle duration; Calculating the proportion of the exhalation phase sub-phase duration and the exhalation plateau sub-phase duration in the total respiratory cycle duration based on the exhalation phase sub-phase duration, the exhalation plateau sub-phase duration, and the total respiratory cycle duration to obtain the exhalation phase duration proportion; Calculating the proportion of the exhalation plateau sub-phase duration in the exhalation phase sub-phase duration based on the exhalation plateau sub-phase duration and the exhalation phase sub-phase duration to obtain the exhalation plateau index; Calculate the integral area based on the respiratory velocity waveform in the inspiratory sub-phase within the respiratory cycle to obtain the inspiratory effort degree; Calculate the number of time points where the first derivative is zero based on the respiratory velocity waveform within the respiratory cycle to obtain the inspiratory jitter index.

5. The method according to claim 1, wherein Calculate a group of stability metric features based on the inspiratory sub-phase duration and the expiratory sub-phase duration, including: Calculate the standard deviation and the average value respectively based on the durations of all respiratory cycles of the target object; Calculate the proportion of the standard deviation to the average value based on the standard deviation and the average value to obtain the respiratory rhythm disorder index; Calculate the difference in the integral area over time between the respiratory velocity waveform of each respiratory cycle and the respiratory velocity waveform after low-pass filtering based on the respiratory velocity waveforms of each respiratory cycle; Perform a smoothing calculation based on the difference and the maximum value of the respiratory velocity waveform of each respiratory cycle to obtain the smoothness of the respiratory velocity waveform; Calculate the number of events where the absolute value of the integral area over time of the respiratory velocity waveform of each respiratory cycle within a preset time is greater than twice the average value of the double integral area over time of the respiratory velocity waveform of each respiratory cycle based on the respiratory velocity waveforms of each respiratory cycle to obtain the index of paroxysmal respiratory enhancement during sleep.

6. The method according to claim 1, wherein Calculate a group of comprehensive features based on the inspiratory sub-phase duration and the expiratory sub-phase duration, including: Calculate 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; Calculate the energy of the Fourier-transformed respiratory velocity waveform of each respiratory cycle within a second preset frequency range to obtain the fundamental frequency harmonic energy; Calculate the ratio of the second harmonic energy to the fundamental frequency harmonic energy based on the second harmonic energy and the fundamental frequency harmonic energy to obtain the proportion of harmonic energy.

7. The method according to claim 1, wherein The acquisition of the respiratory velocity waveform of the target object includes: Acquire a first 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 monitored by a millimeter-wave radar within a preset duration; Extract the waveforms representing 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; Perform weighted summation on the first respiratory movement waveform and the second respiratory movement waveform to obtain the respiratory velocity waveform.

8. The method according to claim 7, characterized in that, It also includes: Calculate the respiratory dominance degree of the second target part and the respiratory contradiction index between the two target parts based on the first respiratory movement waveform and the second respiratory movement waveform.

9. The method according to claim 8, wherein The calculation of the respiratory dominance degree of the second target part and the respiratory contradiction index between the two target parts based on the first respiratory movement waveform and the second respiratory movement waveform includes: Calculate the total energy within the preset duration based on the first respiratory movement waveform to obtain the total energy of the first target part; Calculate the total energy within the preset duration based on the second respiratory movement waveform to obtain the total energy of the second target part; Based on the total energy of the first target part and the total energy of the second target part, calculate the ratio of the total energy of the second target part to the total energy of the first target part to obtain the respiratory dominance of the second target part; Based on the first respiratory motion waveform and the second respiratory motion waveform, calculate the absolute value of the difference between the first respiratory motion waveform and the second respiratory motion waveform; Based on the absolute value of the difference and the preset duration, calculate the proportion of the absolute value of the difference in the preset duration to obtain the respiratory contradiction index of the two target parts.

10. A device for constructing pulmonary function characteristics during sleep, characterized in that, Includes: A processor and a memory connected to the processor; wherein, the memory stores instructions executable by the processor, and the instructions are executed by the processor to enable the processor to execute the method for constructing pulmonary function characteristics during sleep according to any one of claims 1-9.

Images