Method and device for determining SAS patient based on PPG signal

Abstract

The invention discloses a method and device for determining SAS patients based on PPG signals, and relates to the technical field of biomedicine. The method comprises the following steps: acquiring a target continuous PPG signal and oxyhemoglobin saturation data of a patient within a set duration; determining a trough position of the target continuous PPG signal based on a window sliding minimum detection method, and cutting the target continuous PPG signal into at least two single PPG signals; determining at least one risk duration corresponding to the patient and a blood oxygen change amplitude corresponding to each risk duration from set durations according to the blood oxygen saturation data; performing multi-peak fitting processing on each single PPG signal by adopting a Gaussian function to obtain a Gaussian wave mean value variation amplitude corresponding to each risk duration; and determining an SAS result of the patient according to the blood oxygen change amplitude and the Gaussian wave mean value change amplitude corresponding to each risk duration and a judgment standard. According to the method, the Gaussian wave mean value is used for replacing the heart rate, interference of high-frequency signals can be effectively ignored, and the SAS detection result is more reliable.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of biomedical technology, and in particular to a method and device for determining SAS patients based on PPG signals. Background Art

[0002] SAS usually refers to Sleep Apnea Syndrome (SAS), a common sleep disorder characterized by repeated pauses in breathing or irregular breathing during sleep, resulting in insufficient oxygen at night and reduced sleep quality.

[0003] In the prior art, when determining whether a patient is a SAS patient, a photoplethysmography (PPG) sensor is usually used to collect the patient's heart rate and blood oxygen saturation, and then the PPG signal is processed by wavelet transform to extract blood oxygen saturation (SpO2), heart rate (HR) and its amplitude change (ΔSpO2, ΔHR), and the relationship between the ratio of ΔSpO2 and ΔHR and the screening criteria is analyzed to determine whether the patient has SAS. However, research has found that the accuracy of this method is completely dependent on the stability of HR, but the HR detection results will be affected by environmental noise and motion artifacts, thereby affecting the SAS screening results and increasing the risk of misjudgment. Summary of the invention

[0004] The purpose of this application is to solve at least one of the above-mentioned technical deficiencies.

[0005] On the one hand, an embodiment of the present application provides a method for determining SAS patients based on PPG signals, the method comprising:

[0006] Obtain the patient's target continuous PPG signal and blood oxygen saturation data within a set time period, where the target continuous PPG signal is the continuous PPG signal corresponding to the pulse data;

[0007] Determine the trough position of the target continuous PPG signal based on the window sliding minimum detection method, and cut the target continuous PPG signal into at least two single PPG signals according to the trough position;

[0008] Determine at least one risk duration corresponding to the patient from the set duration according to the blood oxygen saturation data, and the blood oxygen change amplitude corresponding to each risk duration;

[0009] Gaussian function was used to perform multi-peak fitting processing on each single PPG signal to obtain the Gaussian wave mean change amplitude corresponding to each risk duration;

[0010] The patient's SAS result is determined based on the blood oxygen change amplitude corresponding to each risk duration, the Gaussian wave mean change amplitude corresponding to each risk duration, and the judgment criteria.

[0011] Optionally, obtain the patient's target continuous PPG signal within a set time period, including:

[0012] Obtaining the initial continuous PPG signal corresponding to the patient's pulse data within a set time period;

[0013] Obtaining a cutoff frequency and a high-pass filter, and determining a filter coefficient according to the cutoff frequency and the high-pass filter;

[0014] Based on the filter coefficient, the initial continuous PPG signal is processed to remove the baseline drift interference to obtain a first continuous PPG signal;

[0015] Acquire a notch frequency and a notch filter, and determine a notch filter coefficient according to the notch frequency and the notch filter;

[0016] The first continuous PPG signal is processed to remove specific frequency interference based on the notch filter coefficient to obtain a target continuous PPG signal.

[0017] Optionally, determining the trough position of the target continuous PPG signal based on a window sliding minimum detection method includes:

[0018] An initial window is obtained, where the number of sampling points included in the initial window is determined according to the sampling rate of the target continuous PPG signal and the heart rate reference value;

[0019] Based on each sliding of the initial window on the target continuous PPG signal by a set distance, at least one first window is obtained, and according to the data point value in each first window, at least one second window is determined from the at least one first window;

[0020] According to the values ​​of the data points in each second window, respectively determine the minimum data points corresponding to each second window, and determine the rising and falling trends between each minimum data point and adjacent data points;

[0021] The position of the minimum data point whose rising and falling trend meets the preset requirements is taken as the trough position of the target continuous PPG signal.

[0022] Optionally, if the number of extremely small data points whose rising and falling trends meet preset requirements reaches a set number, and the sliding distance does not reach the end point of the target continuous PPG signal, the method further includes:

[0023] The window length of the initial window and the size of the set distance are adjusted respectively to obtain an adjustment window and an adjustment distance, and the trough position of the target continuous PPG signal is further determined based on the adjustment window and the adjustment distance.

[0024] Optionally, determining at least one risk duration corresponding to the patient from the set duration according to the blood oxygen saturation data includes:

[0025] Determine at least one time duration during which the blood oxygen value in the blood oxygen saturation data corresponding to the set time duration is lower than the preset value;

[0026] At least one duration during which the blood oxygen value is lower than a preset value is used as at least one risk duration corresponding to the patient.

[0027] Optionally, a Gaussian function is used to perform multi-peak fitting processing on each single PPG signal to obtain the Gaussian wave mean change amplitude corresponding to each risk duration, including:

[0028] Determining at least two target single PPG signals corresponding to each risk duration from at least two single PPG signals according to time information of each single PPG signal;

[0029] For each risk duration, a Gaussian function is used to perform multi-peak fitting processing on each target single PPG signal corresponding to the risk duration to obtain the Gaussian wave mean change amplitude corresponding to each risk duration.

[0030] Optionally, a Gaussian function is used to perform multi-peak fitting processing on each target single PPG signal corresponding to the risk duration to obtain the Gaussian wave mean change amplitude corresponding to each risk duration, including:

[0031] The Gaussian function is used to perform multi-peak fitting processing on the single PPG signal of each target corresponding to the risk duration to obtain the Gaussian wave mean of the single PPG signal of each target;

[0032] According to the Gaussian wave mean of each target single PPG signal, the Gaussian wave mean change amplitude corresponding to each risk duration is obtained.

[0033] Optionally, a Gaussian function is used to perform multi-peak fitting processing on each target single PPG signal corresponding to the risk duration to obtain a Gaussian wave mean of each target single PPG signal, including:

[0034] For each target single PPG signal, a Gaussian function and an initial parameter value of the function are obtained, and the target single PPG signal is processed based on the Gaussian function to obtain a function value corresponding to each data point in the target single PPG signal;

[0035] Constructing a corresponding target function based on the numerical value of each data point in the target single PPG signal and the function value corresponding to each data point in the target single PPG signal;

[0036] Substitute the initial parameter value of the function into the objective function and perform iterative calculation until the convergence condition is reached to obtain the Gaussian wave mean of the target single PPG signal.

[0037] Optionally, the judgment criteria include the product standard value and the hypopnea frequency standard, and the SAS result of the patient is determined according to the blood oxygen change amplitude corresponding to each risk duration, the Gaussian wave mean change amplitude corresponding to each risk duration, and the judgment criteria, including:

[0038] For each risk duration, the blood oxygen change amplitude corresponding to the risk duration and the corresponding Gaussian wave mean change amplitude are multiplied to obtain a first value corresponding to the risk duration;

[0039] Compare the first value corresponding to each risk duration with the product standard respectively, and determine the number of target risk durations from all risk durations;

[0040] The number of target risk times was compared with the hypopnea criteria to determine the patient's SAS outcome.

[0041] On the other hand, an embodiment of the present application provides a device for determining SAS patients based on a PPG signal, comprising:

[0042] A data acquisition module is used to obtain the patient's target continuous PPG signal and blood oxygen saturation data within a set time period, where the target continuous PPG signal is a continuous PPG signal corresponding to the pulse data;

[0043] A signal cutting module, used to determine the trough position of the target continuous PPG signal based on the window sliding minimum detection method, and cut the target continuous PPG signal into at least two single PPG signals according to the trough position;

[0044] A data processing module, used to determine at least one risk duration corresponding to the patient from the set duration according to the blood oxygen saturation data, and a blood oxygen variation amplitude corresponding to each risk duration;

[0045] The data fitting module is used to perform multi-peak fitting processing on each single PPG signal using a Gaussian function to obtain the Gaussian wave mean change amplitude corresponding to each risk duration;

[0046] The result determination module is used to determine the patient's SAS result according to the blood oxygen change amplitude corresponding to each risk duration, the Gaussian wave mean change amplitude corresponding to each risk duration, and the judgment criteria.

[0047] On the other hand, an embodiment of the present application provides an electronic device, including a processor and a memory:

[0048] The memory is configured to store machine-readable instructions, which, when executed by the processor, cause the processor to perform any one of the methods for determining a SAS patient based on a PPG signal.

[0049] The beneficial effects brought by the technical solution provided in the embodiments of the present application include at least:

[0050] In the embodiment of the present application, based on the window minimum detection method, the continuous PPG signal is cut into a PPG signal with a length of one cardiac cycle (i.e., a single PPG signal) on the time axis, and then the single PPG signal is decomposed to obtain the Gaussian wave mean through Gaussian multi-peak fitting processing, and the Gaussian wave mean change amplitude is determined, and finally, whether the patient suffers from SAS is determined based on the Gaussian wave mean change amplitude and blood oxygen change amplitude. That is, in the present application, the Gaussian wave mean (μ1) is used to replace the heart rate (HR), and the interference of high-frequency signals can be effectively ignored at this time, making the SAS detection result more reliable, especially suitable for environments with large heart rate changes or signal interference, and providing an efficient and accurate heart rate variability detection technology for medical health monitoring.

[0051] In an embodiment of the present application, the acquired initial continuous PPG signal is processed based on a high-pass filter and a notch filter. At this time, the low-frequency baseline drift and specific frequencies caused by physiological changes, motion artifacts or other non-cardiovascular signals in the initial continuous PPG signal can be removed, and the influence of some high-frequency signals can be effectively ignored, making the detection result more reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0053] Figure 1 A schematic diagram of a flow chart of a method for determining SAS patients based on PPG signals provided in an embodiment of the present application;

[0054] Figure 2 A schematic diagram of a process for determining a trough position provided in an embodiment of the present application;

[0055] Figure 3 A waveform diagram of a single PPG signal provided in an embodiment of the present application;

[0056] Figure 4 A schematic flow chart of another method for determining SAS patients based on PPG signals provided in an embodiment of the present application;

[0057] Figure 5 A schematic diagram of the structure of a device for determining SAS patients based on PPG signals provided in an embodiment of the present application;

[0058] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present invention.

[0060] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0061] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0062] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0063] Specifically, Figure 1 As shown, the method may include:

[0064] Step S101, obtaining a target continuous PPG signal and blood oxygen saturation data of a patient within a set time period, wherein the target continuous PPG signal is a continuous PPG signal corresponding to the pulse data.

[0065] Optionally, the set time can be set according to the actual situation of the patient, and the embodiment of the present application is not limited. For example, the set time can be set to 1 hour, and the continuous PPG signal and blood oxygen saturation data corresponding to the pulse data of the patient within the 1 hour can be obtained based on the PPG sensor.

[0066] In an optional embodiment of the present application, obtaining a target continuous PPG signal of a patient within a set time period includes:

[0067] Obtaining the initial continuous PPG signal corresponding to the patient's pulse data within a set time period;

[0068] Obtaining a cutoff frequency and a high-pass filter, and determining a filter coefficient according to the cutoff frequency and the high-pass filter;

[0069] Based on the filter coefficient, the initial continuous PPG signal is processed to remove the baseline drift interference to obtain a first continuous PPG signal;

[0070] Acquire a notch frequency and a notch filter, and determine a notch filter coefficient according to the notch frequency and the notch filter;

[0071] The first continuous PPG signal is processed to remove specific frequency interference based on the notch filter coefficient to obtain a target continuous PPG signal.

[0072] Optionally, the initial continuous PPG signal acquired based on the PGG sensor may have low-frequency baseline drift and interference of specific frequencies caused by physiological changes, motion artifacts or other non-cardiovascular signals. Since these drifts and interferences may affect the final judgment result, the initial continuous PPG signal acquired in this application will be processed to remove baseline drift interference and specific frequency interference.

[0073] Specifically, the cutoff frequency ω can be obtained C And high-pass filter, in practical applications, the baseline drift frequency of the PPG signal is low, usually between 0.01Hz and 0.5Hz. For PPG signals, the Butterworth filter is commonly used because it has a flat response within the passband. At this time, the Butterworth high-pass filter can be obtained, as shown below:

[0074]

[0075] Where s is the complex frequency, ω C is the cut-off frequency and Q is the quality factor.

[0076] Furthermore, the filter coefficient can be determined according to the obtained cutoff frequency and the Butterworth high-pass filter. Specifically, the filter coefficient can be calculated using the filter design function in Matlab (a programming tool), and then the calculated filter coefficient is applied to the initial continuous PPG signal to obtain the first continuous PPG signal. At this time, the first continuous PPG signal obtained removes the low-frequency component.

[0077] Correspondingly, for interference of a specific frequency in the PPG signal, such as 50Hz power frequency interference of the power system, the notch frequency and the notch filter with the notch frequency set to 50Hz can be obtained:

[0078]

[0079] Where ω0 is the notch frequency and ε is the damping ratio.

[0080] Furthermore, the notch filter coefficient is determined according to the acquired notch frequency and the notch filter. Specifically, the notch filter design function in Matlab can be used to calculate the notch filter coefficient, and then the calculated notch filter coefficient is applied to the first continuous PPG signal to obtain the target continuous PPG signal. At this time, the target continuous PPG signal obtained removes interference of a specific frequency.

[0081] It can be understood that in actual applications, for the initial continuous PPG signal obtained, there is no order of precedence between the high-pass filter and the notch filter used to remove the low-frequency baseline drift and the interference of the specific frequency. The low-frequency baseline drift can be removed based on the high-pass filter first, and then the interference of the specific frequency can be removed by the notch filter. Alternatively, the interference of the specific frequency can be removed by the notch filter first, and then the low-frequency baseline drift can be removed by the high-pass filter. The embodiment of the present application does not limit the order of precedence of the high-pass filter and the notch filter used.

[0082] Step S102, determining the trough position of the target continuous PPG signal based on the window sliding minimum detection method, and cutting the target continuous PPG signal into at least two single PPG signals according to the trough position.

[0083] Optionally, after obtaining the patient's target continuous PPG signal within a set time, the trough position of the target continuous PPG signal can be determined based on the window sliding minimum detection method, and then the target continuous PPG signal can be cut into multiple single PPG signals based on the determined trough position. The trough position is the end point of the previous single PPG signal and the starting point of the next single PPG signal. The target continuous PPG signal is like a rope. At this time, the position of the whole centimeter can be marked with a ruler according to the trough position, and then the target continuous PPG signal can be cut at the marked point with scissors to obtain multiple single PPG signals.

[0084] In an optional embodiment of the present application, determining the trough position of the target continuous PPG signal based on the window sliding minimum detection method includes:

[0085] An initial window is obtained, where the number of sampling points included in the initial window is determined according to the sampling rate of the target continuous PPG signal and the heart rate reference value;

[0086] Based on each sliding of the initial window on the target continuous PPG signal by a set distance, at least one first window is obtained, and according to the data point value in each first window, at least one second window is determined from the at least one first window;

[0087] According to the values ​​of the data points in each second window, respectively determine the minimum data points corresponding to each second window, and determine the rising and falling trends between each minimum data point and adjacent data points;

[0088] The position of the minimum data point whose rising and falling trend meets the preset requirements is taken as the trough position of the target continuous PPG signal.

[0089] Optionally, the process for determining the trough position of the target continuous PPG signal based on the window sliding minimum method can be as follows: Figure 2 As shown, it can specifically include obtaining a target continuous PPG signal (ie Figure 2 The preprocessed PPG signal in the image is used as the input data and the initial window size is used. Then, the local minimum is found in the initial window and the trough is confirmed. At the same time, it is determined whether the end point of the target continuous PPG signal is reached (that is, the data traversal in the figure is ended?). If the end point of the target continuous PPG signal is reached (that is, the Y branch in the figure), all troughs can be output at this time. If the end point of the target continuous PPG signal is not reached (that is, the N branch in the figure), the sliding distance and window length of the sliding window are adjusted according to the distance between adjacent troughs (that is, the sliding window and adjustment window length in the figure). A new trough is found in the updated window based on the method of finding the local minimum until the end point is reached and all troughs are output.

[0090] Among them, the selection of the initial window size is crucial to the accuracy of trough detection. If the window is too small, the complete waveform may not be captured, while if the window is too large, multiple waveforms may be merged together. Therefore, when determining the number of sampling points contained in the initial window, it can be determined based on the sampling rate of the target continuous PPG signal and the heart rate reference value. For example, the normal human heart rate is between 60-120 beats / minute. When the PPG signal sampling rate is 500, it is possible to choose to use an initial heart rate of 90 beats / minute, and then set the number of sampling points contained in the initial window length to 334 sampling points.

[0091] Furthermore, based on the set distance that the initial window slides on the target continuous PPG signal each time, such as sliding a 0.67s window on the target continuous PPG signal each time, at least one first window is obtained, and then at least one second window is determined from the at least one first window according to the data point value in each first window. The second window can be determined by comparing the value of each data point in each first window with the value of its adjacent data points. If the value of a data point in the first window is less than the value of its adjacent data points before and after, then the first window is the second window.

[0092] Correspondingly, according to the values ​​of the data points in each second window, the minimum data points corresponding to each second window are determined respectively (that is, the value of the data point is smaller than the values ​​of the adjacent data points before and after it), and the rising and falling trends between each minimum data point and the adjacent data points are determined. If the rising and falling trends of the minimum data points meet the preset requirements, the position of the minimum data point is the trough position of the target continuous PPG signal.

[0093] In an optional embodiment of the present application, if the number of extremely small data points whose rising and falling trends meet the preset requirements reaches a set number, and the sliding distance does not reach the end point of the target continuous PPG signal, the method further includes:

[0094] The window length of the initial window and the size of the set distance are adjusted respectively to obtain an adjustment window and an adjustment distance, and the trough position of the target continuous PPG signal is further determined based on the adjustment window and the adjustment distance.

[0095] Among them, the specific value of the set number can be set according to actual needs, and this application does not limit this. Optionally, when the minimum data points whose rising and falling trends meet the preset requirements reach a set number (that is, the determined trough positions reach a set number), and the sliding distance does not reach the end point of the target continuous PPG signal, the window length of the initial window and the size of each sliding distance (that is, the set distance) can be adjusted at this time, and then the trough position of the target continuous PPG signal is determined based on the adjusted window and the adjusted set distance based on the method above until the end point of the target continuous PPG signal is reached. For example, when more than three trough positions are detected, the set distance is adjusted to the average length of the previous three trough distances, and the window length is adjusted to 60% of the window movement distance. Furthermore, after sliding to the end point of the target continuous PPG signal based on the window, the detected trough position is recorded for subsequent analysis.

[0096] Step S103, determining at least one risk duration corresponding to the patient from the set durations according to the blood oxygen saturation data, and the blood oxygen variation amplitude corresponding to each risk duration.

[0097] Among them, the risk duration may refer to the duration during which the patient may have SAS symptoms. Optionally, after obtaining the patient's blood oxygen saturation data within the set duration, the risk duration within the set duration can be determined based on the specific value of the blood oxygen saturation, and then the blood oxygen change amplitude corresponding to each risk duration is determined based on the specific value of the blood oxygen saturation within each risk duration, and the blood oxygen change amplitude is the difference between the highest blood oxygen saturation value and the lowest blood oxygen saturation value within each risk duration, which can be expressed by ΔSpO2.

[0098] In an optional embodiment of the present application, determining at least one risk duration corresponding to the patient from the set duration according to the blood oxygen saturation data includes:

[0099] Determine at least one time duration during which the blood oxygen value in the blood oxygen saturation data corresponding to the set time duration is lower than the preset value;

[0100] At least one duration during which the blood oxygen value is lower than a preset value is used as at least one risk duration corresponding to the patient.

[0101] Among them, the risk duration can specifically refer to the duration when the blood oxygen saturation value drops by more than 4% from a stable state. For example, when the blood oxygen saturation standard is 90 or above, the duration when the blood oxygen saturation data is lower than 86 is the risk duration. Optionally, for the blood oxygen saturation data corresponding to the set duration obtained, at least one duration when the blood oxygen value is lower than a preset value can be determined based on the specific value of the blood oxygen saturation and its corresponding time information, and then at least one duration when the blood oxygen value is lower than the preset value is used as at least one risk duration corresponding to the patient. For example, the duration when the blood oxygen saturation data is lower than 86 is used as the risk duration.

[0102] Step S104, using a Gaussian function to perform multi-peak fitting processing on each single PPG signal, to obtain the Gaussian wave mean change amplitude corresponding to each risk duration.

[0103] Optionally, the waveform of each individual PPG signal can be as follows: Figure 3 As shown, each single PPG signal is a complete pulse waveform of a cardiac cycle, which may include the main wave ( Figure 3 A wave in the Figure 3 B wave) and dicrotic wave ( Figure 3 Furthermore, a Gaussian function can be used to perform multi-peak fitting processing on each single PPG signal to obtain the Gaussian wave mean change amplitude corresponding to each risk duration.

[0104] In an optional embodiment of the present application, a Gaussian function is used to perform multi-peak fitting processing on each single PPG signal to obtain the Gaussian wave mean change amplitude corresponding to each risk duration, including:

[0105] Determining at least two target single PPG signals corresponding to each risk duration from at least two single PPG signals according to time information of each single PPG signal;

[0106] For each risk duration, a Gaussian function is used to perform multi-peak fitting processing on each target single PPG signal corresponding to the risk duration to obtain the Gaussian wave mean change amplitude corresponding to each risk duration.

[0107] Optionally, each risk duration and a single PPG signal will have their own corresponding time information. At this time, for a risk duration, a single PPG signal whose time information is consistent with the time information of the risk duration can be determined based on the time information corresponding to the risk duration and each single PPG signal, and the corresponding single PPG signal is used as the target single PPG signal corresponding to the risk duration. Furthermore, a Gaussian function can be used to perform multi-peak fitting processing on each target single PPG signal corresponding to the risk duration to obtain the Gaussian wave mean change amplitude corresponding to the risk duration.

[0108] In an optional embodiment of the present application, a Gaussian function is used to perform multi-peak fitting processing on each target single PPG signal corresponding to the risk duration to obtain the Gaussian wave mean change amplitude corresponding to each risk duration, including:

[0109] The Gaussian function is used to perform multi-peak fitting processing on the single PPG signal of each target corresponding to the risk duration to obtain the Gaussian wave mean of the single PPG signal of each target;

[0110] According to the Gaussian wave mean of each target single PPG signal, the Gaussian wave mean change amplitude corresponding to each risk duration is obtained.

[0111] Optionally, for each risk duration, a multi-peak fitting process can be performed on each target single PPG signal corresponding to the risk duration based on a Gaussian function. At this time, each target single PPG signal will have its own corresponding Gaussian wave mean. Further, the maximum and minimum values ​​of the Gaussian wave mean of the target single PPG signal in the risk duration can be determined, and then the difference between the maximum and minimum values ​​is used as the Gaussian wave mean change amplitude corresponding to the risk duration, and is represented by Δμ1.

[0112] In an optional embodiment of the present application, a Gaussian function is used to perform multi-peak fitting processing on each target single PPG signal corresponding to the risk duration to obtain the Gaussian wave mean of each target single PPG signal, including:

[0113] For each target single PPG signal, a Gaussian function and an initial parameter value of the function are obtained, and the target single PPG signal is processed based on the Gaussian function to obtain a function value corresponding to each data point in the target single PPG signal;

[0114] Constructing a corresponding target function based on the numerical value of each data point in the target single PPG signal and the function value corresponding to each data point in the target single PPG signal;

[0115] Substitute the initial parameter value of the function into the objective function and perform iterative calculation until the convergence condition is reached to obtain the Gaussian wave mean of the target single PPG signal.

[0116] Optionally, each Gaussian function can be expressed as:

[0117]

[0118] Where a is the amplitude, μ is the Gaussian mean, and σ is the standard deviation.

[0119] Furthermore, since each target single PPG signal usually requires three Gaussian functions for fitting processing, the Gaussian model of each cardiac cycle PPG(x) of each target single PPG signal can be expressed as:

[0120]

[0121] It can be seen that each Gaussian function requires three parameters, a, μ and σ. For a target single PPG signal, because three Gaussian functions are needed to fit a cardiac cycle, nine parameters need to be estimated, namely a1, μ1, σ1, a2, μ2, σ2, a3, μ3, σ3.

[0122] Furthermore, each data point in the target single PPG signal can be substituted into the Gaussian model of each cardiac cycle PPG(x) to obtain the corresponding function value y(x i ), and then the least squares method is used to estimate the values ​​of these 9 parameters.

[0123] Optionally, the initial function parameter values ​​can be obtained, that is, the initial values ​​of a1, μ1, σ1, a2, μ2, σ2, a3, μ3, and σ3. At this time, the initial function parameter values ​​can be set to:

[0124] [a1,μ1,σ1; a2,μ2,σ2; a3,μ3,σ3]=[1,70,0.2;0.8,100,0.5;0.5,150,1.0]

[0125] Furthermore, a corresponding objective function may be constructed based on the numerical value of each data point in the target single PPG signal and the function value corresponding to each data point in the target single PPG signal, that is, the residual sum of squares between each data point in the target single PPG signal and the Gaussian model:

[0126]

[0127] Among them, PPG(x i ) is the target single PPG signal x i The value of the data point at i ) Gaussian function at x i The numerical value at .

[0128] Then, the initial parameter value of the function can be substituted into the objective function for iterative calculation until the convergence condition is reached to obtain the Gaussian wave mean of the target single PPG signal. Among them, the specific tools for iterative calculation and the convergence condition can be selected and set according to actual needs, and this application does not limit this. For example, the Gauss-Newton method in Matlab can be used to iteratively update the parameters until the set convergence condition is met or the maximum number of iterations is reached. At this time, the final values ​​of 9 parameters (i.e. [a1, μ1, σ1; a2, μ2, σ2; a3, μ3, σ3]) will be obtained. In this application, μ1 is extracted as the Gaussian wave mean of the target single PPG signal.

[0129] Step S105, determining the SAS result of the patient according to the blood oxygen change amplitude corresponding to each risk duration, the Gaussian wave mean change amplitude corresponding to each risk duration, and the judgment criteria.

[0130] Optionally, after obtaining the blood oxygen change amplitude corresponding to each risk duration and the Gaussian wave mean change amplitude corresponding to each risk duration, a pre-set judgment standard can be obtained, and then the blood oxygen change amplitude and the Gaussian wave mean change amplitude corresponding to each risk duration are compared with the judgment standard to obtain the patient's final SAS result.

[0131] In an optional embodiment of the present application, the judgment criteria include a product standard value and a hypopnea frequency standard, and the SAS result of the patient is determined according to the blood oxygen change amplitude corresponding to each risk duration, the Gaussian wave mean change amplitude corresponding to each risk duration, and the judgment criteria, including:

[0132] For each risk duration, the blood oxygen change amplitude corresponding to the risk duration and the corresponding Gaussian wave mean change amplitude are multiplied to obtain a first value corresponding to the risk duration;

[0133] Compare the first value corresponding to each risk duration with the product standard respectively, and determine the number of target risk durations from all risk durations;

[0134] The number of target risk times was compared with the hypopnea criteria to determine the patient's SAS outcome.

[0135] Optionally, the judgment criteria may include a product standard value (which may be expressed as ΔSpO2*Δμ1) and a hypopnea frequency standard within a set time (which may be expressed as AHI), and the specific values ​​of the product standard value and the hypopnea frequency standard may be set according to the actual situation of the patient, and are not limited in the embodiments of the present application. For example, since ΔSpO2 and Δμ1 are positively correlated, when sleep apnea syndrome (SAS) occurs, ΔSpO2 and Δμ1 will increase at the same time, and the ΔSpO2*Δμ1 value will also increase significantly. Therefore, the judgment criteria can be set to a product standard value of >200, and a hypopnea frequency standard of ≥5 times / hour, which is a SAS result.

[0136] Furthermore, the blood oxygen change amplitude (ΔSpO2) corresponding to each risk duration and the corresponding Gaussian wave mean change amplitude (Δμ1) can be multiplied to obtain the first value corresponding to each risk duration (i.e., the product value ΔSpO2*Δμ1), and then the first value corresponding to each risk duration is compared with the product standard, and the risk duration whose first value is greater than the product standard is determined as the target risk duration. Accordingly, the number of target risk durations can be determined and compared with the low ventilation frequency standard. If the number of target risk durations reaches the low ventilation frequency standard, it is determined that the patient suffers from SAS. If the number of target risk durations does not reach the low ventilation frequency standard, it is determined that the patient does not suffer from SAS. For example, when the first value ΔSpO2*Δμ1 corresponding to the risk duration is >200, it is considered that a low ventilation has occurred, and the AHI value is increased by 1 at this time. When AHI ≥5 times / hour, it can be considered that the patient suffers from SAS.

[0137] In the embodiment of the present application, the signal preprocessing and window minimum detection method are combined to cut the continuous PPG signal into a PPG signal with a length of one cardiac cycle (i.e., a single PPG signal) on the time axis, and then the single PPG signal is decomposed to obtain the Gaussian wave mean through Gaussian multi-peak fitting processing, and the Gaussian wave mean change amplitude is determined, and finally, whether the patient suffers from SAS is determined based on the Gaussian wave mean change amplitude and blood oxygen change amplitude. That is, in the present application, the Gaussian wave mean (μ1) is used to replace the heart rate (HR), which can effectively ignore the interference of high-frequency signals, making the SAS detection result more reliable, especially suitable for environments with large heart rate changes or signal interference, and providing an efficient and accurate heart rate variability detection technology for medical health monitoring.

[0138] In order to better understand the method provided in the embodiments of the present application, the following Figure 4 The method flow in this application is described again.

[0139] Step 401, PPG signal: obtaining the patient's initial continuous PPG signal and blood oxygen saturation data within a set time period;

[0140] Step 402, preprocessing: removing baseline drift interference from the initial continuous PPG signal based on a high-pass filter to obtain a first continuous PPG signal, and then removing specific frequency interference from the first continuous PPG signal based on a notch filter to obtain a target continuous PPG signal;

[0141] Step 403, trough detection, PPG segmentation: determining the trough position of the target continuous PPG signal based on the window sliding minimum detection method, and cutting the target continuous PPG signal into at least two single PPG signals according to the trough position;

[0142] Step 404, Gaussian multi-peak fitting: using a Gaussian function to perform multi-peak fitting processing on each target single PPG signal to obtain the Gaussian wave mean of each target single PPG signal;

[0143] Step 405, feature extraction: calculating the Gaussian wave mean change amplitude (Δμ1) and blood oxygen change amplitude (ΔSpO2) of each target single PPG signal;

[0144] Step 406, statistical analysis: Calculate ΔSpO2*Δμ1, when ΔSpO2*Δμ1>200, the AHI value is increased by 1, and when AHI≥5 times / hour, it is confirmed that the patient suffers from SAS.

[0145] The embodiment of the present application provides a device for determining SAS patients based on PPG signals, such as Figure 5 As shown, the device may include: a data acquisition module 501, a signal cutting module 502, a data processing module 503, a data fitting module 504 and a result determination module 505, wherein:

[0146] A data acquisition module is used to obtain the patient's target continuous PPG signal and blood oxygen saturation data within a set time period, where the target continuous PPG signal is a continuous PPG signal corresponding to the pulse data;

[0147] A signal cutting module, used to determine the trough position of the target continuous PPG signal based on the window sliding minimum detection method, and cut the target continuous PPG signal into at least two single PPG signals according to the trough position;

[0148] A data processing module, used to determine at least one risk duration corresponding to the patient from the set duration according to the blood oxygen saturation data, and a blood oxygen variation amplitude corresponding to each risk duration;

[0149] The data fitting module is used to perform multi-peak fitting processing on each single PPG signal using a Gaussian function to obtain the Gaussian wave mean change amplitude corresponding to each risk duration;

[0150] The result determination module is used to determine the patient's SAS result according to the blood oxygen change amplitude corresponding to each risk duration, the Gaussian wave mean change amplitude corresponding to each risk duration, and the judgment criteria.

[0151] Optionally, when acquiring the patient's target continuous PPG signal within a set time period, the data acquisition module is specifically used to:

[0152] Obtaining the initial continuous PPG signal corresponding to the patient's pulse data within a set time period;

[0153] Obtaining a cutoff frequency and a high-pass filter, and determining a filter coefficient according to the cutoff frequency and the high-pass filter;

[0154] Based on the filter coefficient, the initial continuous PPG signal is processed to remove the baseline drift interference to obtain a first continuous PPG signal;

[0155] Acquire a notch frequency and a notch filter, and determine a notch filter coefficient according to the notch frequency and the notch filter;

[0156] The first continuous PPG signal is processed to remove specific frequency interference based on the notch filter coefficient to obtain a target continuous PPG signal.

[0157] Optionally, when the signal cutting module determines the trough position of the target continuous PPG signal based on the window sliding minimum detection method, it is specifically used to:

[0158] An initial window is obtained, where the number of sampling points included in the initial window is determined according to the sampling rate of the target continuous PPG signal and the heart rate reference value;

[0159] Based on each sliding of the initial window on the target continuous PPG signal by a set distance, at least one first window is obtained, and according to the data point value in each first window, at least one second window is determined from the at least one first window;

[0160] According to the values ​​of the data points in each second window, respectively determine the minimum data points corresponding to each second window, and determine the rising and falling trends between each minimum data point and adjacent data points;

[0161] The position of the minimum data point whose rising and falling trend meets the preset requirements is taken as the trough position of the target continuous PPG signal.

[0162] Optionally, if the minimum data points whose rising and falling trends meet the preset requirements reach a set number, and the sliding distance does not reach the end point of the target continuous PPG signal, the signal cutting module is further used to:

[0163] The window length of the initial window and the size of the set distance are adjusted respectively to obtain an adjustment window and an adjustment distance, and the trough position of the target continuous PPG signal is further determined based on the adjustment window and the adjustment distance.

[0164] Optionally, when the data processing module determines at least one risk duration corresponding to the patient from the set duration according to the blood oxygen saturation data, it is specifically used to:

[0165] Determine at least one time duration during which the blood oxygen value in the blood oxygen saturation data corresponding to the set time duration is lower than the preset value;

[0166] At least one duration during which the blood oxygen value is lower than a preset value is used as at least one risk duration corresponding to the patient.

[0167] Optionally, when the data fitting module uses a Gaussian function to perform multi-peak fitting processing on each single PPG signal to obtain the Gaussian wave mean change amplitude corresponding to each risk duration, it is specifically used to:

[0168] Determining at least two target single PPG signals corresponding to each risk duration from at least two single PPG signals according to time information of each single PPG signal;

[0169] For each risk duration, a Gaussian function is used to perform multi-peak fitting processing on each target single PPG signal corresponding to the risk duration to obtain the Gaussian wave mean change amplitude corresponding to each risk duration.

[0170] Optionally, when the data fitting module uses a Gaussian function to perform multi-peak fitting processing on each target single PPG signal corresponding to the risk duration to obtain the Gaussian wave mean change amplitude corresponding to each risk duration, it is specifically used to:

[0171] The Gaussian function is used to perform multi-peak fitting processing on the single PPG signal of each target corresponding to the risk duration to obtain the Gaussian wave mean of the single PPG signal of each target;

[0172] According to the Gaussian wave mean of each target single PPG signal, the Gaussian wave mean change amplitude corresponding to each risk duration is obtained.

[0173] Optionally, when the data fitting module uses a Gaussian function to perform multi-peak fitting processing on each target single PPG signal corresponding to the risk duration to obtain the Gaussian wave mean of each target single PPG signal, it is specifically used to:

[0174] For each target single PPG signal, a Gaussian function and an initial parameter value of the function are obtained, and the target single PPG signal is processed based on the Gaussian function to obtain a function value corresponding to each data point in the target single PPG signal;

[0175] Constructing a corresponding target function based on the numerical value of each data point in the target single PPG signal and the function value corresponding to each data point in the target single PPG signal;

[0176] Substitute the initial parameter value of the function into the objective function and perform iterative calculation until the convergence condition is reached to obtain the Gaussian wave mean of the target single PPG signal.

[0177] Optionally, when the judgment criteria include the product standard value and the hypopnea frequency standard, the result determination module determines the SAS result of the patient according to the blood oxygen change amplitude corresponding to each risk duration, the Gaussian wave mean change amplitude corresponding to each risk duration, and the judgment criteria, and is specifically used to:

[0178] For each risk duration, the blood oxygen change amplitude corresponding to the risk duration and the corresponding Gaussian wave mean change amplitude are multiplied to obtain a first value corresponding to the risk duration;

[0179] Compare the first value corresponding to each risk duration with the product standard respectively, and determine the number of target risk durations from all risk durations;

[0180] The number of target risk times was compared with the hypopnea criteria to determine the patient's SAS outcome.

[0181] The device for determining SAS patients based on PPG signals of this embodiment can execute the method for determining SAS patients based on PPG signals shown in the embodiment of the present application. The implementation principle is similar and will not be repeated here.

[0182] An embodiment of the present application provides an electronic device, and the electronic device in the embodiment of the present application includes: a processor; and a memory, the memory is configured to store machine-readable instructions, and when the instructions are executed by the processor, the processor executes a method for determining SAS patients based on PPG signals.

[0183] The present application embodiment provides an electronic device, such as Figure 6 As shown, Figure 6 The electronic device shown includes: a processor 2001 and a memory 2003. The processor 2001 and the memory 2003 are connected, such as through a bus 2002. Optionally, the electronic device 2000 may also include a transceiver 2004. It should be noted that in actual applications, the transceiver 2004 is not limited to one, and the structure of the electronic device 2000 does not constitute a limitation on the embodiments of the present application.

[0184] Processor 2001 may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 2001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0185] The bus 2002 may include a path to transmit information between the above components. The bus 2002 may be a PCI bus or an EISA bus, etc. The bus 2002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0186] The memory 2003 may be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an EEPROM, a CD-ROM or other optical disk storage, an optical disk storage (including a compressed optical disk, a laser disk, an optical disk, a digital versatile disk, a Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0187] The memory 2003 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 2001. The processor 2001 is used to execute the application code stored in the memory 2003 to implement Figure 5 The illustrated embodiment provides an action for determining a SAS patient device based on a PPG signal.

[0188] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0189] The above is only part of the embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A method for determining SAS patients based on PPG signals, characterized in that: include: Obtaining a target continuous PPG signal and blood oxygen saturation data of the patient within a set time period, wherein the target continuous PPG signal is a continuous PPG signal corresponding to the pulse data; Determine a trough position of the target continuous PPG signal based on a window sliding minimum detection method, and cut the target continuous PPG signal into at least two single PPG signals according to the trough position; Determining at least one risk duration corresponding to the patient from the set durations according to the blood oxygen saturation data, and a blood oxygen variation amplitude corresponding to each risk duration; A Gaussian function is used to perform multi-peak fitting processing on each of the single PPG signals to obtain a Gaussian wave mean change amplitude corresponding to each risk duration; The SAS result of the patient is determined according to the blood oxygen change amplitude corresponding to each risk duration, the Gaussian wave mean change amplitude corresponding to each risk duration, and the judgment criteria.

2. The method according to claim 1, characterized in that The step of obtaining a target continuous PPG signal of a patient within a set time period includes: Obtaining an initial continuous PPG signal corresponding to the patient's pulse data within a set time period; Obtaining a cutoff frequency and a high-pass filter, and determining a filter coefficient according to the cutoff frequency and the high-pass filter; Performing a baseline drift interference removal process on the initial continuous PPG signal based on the filter coefficient to obtain a first continuous PPG signal; Acquire a notch frequency and a notch filter, and determine a notch filter coefficient according to the notch frequency and the notch filter; Based on the notch filter coefficient, the first continuous PPG signal is processed to remove specific frequency interference to obtain the target continuous PPG signal.

3. The method according to claim 1, characterized in that The method of determining the trough position of the target continuous PPG signal based on the window sliding minimum detection method includes: Acquire an initial window, where the number of sampling points included in the initial window is determined according to the sampling rate of the target continuous PPG signal and the heart rate reference value; Based on each sliding of the initial window on the target continuous PPG signal by a set distance, at least one first window is obtained, and according to the data point value in each first window, at least one second window is determined from the at least one first window; According to the values ​​of the data points in each of the second windows, respectively determine the minimum data points corresponding to each of the second windows, and determine the rising and falling trends between each of the minimum data points and adjacent data points; The position of the minimum data point whose rising and falling trend meets the preset requirements is taken as the trough position of the target continuous PPG signal.

4. The method according to claim 3, characterized in that If the number of extremely small data points whose rising and falling trends meet the preset requirements reaches a set number, and the sliding distance does not reach the end point of the target continuous PPG signal, the method further includes: The window length of the initial window and the size of the set distance are adjusted respectively to obtain an adjustment window and an adjustment distance, and the trough position of the target continuous PPG signal is continued to be determined based on the adjustment window and the adjustment distance.

5. The method according to claim 1, characterized in that The determining at least one risk duration corresponding to the patient from the set duration according to the blood oxygen saturation data includes: Determine at least one time duration during which the blood oxygen value in the blood oxygen saturation data corresponding to the set time duration is lower than a preset value; At least one duration during which the blood oxygen value is lower than a preset value is used as at least one risk duration corresponding to the patient.

6. The method according to claim 1, characterized in that The Gaussian function is used to perform multi-peak fitting processing on each of the single PPG signals to obtain the Gaussian wave mean value change amplitude corresponding to each risk duration, including: Determining at least two target single PPG signals corresponding to each risk duration from the at least two single PPG signals according to the time information of each single PPG signal; For each of the risk durations, a Gaussian function is used to perform multi-peak fitting processing on each of the target single PPG signals corresponding to the risk duration to obtain the Gaussian wave mean change amplitude corresponding to each of the risk durations.

7. The method according to claim 6, characterized in that The Gaussian function is used to perform multi-peak fitting processing on each of the target single PPG signals corresponding to the risk duration to obtain the Gaussian wave mean value change amplitude corresponding to each of the risk durations, including: A Gaussian function is used to perform multi-peak fitting processing on each of the target single PPG signals corresponding to the risk duration to obtain a Gaussian wave mean of each of the target single PPG signals; According to the Gaussian wave mean of each target single PPG signal, the Gaussian wave mean change amplitude corresponding to each risk duration is obtained.

8. The method according to claim 7, characterized in that The using of a Gaussian function to perform multi-peak fitting processing on each of the target single PPG signals corresponding to the risk duration to obtain a Gaussian wave mean of each of the target single PPG signals includes: For each of the target single PPG signals, a Gaussian function and an initial parameter value of the function are obtained, and the target single PPG signal is processed based on the Gaussian function to obtain a function value corresponding to each data point in the target single PPG signal; constructing a corresponding target function based on the numerical value of each data point in the target single PPG signal and the function value corresponding to each data point in the target single PPG signal; The initial parameter value of the function is substituted into the objective function for iterative calculation until the convergence condition is reached to obtain the Gaussian wave mean of the target single PPG signal.

9. The method according to claim 1, characterized in that: The judgment standard includes a product standard value and a hypopnea frequency standard, and the SAS result of the patient is determined according to the blood oxygen change amplitude corresponding to each risk duration, the Gaussian wave mean change amplitude corresponding to each risk duration, and the judgment standard, including: For each risk duration, multiplying the blood oxygen change amplitude corresponding to the risk duration and the corresponding Gaussian wave mean change amplitude to obtain a first value corresponding to the risk duration; Compare the first numerical value corresponding to each of the risk durations with the product standard respectively, and determine the number of target risk durations from all the risk durations; The number of target risk durations is compared with the hypopnea frequency criteria to determine the SAS result of the patient.

10. A device for determining SAS patients based on PPG signals, characterized in that: include: A data acquisition module, used to acquire a patient's target continuous PPG signal and blood oxygen saturation data within a set time period, wherein the target continuous PPG signal is a continuous PPG signal corresponding to the pulse data; a signal cutting module, configured to determine a trough position of the target continuous PPG signal based on a window sliding minimum detection method, and cut the target continuous PPG signal into at least two single PPG signals according to the trough position; A data processing module, configured to determine at least one risk duration corresponding to the patient and a blood oxygen variation amplitude corresponding to each risk duration from the set duration according to the blood oxygen saturation data; A data fitting module, used to perform multi-peak fitting processing on each of the single PPG signals using a Gaussian function to obtain a Gaussian wave mean change amplitude corresponding to each risk duration; The result determination module is used to determine the SAS result of the patient according to the blood oxygen change amplitude corresponding to each risk duration, the Gaussian wave mean change amplitude corresponding to each risk duration, and the judgment criteria.

Images