Method and system for identifying early critical breathing state of children

Abstract

The invention relates to the technical field of respiration monitoring, in particular to a method and a system for identifying early critical respiration states of children. The method comprises the following steps: firstly, acquiring a historical respiration signal and segmenting to obtain respiration segments; further dividing a breathing mode according to the difference of the breathing amplitudes and the difference of the signal components between the breathing segments; further acquiring the breathing frequency and the breathing amplitude range of each breathing mode, and screening out a normal breathing mode; further acquiring a real-time respiration signal of the current patient and segmenting the real-time respiration signal in real time; according to the difference characteristic between the breathing segment to which the current moment belongs and the normal breathing mode, the number difference between the breathing mode to which the current moment belongs and the breathing mode of the adjacent breathing segment and the number of the breathing segments is combined, and a breathing anomaly coefficient is obtained; finally, whether early warning is sent out or not is judged based on the breathing abnormal coefficient, the influence of modal mixing is reduced, the influence of physiological differences of different age groups or individuals is reduced, and the breathing state recognition accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of respiratory monitoring, and in particular to a method and system for identifying a critical respiratory state in early childhood. Background Art

[0002] Non-contact breathing detection based on microwave radar detects the human body based on the certain correlation between the micro-movement of the human body surface and the phase of the reflected echo signal to achieve the purpose of breathing detection. Then, based on the empirical mode decomposition (EMD), the breathing signal detected by microwave can be decomposed into a series of intrinsic mode functions (IMF components) with high to low frequencies, and then the breathing state can be identified according to the frequency of the IMF components.

[0003] Pediatric critical illnesses are hidden, change rapidly, and are easily overlooked. In addition, breathing varies with age, so accurate detection of breathing in child patients is extremely important. However, when respiratory status is identified by performing empirical mode decomposition of respiratory signals, the frequency of the IMF component is not completely concentrated, and there is a problem of mode mixing, which results in poor detection effect and unsatisfactory accuracy in respiratory status identification. Summary of the invention

[0004] In order to solve the technical problem that the existing microwave detection and signal decomposition method has low accuracy in identifying the respiratory state of children, the purpose of the present invention is to provide a method and system for identifying the critical respiratory state of children in the early stage. The technical scheme adopted is as follows: A method for identifying an early critical respiratory state in a child, the method comprising: Acquire the historical respiratory signal of the current patient within a preset time interval; slide a preset window on the historical respiratory signal, perform signal decomposition on the historical respiratory signal within the preset window after sliding based on the EMD algorithm, iteratively adjust the window length according to the frequency concentration characteristics of the signal components, segment the historical respiratory signal, and obtain respiratory segments; According to the difference in the breathing amplitude between any two of the breathing segments and the difference in the signal components, a cluster distance between the corresponding two breathing segments is obtained; based on the cluster distance, the breathing segments are clustered, and each cluster cluster corresponds to a breathing pattern; According to the overall characteristics of the breathing amplitude ranges of all the breathing segments in each cluster and the distribution characteristics of the frequencies of all the first signal components, the breathing frequency and breathing amplitude range of each breathing pattern are obtained; according to the length characteristics of the breathing segments in each breathing pattern, a normal breathing pattern is obtained; The real-time breathing signal of the current patient is obtained and segmented in real time; according to the difference characteristics of the breathing amplitude range between the breathing segment at the current moment and the normal breathing pattern, as well as the difference characteristics of the breathing frequency, combined with the difference in the number of breathing segments between the breathing pattern at the current moment and the breathing pattern of the adjacent breathing segments, the breathing abnormality coefficient at the current moment is obtained; based on the breathing abnormality coefficient at the current moment, it is determined whether to issue an early warning.

[0005] Furthermore, the method for obtaining the breathing segmentation includes: The preset window starts to slide from the starting point of the historical respiratory signal, and the window length is iteratively adjusted after each sliding, and the window length determined after each sliding is used as the sliding step length for the next sliding; For the historical breathing signal of the latest window length after any sliding, select any signal component as the target signal component; obtain the spectrum of the target signal component, translate the straight line parallel to the frequency axis from the maximum value to the minimum value of the spectrum amplitude, and obtain the intersection length of the straight line corresponding to each spectrum amplitude and the spectrum line; according to the variation characteristics of the intersection length of the target signal component with the spectrum amplitude, obtain the frequency concentration sub-coefficient of the target signal component; According to the mean of the frequency concentration sub-coefficients of all the signal components, combined with the difference between the frequency concentration sub-coefficient of each signal component and the mean of the frequency concentration sub-coefficients, the frequency concentration coefficient of the latest window length is obtained; the mean of the frequency concentration sub-coefficients is positively correlated with the frequency concentration coefficient; the difference between the frequency concentration sub-coefficients and the mean of the frequency concentration sub-coefficients is negatively correlated with the frequency concentration coefficient; If the frequency concentration coefficient of the current latest window length is less than the first preset concentration threshold, the window length is reduced by the preset adjustment step to obtain a new window length; if the frequency concentration coefficient of the current latest window length is greater than or equal to the second preset concentration threshold, the window length is increased by the preset adjustment step to obtain a new window length; if the frequency concentration coefficient of the current latest window length is greater than or equal to the first preset concentration threshold and less than the second preset concentration threshold, the iteration is terminated and the historical breathing signal corresponding to the current latest window length is taken as a breathing segment.

[0006] Furthermore, the method for obtaining the sub-coefficients in the frequency concentration includes: After normalizing the sum of the products of all the negative correlation mapping values ​​of the intersection lengths of the target signal component and the corresponding spectrum amplitudes, the normalized result is used as the frequency concentrated sub-coefficient of the target signal component.

[0007] Furthermore, the method for obtaining the cluster distance includes: The frequency at the maximum value of the spectrum amplitude in the spectrum diagram of each signal component is recorded as the representative frequency; any two of the breathing segments are obtained to form a target binary group, and for each of the signal components in any of the breathing segments in the target binary group, the signal component with the closest representative frequency in the other breathing segment is obtained as the matching signal component; The calculation formula for cluster distance includes: ; Among them, u and v are the serial numbers of the breathing segments; represents the clustering distance between the u-th breathing segment and the v-th breathing segment; represents linear normalization; represents the absolute value of the difference between the maximum breathing amplitude of the u-th breathing segment and the v-th breathing segment; represents the absolute value of the difference between the minimum breathing amplitude of the u-th breathing segment and the v-th breathing segment; i represents the sequence number of the signal component of the u-th breathing segment; k represents the sequence number of the signal component of the v-th breathing segment; represents the number of signal components of the u-th respiratory segment; represents the number of signal components of the vth respiratory segment; represents the representative frequency of the i-th signal component of the u-th respiratory segment; The i-th signal component of the u-th breathing segment and the representative frequency of the corresponding matching signal component in the v-th breathing segment; Indicates taking the absolute value; represents the representative frequency of the kth signal component of the vth respiratory segment; The kth signal component of the vth respiratory segment corresponds to the representative frequency of the matching signal component in the uth respiratory segment.

[0008] Furthermore, the method for obtaining the respiratory frequency and respiratory amplitude range of each respiratory mode includes: Taking the mean of the representative frequencies of the first signal components of all the respiratory segments in each cluster as the respiratory frequency of the corresponding respiratory pattern; The average of the maximum values ​​of the breathing amplitude of all the breathing segments in each cluster is used as the maximum value of the breathing amplitude range of the corresponding breathing pattern; the average of the minimum values ​​of the breathing amplitude of all the breathing segments in each cluster is used as the minimum value of the breathing amplitude range of the corresponding breathing pattern.

[0009] Furthermore, the method for acquiring the normal breathing pattern includes: The product of the mean value of the time domain lengths of all the breathing segments of each breathing pattern and the sum of the time domain lengths of all the breathing segments is used as the normal possible coefficient of each breathing pattern; The breathing pattern with the largest normal possible coefficient is selected as the normal breathing pattern.

[0010] Furthermore, the calculation formula of the abnormal breathing coefficient includes: ; Wherein, L represents the respiratory abnormality coefficient at the current moment; represents an exponential function with the natural constant e as the base; h is the serial number of the breathing segment to which the current moment belongs; Indicates the breathing amplitude range of the breathing segment at the current moment; Respiratory amplitude range representing normal breathing pattern; Indicates the intersection of the breathing amplitude range of the breathing segment at the current moment and the breathing amplitude range of the normal breathing pattern; The union of the breathing amplitude range of the breathing segment at the current moment and the breathing amplitude range of the normal breathing pattern; represents the linear normalization function; Indicates taking the absolute value; Indicates the representative frequency of the breathing segment at the current moment; Respiratory rate, which indicates a normal breathing pattern; The number of breathing segments representing the breathing pattern of adjacent breathing segments at the current moment; Indicates the number of breathing segments corresponding to the breathing pattern at the current moment.

[0011] Furthermore, the method for determining whether to issue an early warning based on the abnormal breathing coefficient at the current moment includes: When the abnormal breathing coefficient is greater than a preset abnormal threshold, an early warning is issued.

[0012] Furthermore, the preset adjustment step is 1 second.

[0013] The present invention also proposes a system for identifying early critical respiratory states in children. The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any step of the method for identifying early critical respiratory states in children.

[0014] The present invention has the following beneficial effects: The present invention first obtains historical breathing signals to provide a data basis for determining different breathing patterns of patients; further slides a preset window on the historical breathing signal, performs signal decomposition on the historical breathing signal in the preset window after sliding based on the EMD algorithm, iteratively adjusts the window length according to the frequency concentration characteristics of the signal components, segments the historical breathing signal, obtains breathing segments, reduces the influence of modal mixing, and ensures that longer breathing segments can contain more complete breathing cycles, which is more conducive to analyzing different breathing patterns; further divides the breathing patterns, determines the breathing frequency and breathing amplitude range of each breathing pattern, clarifies the parameter boundaries of the breathing pattern, and distinguishes different breathing patterns; further according to each breathing The length characteristics of the breathing segments within the pattern are used to obtain the normal breathing pattern as the reference pattern. The normal breathing pattern determined based on the historical breathing signal of the current patient can better represent the normal breathing pattern of the current patient and reduce the influence of physiological differences of different age groups or individuals; further, according to the difference in breathing amplitude range and breathing frequency between the breathing segment at the current moment and the normal breathing pattern, combined with the breathing pattern at the current moment and the breathing pattern of the adjacent breathing segment, the number difference of breathing segments is used to obtain the breathing abnormality coefficient at the current moment, characterize the abnormal degree of the breathing state of the current child patient at the current moment, and provide a basis for subsequent determination of whether to issue an early warning; finally, determine whether to issue an early warning based on the breathing abnormality coefficient. The present invention reduces the influence of mode mixing by adjusting the window length by analyzing the mode mixing of signal decomposition during signal segmentation; reduces the influence of physiological differences of different age groups or individuals by determining the normal breathing pattern based on the historical breathing signal of the current patient, and improves the accuracy of respiratory state recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flowchart of a method for identifying an early critical respiratory state in children provided by an embodiment of the present invention; Figure 2 A flowchart of a method for obtaining breathing segments provided by an embodiment of the present invention; Figure 3 A schematic diagram of an intersection length provided by an embodiment of the present invention; Figure 4 A schematic diagram of a breathing amplitude range of all breathing modes provided by an embodiment of the present invention; Figure 5 A schematic diagram of the respiratory frequencies of all respiratory modes provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a method and system for identifying critical respiratory status in early childhood proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The specific scheme of the method and system for identifying the early critical respiratory state of children provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flow chart of a method for identifying an early critical respiratory state of a child provided by an embodiment of the present invention, specifically comprising: Step S1: Obtain the historical respiratory signal of the current patient in a preset time interval; slide the preset window on the historical respiratory signal, decompose the historical respiratory signal in the preset window after sliding based on the EMD algorithm, iteratively adjust the window length according to the frequency concentration characteristics of the signal component, segment the historical respiratory signal, and obtain respiratory segments.

[0021] In an embodiment of the present invention, a microwave radar is used to detect the patient's breathing and obtain a breathing signal. First, the historical breathing signal of the current patient within a preset time interval is obtained, and the historical breathing signal is analyzed to determine the patient's different breathing patterns, thereby identifying the patient's real-time breathing pattern.

[0022] It should be noted that the use of microwave radar to detect the patient's breathing and the EMD algorithm to decompose the signal are both existing technologies. Please refer to the document "Design and Research of Microwave-Based Non-Contact Respiration Detection and Analysis System" by Liang Song; in one embodiment of the present invention, the length of the preset time interval is 24 hours, and the historical breathing signal of the current patient in the 24 hours of the previous day is obtained. The preset time interval is from the beginning to the end of the day, and the historical breathing signal is updated once at 0:00 every day to update the normal breathing pattern; during the update period, the respiratory state recognition still uses the data before the update, and the implementer can set it according to the implementation scenario.

[0023] The amplitude and frequency of each breath of the patient are different, and the difference between different breathing patterns is only the difference in amplitude and frequency. At the same time, because breathing is continuous, analyzing it in units of single breath will lead to too many breathing patterns, which is not conducive to state recognition. Therefore, we can first divide continuous breaths with similar states into the same breathing segment by adding windows. Since the maintenance time of breathing segments is not the same, we can adaptively determine the window size by analyzing the performance of the breathing signal in the window.

[0024] To reduce the impact of modal mixing, the frequency of the signal component within a breathing segment cannot be too discrete. At the same time, it is ensured that longer breathing segments can contain more complete breathing cycles, which is more conducive to analyzing different breathing patterns. Therefore, a preset window is slid on the historical breathing signal, and the historical breathing signal in the preset window after sliding is decomposed. The window length is iteratively adjusted according to the frequency concentration characteristics of the signal component. The historical breathing signal is segmented with the window after each sliding and iterative adjustment to obtain breathing segments, which is convenient for the subsequent division of breathing patterns.

[0025] Preferably, in one embodiment of the present invention, the method for acquiring breathing segments includes: First, the sliding process is explained: the preset window starts to slide from the starting point of the historical breathing signal, and the window length is iteratively adjusted after each sliding. The window length determined after each sliding is used as the sliding step for the next sliding; at the same time, the window length determined after each sliding is also the time domain length of a breathing segment.

[0026] As an example, the preset window is 5 seconds, the preset adjustment step is 1 second, the starting point of the historical breathing signal is set to 0, the initial position of the preset window is at 0-5 seconds, and it is assumed that after iterative adjustment, the window length is finally adjusted to 20 seconds. The first breathing segment is 0-20, and the preset window slides for 20 seconds, and iterative adjustment is performed again at 20-25 seconds; assuming that after iterative adjustment, the window length is finally adjusted to 4 seconds, the second breathing segment is 20-24, and the preset window slides for 4 seconds, and iterative adjustment is performed again at 24-29 seconds; and so on, all breathing segments of the historical breathing signal are obtained.

[0027] It should be noted that the time domain length of the preset window is the basic value of the window length after each sliding, and remains unchanged during the sliding process.

[0028] See also Figure 2 , which shows a flow chart of a method for obtaining breathing segments provided by an embodiment of the present invention, specifically comprising: Step S101: For the historical breathing signal of the latest window length after any sliding, select any signal component as the target signal component; obtain the spectrum of the target signal component, translate the straight line parallel to the frequency axis from the maximum value to the minimum value of the spectrum amplitude, and obtain the intersection length of the straight line corresponding to each spectrum amplitude and the spectrum line; according to the variation characteristics of the intersection length of the target signal component with the spectrum amplitude, obtain the frequency concentration sub-coefficient of the target signal component.

[0029] Since the processing method for the latest window length after each slide is consistent, and the analysis method for each signal component of the historical respiratory signal of the latest window length is consistent, one of them is selected as the target signal component for description and will not be repeated.

[0030] Considering that the spectrum diagram is more conducive to analyzing the concentrated characteristics of frequency, the more concentrated the frequency is, the sharper the waveform in the spectrum diagram is, the higher the amplitude is, and the narrower the waveform is. Therefore, the straight line parallel to the frequency axis is translated from the maximum value to the minimum value of the spectrum diagram to obtain the intersection length of the straight line corresponding to each spectrum amplitude and the spectrum line.

[0031] It should be noted that the straight line corresponding to the spectrum amplitude intersects the spectrum line and is between the spectrum line and the horizontal axis, which is an intersecting line segment; when the straight line corresponding to the spectrum amplitude and the spectrum line have multiple intersecting line segments, the sum of all the intersecting line segments is taken as the intersection length. Figure 3 , which shows a schematic diagram of an intersection length provided by an embodiment of the present invention; Figure 3 In the figure, the horizontal axis is frequency and the vertical axis is spectrum amplitude. Set the waveform function to (For illustration only, not actual spectrum line), Y1 corresponds to , Y2 corresponds to , Y1 is the straight line corresponding to the maximum value of the spectrum amplitude. If we translate downward from Y1 to obtain Y2, there are two intersecting line segments between the straight line Y2 and the spectrum line. and The length and value of these two line segments is the intersection length of the spectrum amplitude corresponding to Y2.

[0032] The higher the spectrum amplitude, the shorter the intersection length, which means the frequency is more concentrated. Therefore, the frequency concentration sub-coefficient of the target signal component is obtained according to the variation characteristics of the intersection length of the target signal component with the spectrum amplitude.

[0033] In one embodiment of the present invention, the sum of the products of the negative correlation mapping values ​​of all intersection lengths of the target signal component and the corresponding spectrum amplitudes is normalized, and the normalized result is used as the frequency concentrated sub-coefficient of the target signal component.

[0034] As an example: The calculation formula for the frequency concentration coefficient includes: ; Wherein, i represents the serial number of the target signal component; represents the frequency-concentrated sub-coefficient of the i-th target signal component; represents the linear normalization function; y represents the sequence number of the spectrum amplitude; The data value representing the yth spectrum amplitude of the i-th target signal component; Indicates the number of spectrum amplitudes; It represents the exponential function with the natural constant e as the base; Represents the intersection length of the yth spectrum amplitude of the i-th target signal component; Represents the negative correlation mapping value of the intersection length of the yth spectrum amplitude of the i-th target signal component.

[0035] In the calculation formula of the frequency concentration coefficient, the intersection length is used as the independent variable x for negative correlation mapping through the exp(-x) function to obtain the negative correlation mapping value, and the spectrum amplitude and the intersection length are fused by multiplication, and then summed to obtain It shows the variation characteristics of the intersection length with the spectrum amplitude. The higher the spectrum amplitude, the shorter the intersection length, which means the frequency is more concentrated and the frequency concentration coefficient is larger.

[0036] It should be noted that when the straight line parallel to the frequency axis is translated, the translation step is set to 1 to obtain the number of spectrum amplitudes. The implementer can also adjust the translation step by himself.

[0037] Step S102: according to the mean of the frequency concentrated sub-coefficients of all signal components, combined with the difference between the frequency concentrated sub-coefficient of each signal component and the mean of the frequency concentrated sub-coefficients, the frequency concentrated coefficient of the current latest window length is obtained.

[0038] Considering that there are multiple signal components in the historical breathing signal of the latest window length, it is necessary to further integrate all signal components, evaluate the overall frequency concentration characteristics, and obtain the frequency concentration coefficient; considering that the larger the mean of the frequency concentration sub-coefficient, the more concentrated the frequencies of all signal components, the mean of the frequency concentration sub-coefficient is positively correlated with the frequency concentration coefficient; at the same time, the smaller the difference between the frequency concentration sub-coefficient and the mean of the frequency concentration sub-coefficient of each signal component, the lower the degree of discreteness and the better the overall signal decomposition effect, so the difference between the mean of the frequency concentration sub-coefficient and the frequency concentration sub-coefficient is negatively correlated with the frequency concentration coefficient.

[0039] As an example, the calculation formula for the frequency concentration factor includes: ; in, Indicates the frequency concentration factor corresponding to the latest window length; Represents the mean value of the sub-coefficients of the frequency concentration of all signal components of the historical respiratory signal of the latest window length; I represents the number of target signal components; i represents the sequence number of the target signal component; represents the frequency-concentrated sub-coefficient of the i-th target signal component; Indicates taking the absolute value.

[0040] In the calculation formula of the frequency concentration coefficient, the difference between the frequency concentration coefficient and the mean of the frequency concentration coefficient is expressed by the absolute value of the difference. The function performs negative correlation mapping, adjusts the logical relationship, and then merges by multiplication and , which shows the frequency concentration characteristics of the signal component of the latest window length.

[0041] Step S103: If the frequency concentration coefficient of the current latest window length is less than the first preset concentration threshold, the window length is reduced by the preset adjustment step to obtain a new window length; if the frequency concentration coefficient of the current latest window length is greater than or equal to the second preset concentration threshold, the window length is increased by the preset adjustment step to obtain a new window length; if the frequency concentration coefficient of the current latest window length is greater than or equal to the first preset concentration threshold and less than the second preset concentration threshold, the iteration is terminated and the historical breathing signal corresponding to the current latest window length is taken as a breathing segment.

[0042] As an example, the first preset concentration threshold is 0.5, and the second preset concentration threshold is 0.7. For example, the current latest window length is 5 seconds, the frequency concentration coefficient is 0.9, and the window length is adjusted to 6 seconds; the latest window length is 6 seconds, the frequency concentration coefficient is 0.85, and the window length is adjusted to 7 seconds; the latest window length is 7 seconds, the frequency concentration coefficient is 0.8, and the window length is adjusted to 8 seconds; the latest window length is 8 seconds, the frequency concentration coefficient is 0.77, and the window length is adjusted to 9 seconds; the latest window length is 9 seconds, the frequency concentration coefficient is 0.68, and the iteration is terminated. The current latest window length is 9 seconds, and the historical breathing signal in the window corresponding to this window length is regarded as a breathing segment.

[0043] It should be noted that the implementer can adjust the first preset concentration threshold and the second preset concentration threshold by himself; when there are two consecutive iterative adjustments with opposite adjustment directions, the shorter window length is selected. For example, if the frequency concentration feature corresponding to a window length of 20 seconds is 0.75, after increasing the adjustment, the frequency concentration feature corresponding to the new window length of 21 seconds is 0.48, and the window length is 20 seconds at this time. For example, if the frequency concentration feature corresponding to a window length of 20 seconds is 0.4, after decreasing the adjustment, the frequency concentration feature corresponding to the new window length of 19 seconds is 0.72, and the window length is 19 seconds at this time.

[0044] Step S2: according to the difference of the breathing amplitude and the difference of the signal component between any two breathing segments, the cluster distance between the corresponding two breathing segments is obtained; based on the cluster distance, the breathing segments are clustered, and each cluster corresponds to a breathing pattern.

[0045] After segmenting the respiratory signal, it is necessary to analyze the differences between the respiratory segments and divide the respiratory patterns to prepare for the subsequent real-time identification of the respiratory status of child patients.

[0046] Considering that the differences between different breathing patterns are mainly reflected in the breathing amplitude and frequency, and EMD decomposition can decompose the signal into signal components in different frequency ranges, including the breathing frequency characteristics of the breathing segment, the clustering distance between the corresponding two breathing segments is obtained according to the difference in breathing amplitude and signal components between any two breathing segments; based on the clustering distance, the breathing segments are clustered, and each cluster corresponds to a breathing pattern. With the help of clustering, similar breathing segments are clustered into one category to distinguish different breathing patterns.

[0047] Preferably, in one embodiment of the present invention, considering that the frequency at the maximum spectrum amplitude is the most important frequency of the signal component, the frequency at the maximum spectrum amplitude in the spectrum diagram of each signal component is recorded as the representative frequency, which simplifies the frequency identification and facilitates the comparison of frequency differences between different signal components; Any two breathing segments are obtained to form a target binary group. For each signal component in any breathing segment in the target binary group, a signal component with the closest representative frequency in another breathing segment is obtained as a matching signal component.

[0048] For example, the breathing segment with serial number Z1 has 5 signal components, and the breathing segment with serial number Z2 has 6 signal components. The representative frequencies of the first signal component in Z1 and the second signal component in Z2 are closest, that is, the absolute value of the representative frequency difference is the smallest. Then, the second signal component in Z2 is the matching signal component of the first signal component in Z1.

[0049] It should be noted that the same signal component can be a matching signal component of multiple signal components. For example, when the second signal component in Z1 is also closest to the representative frequency of the second signal component in Z2, the second signal component in Z2 is also a matching signal component of the first signal component in Z1.

[0050] The calculation formula for cluster distance includes: ; Among them, u and v are the serial numbers of the breathing segments; represents the clustering distance between the u-th breathing segment and the v-th breathing segment; represents linear normalization; represents the absolute value of the difference between the maximum breathing amplitude of the u-th breathing segment and the v-th breathing segment; represents the absolute value of the difference between the minimum breathing amplitude of the u-th breathing segment and the v-th breathing segment; i represents the sequence number of the signal component of the u-th breathing segment; k represents the sequence number of the signal component of the v-th breathing segment; represents the number of signal components of the u-th respiratory segment; represents the number of signal components of the vth respiratory segment; represents the representative frequency of the i-th signal component of the u-th respiratory segment; The i-th signal component of the u-th breathing segment and the representative frequency of the corresponding matching signal component in the v-th breathing segment; Indicates taking the absolute value; represents the representative frequency of the kth signal component of the vth respiratory segment; The kth signal component of the vth respiratory segment corresponds to the representative frequency of the matching signal component in the uth respiratory segment.

[0051] In the calculation formula of cluster distance, the difference characteristics of data are shown by the absolute value of difference, and the difference between two breathing segments is shown by the absolute value of difference. as well as , respectively reflecting the difference in the maximum value of the breathing amplitude and the difference in the minimum value of the breathing amplitude. After multiplication and fusion, it represents the difference in the breathing amplitude between the two breathing segments. It represents the frequency difference characteristics of the signal component of the u-th breathing segment and the signal component with the closest representative frequency in the v-th breathing segment, through The frequency difference characteristics between the signal component of the vth breathing segment and the signal component representing the closest frequency in the uth breathing segment are expressed by multiplication and fusion, and the difference in signal components between the two breathing segments is expressed. The difference in breathing amplitude and breathing frequency reflected by the signal component are fused to measure the difference between the two breathing segments as the clustering distance, which is convenient for the subsequent clustering and division of breathing patterns.

[0052] The clustering distance of all target binary groups is obtained through the clustering distance calculation formula.

[0053] As a preferred embodiment, the neighborhood radius is set to 0.1, the minimum number of points is set to 3, and a number of clusters are obtained using the DBSCAN algorithm. The breathing segments in each cluster are recorded as a breathing pattern, and a number of breathing patterns are obtained.

[0054] It should be noted that the DBSCAN algorithm is already an existing technology, and implementers can also use the K-means clustering algorithm, which will not be described in detail.

[0055] Step S3: According to the overall characteristics of the breathing amplitude range of all breathing segments in each cluster and the distribution characteristics of the frequencies of all first signal components, the breathing frequency and breathing amplitude range of each breathing pattern are obtained; according to the length characteristics of the breathing segments in each breathing pattern, the normal breathing pattern is obtained.

[0056] After dividing the breathing patterns, it is necessary to quantify the physiological characteristics of each pattern to provide a reference for the subsequent identification of abnormal breathing states. Taking into account the overall characteristics of the breathing amplitude range of all breathing segments in the cluster, it represents the range and regularity of changes in the depth of a breathing pattern. The frequency of the first signal component obtained by EMD decomposition represents the main breathing frequency in the breathing signal. Therefore, according to the overall characteristics of the breathing amplitude range of all breathing segments in each cluster, and the distribution characteristics of the frequencies of all first signal components, the breathing frequency and breathing amplitude range of each breathing pattern are obtained, the parameter boundaries of the breathing pattern are clarified, and the ability to distinguish breathing patterns is enhanced.

[0057] Preferably, in one embodiment of the present invention, the mean of the representative frequencies of the first signal components of all respiratory segments in each cluster is used as the respiratory frequency of the corresponding respiratory pattern, and the distribution characteristics of the frequency are represented by the mean of the representative frequencies; The mean of the maximum respiratory amplitude of all respiratory segments in each cluster is taken as the maximum value of the respiratory amplitude range of the corresponding respiratory pattern; the mean of the minimum respiratory amplitude of all respiratory segments in each cluster is taken as the minimum value of the respiratory amplitude range of the corresponding respiratory pattern; the overall characteristics of the respiratory amplitude range are expressed by the mean of the maximum respiratory amplitude and the mean of the minimum respiratory amplitude.

[0058] See also Figure 4 , which shows a schematic diagram of a breathing amplitude range of all breathing modes provided by an embodiment of the present invention; Figure 4 In the figure, the horizontal axis is the serial number of the breathing mode, the vertical axis is the breathing amplitude, and each vertical line corresponds to a breathing amplitude range.

[0059] See also Figure 5 , which shows a schematic diagram of respiratory frequencies of all respiratory modes provided by an embodiment of the present invention; Figure 5 In the figure, the horizontal axis is the serial number of the breathing pattern, the vertical axis is the breathing frequency, each dot corresponds to a breathing frequency, and the curve is the change curve of the breathing frequency with the breathing pattern.

[0060] Further considering that the length of the breathing segment reflects the stable duration of breathing, and the normal breathing pattern is more stable than other breathing patterns, the normal breathing pattern can be effectively screened and obtained as the benchmark pattern according to the length characteristics of the breathing segments in each breathing pattern, so as to facilitate the subsequent real-time judgment of whether the breathing state is abnormal; at the same time, the normal breathing pattern determined based on the historical breathing signal of the current patient can better represent the normal breathing pattern of the current patient, reducing the impact of physiological differences among different age groups or individuals.

[0061] Preferably, in one embodiment of the present invention, considering that for any breathing pattern, the larger the window and the more the number of breathing segments, the greater the possibility that the breathing pattern is a normal pattern, the product of the mean of the time domain lengths of all breathing segments of each breathing pattern and the sum of the time domain lengths of all breathing segments is used as the normal possibility coefficient of each breathing pattern; the length characteristics of the breathing segments in the breathing pattern are represented by the mean and sum of the time domain lengths of all breathing segments of the breathing pattern; The breathing pattern with the largest normal possible coefficient is selected as the normal breathing pattern.

[0062] It should be noted that pediatric patients may have an abnormal breathing pattern for a long time, and the corresponding normal coefficient is the largest. For this patient, this abnormal breathing pattern is a breathing pattern that maintains the stability of the patient's vital signs or the normal operation of the compensatory mechanism, so it should be regarded as the patient's individualized normal breathing pattern.

[0063] Step S4: Acquire the real-time breathing signal of the current patient and segment it in real time; according to the difference characteristics of the breathing amplitude range between the breathing segment at the current moment and the normal breathing pattern, as well as the difference characteristics of the breathing frequency, combined with the difference in the number of breathing segments between the breathing pattern at the current moment and the breathing pattern of the adjacent breathing segments, acquire the breathing abnormality coefficient at the current moment; determine whether to issue an early warning based on the breathing abnormality coefficient at the current moment.

[0064] After obtaining the respiratory frequency and respiratory amplitude range of the normal breathing pattern of the current child patient through steps S1-S3, the real-time respiratory signal of the current patient can be obtained and segmented in real time, so as to identify whether the current child patient is in an abnormal breathing state and issue an early warning in time to ensure the safety of the child patient.

[0065] It should be noted that the real-time segmentation method is consistent with the segmentation method of the breathing segmentation in step S1, which will not be repeated here. Considering that the current moment may be in a new breathing segment, and the new breathing segment is short and it is difficult to show the patient's breathing characteristics, if the current moment is in the preset initial stage of the new breathing segment, it is determined that the current moment belongs to the previous breathing segment in the time domain. As an example, the preset initial stage is the first 3 seconds of a breathing segment, which can be adjusted by the implementer.

[0066] Taking into account the difference characteristics of the breathing amplitude range and breathing frequency between the current breathing segment and the normal breathing pattern, the current degree of abnormal breathing of the patient is reflected; at the same time, considering that there is a difference in the number of breathing segments corresponding to the normal breathing pattern and the abnormal breathing pattern, the difference in the number of breathing segments between the breathing pattern at the current moment and the breathing pattern of the adjacent breathing segment can show the current degree of abnormal breathing from the perspective of the change of the breathing pattern; Therefore, based on the difference characteristics of the breathing amplitude range between the current breathing segment and the normal breathing pattern, as well as the difference characteristics of the breathing frequency, combined with the difference in the number of breathing segments between the current breathing pattern and the adjacent breathing segments, the breathing abnormality coefficient at the current moment is obtained to characterize the degree of abnormality of the current child patient's breathing state at the current moment, providing a basis for subsequent determination of whether to issue an early warning.

[0067] Preferably, in one embodiment of the present invention, the calculation formula of the abnormal breathing coefficient includes: ; Wherein, L represents the respiratory abnormality coefficient at the current moment; represents an exponential function with the natural constant e as the base; h is the serial number of the breathing segment to which the current moment belongs; Indicates the breathing amplitude range of the breathing segment at the current moment; Respiratory amplitude range representing normal breathing pattern; Indicates the intersection of the breathing amplitude range of the breathing segment at the current moment and the breathing amplitude range of the normal breathing pattern; The union of the breathing amplitude range of the breathing segment at the current moment and the breathing amplitude range of the normal breathing pattern; represents the linear normalization function; Indicates taking the absolute value; Indicates the representative frequency of the breathing segment at the current moment; Respiratory rate, which indicates a normal breathing pattern; The number of breathing segments representing the breathing pattern of adjacent breathing segments at the current moment; Indicates the number of breathing segments corresponding to the breathing pattern at the current moment.

[0068] In the calculation formula of the respiratory abnormality coefficient, the intersection and union ratio is used to calculate Indicates the difference characteristics of the breathing amplitude range, The larger the value, the smaller the difference between the breathing segment at the current moment and the breathing amplitude range of the normal breathing pattern. From the perspective of the breathing amplitude range, the less likely it is abnormal at the current moment. The negative correlation mapping is performed through the exp(-x) function to adjust the logic, and the smaller the breathing abnormality coefficient is; the absolute value of the difference is used to Indicates the difference characteristics of breathing rate, The larger the value is, the more likely it is abnormal from the perspective of respiratory frequency, and the greater the respiratory abnormality coefficient is. It shows the difference in the number of breathing segments between the breathing pattern at the current moment and the breathing pattern of the adjacent breathing segment. Since the normal breathing pattern has the largest number of segments and the abnormal breathing pattern has the smallest number of segments, The larger it is, the more likely it is that the normal breathing pattern has changed to an abnormal breathing pattern, the more likely it is abnormal at the current moment, and the larger the breathing abnormality coefficient.

[0069] It should be noted that, in one embodiment of the present invention, the frequency of early warning determination is once per second, and the implementer can adjust the frequency of early warning determination in combination with the implementation scenario.

[0070] When obtaining the breathing pattern of the breathing segment at the current moment, as a preferred embodiment, the implementer can select several breathing segments closest to the center of the cluster in each cluster corresponding to the historical breathing signal, such as selecting 5 breathing segments as representative segments of each cluster, calculate the average value of the cluster distance between the breathing segment at the current moment and the representative segment of each cluster, and select the breathing pattern of the cluster with the smallest average value of the cluster distance as the breathing pattern at the current moment; In another embodiment of the present invention, the matching coefficient between the breathing segment and each breathing pattern can be obtained by combining the difference between the breathing amplitude range of the breathing segment at the current moment and the breathing amplitude range of each breathing pattern, and the best matching breathing pattern can be selected; the calculation formula of the matching coefficient includes: ; Where s is the serial number of the breathing mode; represents the matching coefficient between the hth breathing segment and the sth breathing pattern; Represents the breathing amplitude range of the sth breathing mode.

[0071] In the calculation formula of the matching coefficient, the greater the intersection-and-combination ratio of the breathing amplitude range, the greater the matching degree between the current breathing segment and the corresponding breathing pattern, and the greater the matching coefficient; The smaller it is, the smaller the difference in breathing frequency is, the greater the matching degree is, and the larger the matching coefficient is. Finally, the breathing pattern with the largest matching coefficient is selected as the breathing pattern of the breathing segment at the current moment.

[0072] In another embodiment of the present invention, the breathing pattern of the current moment can be divided into breathing segments by real-time clustering.

[0073] After obtaining the abnormal breathing coefficient representing the abnormal degree of the breathing state of the current child patient at the current moment, it can be determined whether to issue an early warning based on the abnormal breathing coefficient at the current moment.

[0074] Preferably, in one embodiment of the present invention, when the breathing abnormality coefficient is greater than a preset abnormality threshold, an early warning is issued.

[0075] As an example, the preset abnormal threshold is 0.5.

[0076] An embodiment of the present invention also provides a system for identifying an early critical respiratory state in children, the system comprising a memory, a processor and a computer program, wherein the memory is used to store a corresponding computer program, the processor is used to run the corresponding computer program, and when the computer program runs in the processor, it can implement a method for identifying an early critical respiratory state in children described in steps S1-S4.

[0077] In summary, in view of the technical problem that the existing microwave detection and signal decomposition-based methods have low accuracy in identifying children's respiratory status, the present invention proposes a method and system for identifying critical respiratory status in early childhood. The present invention first obtains the historical respiratory signal of the current patient in a preset time interval, segments the historical respiratory signal, and obtains respiratory segments; further divides the respiratory mode according to the difference in respiratory amplitude and signal component between the respiratory segments; further obtains the respiratory frequency and respiratory amplitude range of each respiratory mode, and screens out the normal respiratory mode; further obtains the real-time respiratory signal of the current patient and segments it in real time; according to the difference characteristics between the respiratory segment at the current moment and the normal respiratory mode, combined with the respiratory mode at the current moment and the respiratory mode of the adjacent respiratory segments, the number of respiratory segments is different, and the respiratory abnormality coefficient is obtained; finally, based on the respiratory abnormality coefficient, it is determined whether to issue an early warning, reduce the influence of modal mixing, reduce the influence of physiological differences of different age groups or individuals, and improve the accuracy of respiratory status recognition.

[0078] It should be noted that the sequence of the above embodiments of the present invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0079] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for identifying critical respiratory status in early childhood, characterized in that: The method comprises: Obtain the historical respiratory signal of the current patient within a preset time interval; slide the preset window on the historical respiratory signal, decompose the historical respiratory signal within the preset window after sliding based on the EMD algorithm, iteratively adjust the window length according to the frequency concentration characteristics of the signal components, segment the historical respiratory signal, and obtain respiratory segments; According to the difference in breathing amplitude and signal component between any two breathing segments, a cluster distance between the corresponding two breathing segments is obtained; based on the cluster distance, the breathing segments are clustered, and each cluster cluster corresponds to a breathing pattern; According to the overall characteristics of the respiratory amplitude range of all respiratory segments in each cluster and the distribution characteristics of the frequencies of all first signal components, the respiratory frequency and respiratory amplitude range of each respiratory pattern are obtained; according to the length characteristics of the respiratory segments in each respiratory pattern, the normal respiratory pattern is obtained; The real-time respiratory signal of the current patient is obtained and segmented in real time; based on the difference characteristics of the respiratory amplitude range between the current respiratory segment and the normal respiratory pattern, as well as the difference characteristics of the respiratory frequency, combined with the difference in the number of respiratory segments between the current respiratory pattern and the adjacent respiratory segments, the respiratory abnormality coefficient at the current moment is obtained; based on the current respiratory abnormality coefficient, it is determined whether to issue an early warning.

2. A method for identifying critical respiratory status in early childhood according to claim 1, characterized in that: The method for obtaining the breathing segment comprises: The preset window starts to slide from the starting point of the historical respiratory signal, and the window length is iteratively adjusted after each sliding, and the window length determined after each sliding is used as the sliding step length for the next sliding; For the historical breathing signal of the latest window length after any sliding, select any signal component as the target signal component; obtain the spectrum of the target signal component, translate the straight line parallel to the frequency axis from the maximum value to the minimum value of the spectrum amplitude, and obtain the intersection length of the straight line corresponding to each spectrum amplitude and the spectrum line; according to the variation characteristics of the intersection length of the target signal component with the spectrum amplitude, obtain the frequency concentration sub-coefficient of the target signal component; According to the mean of the frequency concentration sub-coefficients of all the signal components, combined with the difference between the frequency concentration sub-coefficient of each signal component and the mean of the frequency concentration sub-coefficients, the frequency concentration coefficient of the latest window length is obtained; the mean of the frequency concentration sub-coefficients is positively correlated with the frequency concentration coefficient; the difference between the frequency concentration sub-coefficients and the mean of the frequency concentration sub-coefficients is negatively correlated with the frequency concentration coefficient; If the frequency concentration coefficient of the current latest window length is less than the first preset concentration threshold, the window length is reduced by the preset adjustment step to obtain a new window length; if the frequency concentration coefficient of the current latest window length is greater than or equal to the second preset concentration threshold, the window length is increased by the preset adjustment step to obtain a new window length; if the frequency concentration coefficient of the current latest window length is greater than or equal to the first preset concentration threshold and less than the second preset concentration threshold, the iteration is terminated and the historical breathing signal corresponding to the current latest window length is taken as a breathing segment.

3. A method for identifying critical respiratory status in early childhood according to claim 2, characterized in that: The method for obtaining the sub-coefficients in the frequency concentration includes: After normalizing the sum of the products of all the negative correlation mapping values ​​of the intersection lengths of the target signal component and the corresponding spectrum amplitudes, the normalized result is used as the frequency concentrated sub-coefficient of the target signal component.

4. A method for identifying early critical respiratory status in children according to claim 1, characterized in that: The method for obtaining the cluster distance includes: The frequency at the maximum value of the spectrum amplitude in the spectrum diagram of each signal component is recorded as the representative frequency; any two of the breathing segments are obtained to form a target binary group, and for each of the signal components in any of the breathing segments in the target binary group, the signal component with the closest representative frequency in the other breathing segment is obtained as the matching signal component; The calculation formula for cluster distance includes: ； Among them, u and v are the serial numbers of the breathing segments; represents the clustering distance between the u-th breathing segment and the v-th breathing segment; represents linear normalization; represents the absolute value of the difference between the maximum breathing amplitude of the u-th breathing segment and the v-th breathing segment; represents the absolute value of the difference between the minimum breathing amplitude of the u-th breathing segment and the v-th breathing segment; i represents the sequence number of the signal component of the u-th breathing segment; k represents the sequence number of the signal component of the v-th breathing segment; represents the number of signal components of the u-th respiratory segment; represents the number of signal components of the vth respiratory segment; represents the representative frequency of the i-th signal component of the u-th respiratory segment; The representative frequency of the i-th signal component of the u-th breathing segment and the corresponding matching signal component in the v-th breathing segment; Indicates taking the absolute value; represents the representative frequency of the kth signal component of the vth respiratory segment; The kth signal component of the vth respiratory segment corresponds to the representative frequency of the matching signal component in the uth respiratory segment.

5. A method for identifying critical respiratory status in early childhood according to claim 4, characterized in that: The method for obtaining the respiratory frequency and respiratory amplitude range of each respiratory mode includes: Taking the mean of the representative frequencies of the first signal components of all the respiratory segments in each cluster as the respiratory frequency of the corresponding respiratory pattern; The average of the maximum values ​​of the breathing amplitude of all the breathing segments in each cluster is used as the maximum value of the breathing amplitude range of the corresponding breathing pattern; the average of the minimum values ​​of the breathing amplitude of all the breathing segments in each cluster is used as the minimum value of the breathing amplitude range of the corresponding breathing pattern.

6. A method for identifying critical respiratory status in early childhood according to claim 1, characterized in that: The method for acquiring the normal breathing pattern includes: The product of the mean value of the time domain lengths of all the breathing segments of each breathing pattern and the sum of the time domain lengths of all the breathing segments is used as the normal possible coefficient of each breathing pattern; The breathing pattern with the largest normal possible coefficient is selected as the normal breathing pattern.

7. A method for identifying early critical respiratory status in children according to claim 5, characterized in that: The calculation formula of the abnormal breathing coefficient includes: ； Wherein, L represents the respiratory abnormality coefficient at the current moment; represents an exponential function with the natural constant e as the base; h is the serial number of the breathing segment to which the current moment belongs; Indicates the breathing amplitude range of the breathing segment at the current moment; Respiratory amplitude range representing normal breathing pattern; Indicates the intersection of the breathing amplitude range of the breathing segment at the current moment and the breathing amplitude range of the normal breathing pattern; The union of the breathing amplitude range of the breathing segment at the current moment and the breathing amplitude range of the normal breathing pattern; represents the linear normalization function; Indicates taking the absolute value; Indicates the representative frequency of the breathing segment at the current moment; Respiratory rate, which indicates a normal breathing pattern; The number of breathing segments representing the breathing pattern of adjacent breathing segments at the current moment; Indicates the number of breathing segments corresponding to the breathing pattern at the current moment.

8. A method for identifying early critical respiratory status in children according to claim 7, characterized in that: The method for determining whether to issue an early warning based on the abnormal breathing coefficient at the current moment includes: When the abnormal breathing coefficient is greater than a preset abnormal threshold, an early warning is issued.

9. A method for identifying critical respiratory status in early childhood according to claim 2, characterized in that: The preset adjustment step is 1 second.

10. A system for identifying early critical respiratory states in children, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a method for identifying an early critical respiratory state in children as described in any one of claims 1 to 9 are implemented.

Images