Apnea detection method, device, electronic device and storage medium

Abstract

The embodiments of the present invention provide a method, device, electronic device, and storage medium for detecting apnea, which relate to the field of respiratory detection. The method extracts the time domain features of the collected cardiac perturbation signal, extracts the frequency domain features of the cardiac perturbation signal when the time domain features of the cardiac perturbation signal meet the first apnea condition, and determines the presence of an apnea event when the frequency domain features meet the second apnea condition. In this way, the time domain features and frequency domain features of the cardiac perturbation signal are combined, and the presence of an apnea event is determined when apnea is determined in both the time domain and the frequency domain, effectively reducing the possibility of misjudgment and improving the accuracy of apnea event detection. The entire detection process does not require manual judgment, and the acquisition of the cardiac perturbation signal is relatively convenient, which improves the operational simplicity of apnea event detection.

Description

Technical Field

[0001] The present invention relates to the field of respiratory detection, and in particular to a method, device, electronic device and storage medium for detecting apnea. Background Art

[0002] Apnea refers to the cessation of spontaneous breathing, often temporary or self-limiting. Because apnea typically occurs during sleep and is difficult to detect, long-term undetected and untreated apnea can lead to a range of health problems. Therefore, detecting apnea is crucial to human health, and apnea events are also a key indicator in sleep apnea monitoring.

[0003] Polysomnography is often used clinically to monitor sleep status, which requires the cooperation of professional doctors for judgment. That is, the monitoring and judgment of sleep apnea requires special wearable equipment to record and manual interpretation. It is not only complicated to operate, but also affects the user's sleep. Summary of the Invention

[0004] In view of this, an object of the present invention is to provide a method, device, electronic device and storage medium for detecting apnea, so as to solve the problems of low accuracy and complex operation in detecting apnea events in the prior art.

[0005] In order to achieve the above objectives, the technical solutions adopted in the embodiments of the present invention are as follows:

[0006] In a first aspect, the present invention provides a method for detecting apnea, the method comprising:

[0007] Extracting the time domain features of the collected cardiac ballistic signals;

[0008] extracting frequency domain features of the ballistocardi signal when the time domain features of the ballistocardi signal meet the first apnea condition;

[0009] When the frequency domain feature meets the second apnea condition, it is determined that an apnea event exists.

[0010] In an optional embodiment, the time domain feature includes the amplitude of each peak in the ballistocardi signal. When the time domain feature of the ballistocardi signal meets the first apnea condition, before the step of extracting the frequency domain feature of the ballistocardi signal, the method further includes:

[0011] Determining a plurality of continuous target peaks based on the time domain characteristics of the ballistocardial signal; wherein, among the plurality of continuous target peaks, a ratio between the amplitude of a peak preceding a first target peak and the amplitude of the first target peak is greater than a preset ratio, a ratio between the amplitude of a peak following a last target peak and the amplitude of the last target peak is greater than the preset ratio, and, among the amplitudes of any two adjacent target peaks, a ratio between the larger amplitude and the smaller amplitude is less than or equal to the preset ratio;

[0012] If the duration of the multiple consecutive target peaks is greater than or equal to the preset time, it is determined that the time domain characteristics of the ballistocardiographic signal meet the first apnea condition.

[0013] In an optional embodiment, determining a plurality of continuous target peaks according to the time domain characteristics of the ballistocardi signal includes:

[0014] Perform peak searching on the ballistocardiographic signal to determine a first wave peak and a second wave peak that are adjacent to each other, wherein the time corresponding to the first wave peak is less than the time corresponding to the second wave peak;

[0015] If the ratio between the amplitude of the first peak and the amplitude of the second peak is greater than the preset ratio, searching for at least one consecutive third peak after the moment corresponding to the second peak until the ratio between the amplitude of the next peak after the third peak and the amplitude of the third peak is greater than the preset ratio; wherein, for each third peak and the amplitude of the adjacent previous peak, the ratio between the larger amplitude and the smaller amplitude is less than or equal to the preset ratio;

[0016] The second peak and all third peaks are determined as target peaks to obtain multiple continuous target peaks.

[0017] In an optional embodiment, the duration is the difference between the moment of the first target peak and the moment of the last target peak.

[0018] In an optional embodiment, extracting the frequency domain features of the ballistocardiographic signal includes:

[0019] Determining a time period in which the time domain characteristics of the ballistocardiographic signal meet a first apnea condition;

[0020] The frequency spectrum of the ballistocardiographic signal in the time period is calculated; the frequency domain feature includes the amplitude of each peak in the frequency spectrum.

[0021] In an optional embodiment, the spectrum includes a spectrum of a heartbeat frequency band and a spectrum of a respiratory frequency band. Before the step of determining the presence of an apnea event when the frequency domain feature meets the second apnea condition, the method further includes:

[0022] Calculating a first average value of the amplitudes of all the peaks corresponding to the heartbeat frequency band, and a second average value of the amplitudes of all the peaks corresponding to the respiratory frequency band;

[0023] If there is at least one peak in the heartbeat frequency band whose amplitude is greater than a first preset multiple of the first average value, and there is no peak in the respiratory frequency band whose amplitude is greater than a second preset multiple of the second average value, it is determined that the frequency domain feature meets the second apnea condition.

[0024] In an optional embodiment, calculating the frequency spectrum of the ballistocardiogram signal within the time period includes:

[0025] Performing Fourier transform on the ballistocardi signal within the time period to obtain a frequency spectrum of the ballistocardi signal within the time period.

[0026] In a second aspect, the present invention provides an apnea detection device, comprising:

[0027] A time domain feature extraction module is used to extract the time domain features of the collected cardiac ballistometry signal;

[0028] a frequency domain feature extraction module, configured to extract the frequency domain feature of the ballistocardi signal when the time domain feature of the ballistocardi signal meets the first apnea condition;

[0029] The breathing detection module is used to determine the presence of an apnea event when the frequency domain feature meets the second apnea condition.

[0030] In a third aspect, the present invention provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the apnea detection method as described in any one of the aforementioned embodiments.

[0031] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the apnea detection method as described in any one of the aforementioned embodiments.

[0032] The apnea detection method, device, electronic device, and storage medium provided by embodiments of the present invention extract the time domain features of a collected cardiac ballistocardi signal. When the time domain features of the cardiac ballistocardi signal meet a first apnea condition, the frequency domain features of the cardiac ballistocardi signal are extracted. When the frequency domain features meet a second apnea condition, an apnea event is determined. This combines the time domain and frequency domain features of the cardiac ballistocardi signal, allowing the presence of an apnea event to be determined when apnea is determined in both the time and frequency domains. This effectively reduces the possibility of misjudgment and improves the accuracy of apnea event detection. The entire detection process does not require manual judgment, and the acquisition of cardiac ballistocardi signals is relatively convenient, improving the operational simplicity of apnea event detection.

[0033] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0035] Figure 1 A schematic diagram of a flow chart of an apnea detection method provided by an embodiment of the present invention is shown;

[0036] Figure 2 A schematic diagram showing a comparison between a respiratory waveform of a normal respiratory rhythm and a respiratory waveform of apnea;

[0037] Figure 3 Another flowchart of the apnea detection method provided by an embodiment of the present invention is shown;

[0038] Figure 4 Another flow chart of the apnea detection method provided by an embodiment of the present invention is shown;

[0039] Figure 5 Another schematic flow chart of the apnea detection method provided by an embodiment of the present invention is shown;

[0040] Figure 6 Another schematic flow chart of the apnea detection method provided by an embodiment of the present invention is shown;

[0041] Figure 7 A functional module diagram of an apnea detection device provided by an embodiment of the present invention is shown;

[0042] Figure 8 Another functional module diagram of the apnea detection device provided by an embodiment of the present invention is shown;

[0043] Figure 9 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention is shown.

[0044] Icons: 100 - electronic device; 700 - apnea detection device; 111 - processor; 112 - storage medium; 113 - memory; 114 - input / output interface; 115 - wired or wireless network interface; 116 - power supply; 1121 - operating system; 1122 - data; 1123 - application; 710 - time domain feature extraction module; 720 - frequency domain feature extraction module; 730 - breathing detection module; 740 - first determination module; 750 - second determination module. DETAILED DESCRIPTION

[0045] The following will be combined with the accompanying drawings to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0046] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely intended to represent selected embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative work are within the scope of protection of the present invention.

[0047] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0048] In one embodiment, Figure 1As shown, a method for detecting apnea is provided. The method can be applied to electronic devices such as piezoelectric film sensors and cloud servers, and can be used for both offline and online detection. The method for detecting apnea includes the following steps:

[0049] Step S101: extracting the time domain features of the collected ballistocardial signals.

[0050] In this embodiment, the ballistocardiogram signal is a time-domain signal acquired by a piezoelectric film sensor, comprising both a respiratory and heartbeat time-domain signal. The piezoelectric film is placed under the user's chest. As the user breathes, the chest contracts, exerting varying pressures on the piezoelectric film sensor. The ballistocardiogram signal collected by the piezoelectric film sensor reflects the user's breathing condition. Acquiring this ballistocardiogram signal is simple and convenient, requiring no specialized medical equipment or physician intervention, and will not disrupt the user's sleep.

[0051] Optionally, when the apnea detection method provided in this embodiment is applied to a piezoelectric film sensor, the piezoelectric film sensor can collect the cardiac ballistoic signal, extract the time domain characteristics of the cardiac ballistoic signal, and detect apnea events; when the apnea detection method provided in this embodiment is applied on a cloud server, the piezoelectric film sensor can collect the cardiac ballistoic signal, and send the collected cardiac ballistoic signal to the cloud server, which extracts the time domain characteristics based on the received cardiac ballistoic signal and detects apnea events.

[0052] Step S102 : When the time domain feature of the ballistocardi signal meets the first apnea condition, extract the frequency domain feature of the ballistocardi signal.

[0053] In this embodiment, respiratory waveforms of apnea events can be pre-collected, and a first apnea condition can be set based on the respiratory waveforms of the apnea events. After extracting the time domain features of the ballistocardi signal, the electronic device can determine whether the time domain features of the ballistocardi signal meet the pre-set first apnea condition, that is, determine whether apnea has occurred in the time domain. If it is determined that the time domain features of the ballistocardi signal meet the first apnea condition, the frequency domain features of the ballistocardi signal are extracted, so that the frequency domain features of the ballistocardi signal can be used to determine whether apnea has occurred in the frequency domain.

[0054] Step S103: If the frequency domain feature meets the second apnea condition, it is determined that an apnea event exists.

[0055] In this embodiment, a second apnea condition can be pre-set based on the frequency domain representation of the respiratory waveform indicating an apnea event. After extracting the frequency domain features of the ballistocardi signal, the electronic device can determine whether the frequency domain features meet the pre-set second apnea condition. If the frequency domain features meet the pre-set second apnea condition, the ballistocardi signal is determined to exhibit apnea in both the time and frequency domains, thereby determining the presence of an apnea event, i.e., determining that the user has experienced apnea.

[0056] As can be seen, the apnea detection method provided by the embodiment of the present invention extracts the time domain features of the collected ballistocardi signal. When the time domain features of the ballistocardi signal meet the first apnea condition, the frequency domain features of the ballistocardi signal are extracted. When the frequency domain features meet the second apnea condition, the presence of an apnea event is determined. In this way, the time domain and frequency domain features of the ballistocardi signal are combined. When apnea is determined in both the time and frequency domains, the presence of an apnea event is determined, effectively reducing the possibility of misjudgment and improving the accuracy of apnea event detection. The entire detection process does not require manual judgment, and the acquisition of the ballistocardi signal is relatively convenient, which improves the operational simplicity of apnea event detection.

[0057] Alternatively, as Figure 2 The figure shows a comparison diagram of the respiratory waveform of normal respiratory rhythm and the respiratory waveform of apnea. The respiratory waveform of normal respiratory rhythm will produce regular peaks and troughs following the contraction of the chest cavity, while the respiratory waveform of apnea will not produce regular peaks and troughs. Therefore, the time domain characteristics of the cardiac ballistic signal in this embodiment may include the amplitude of each peak in the cardiac ballistic signal. Before the above step S102, it can be determined whether the first apnea condition is met based on the amplitude of each peak in the cardiac ballistic signal. Please refer to Figure 3 Before step S102, the apnea detection method may further include:

[0058] Step S301, determining multiple continuous target peaks based on the time domain characteristics of the cardiac ballistogram signal; wherein, among the multiple continuous target peaks, the ratio between the amplitude of the peak before the first target peak and the amplitude of the first target peak is greater than a preset ratio, the ratio between the amplitude of the peak after the last target peak and the amplitude of the last target peak is greater than a preset ratio, and among the amplitudes of any two adjacent target peaks, the ratio between the larger amplitude and the smaller amplitude is less than or equal to the preset ratio.

[0059] In this embodiment, since, among the multiple consecutive target peaks, the ratio of the amplitude of the peak preceding the first target peak to the amplitude of the first target peak is greater than a preset ratio, and the ratio of the amplitude of the peak following the last target peak to the amplitude of the last target peak is greater than a preset ratio, and at the same time, the ratio of the larger amplitude to the smaller amplitude of any two adjacent target peaks is less than or equal to the preset ratio, this indicates that the amplitude of the peak preceding the first target peak is much greater than the amplitude of the first target peak, the amplitude of the peak following the last target peak is much greater than the amplitude of the last target peak, and the amplitudes of the multiple consecutive target peaks are not much different. In this case, the ballistocardi signal appears in the time domain as a series of multiple peaks with smaller amplitudes. The duration of the multiple peaks with smaller amplitudes (target peaks) can be calculated and compared with a preset time. Based on the comparison result, it is determined whether the time domain characteristics of the ballistocardi signal meet the first apnea condition. It should be understood that the amplitudes of the multiple consecutive target peaks mentioned in this embodiment are not much different. This does not mean that the amplitudes of the multiple consecutive target peaks are basically the same. Instead, it means that the difference between the amplitudes of the multiple consecutive target peaks is smaller than the difference between the amplitudes of the previous peak of the first target peak and the first target peak, and the difference between the amplitudes of the next peak of the last target peak and the last target peak.

[0060] It should be noted that the specific value of the preset ratio can be set according to actual conditions and is not limited in this embodiment. For example, the preset ratio can be 80, 75, 90, etc.

[0061] Step S302: If the duration of the plurality of consecutive target peaks is greater than or equal to a preset time, it is determined that the time domain characteristics of the ballistocardiographic signal meet the first apnea condition.

[0062] In this embodiment, the duration can be the difference between the time when the first target peak is located and the time when the last target peak is located in the multiple consecutive target peaks. When the duration of multiple consecutive target peaks is greater than or equal to the preset time, the cardiac ballistic signal can correspond to Figure 2 The respiratory waveform of the apnea appears as apnea in the time domain, so it is determined that the time domain characteristics of the cardiopulmonary bypass signal meet the first apnea condition.

[0063] Among them, the preset time can be set according to the actual situation. For example, the medical definition of apnea is that the airflow through the mouth and nose completely stops for more than 10 seconds (including 10 seconds) during sleep. Then, the preset time can be set to 10 seconds. When there are multiple consecutive target wave peaks in the cardiac shock signal and the duration of the multiple consecutive target wave peaks is greater than or equal to 10 seconds, it is determined that the time-domain feature of the cardiac shock signal meets the first apnea condition.

[0064] In the apnea detection method provided by the embodiment of the present invention, after extracting the amplitude of each wave peak of the cardiac shock signal, multiple consecutive target wave peaks can be determined according to the amplitude of each wave peak in the cardiac shock signal. When the duration of the multiple consecutive target wave peaks is greater than or equal to the preset time, it is determined that the time-domain feature of the cardiac shock signal meets the first apnea condition. In this way, it is realized to determine whether apnea occurs in the time domain of the cardiac shock signal through the duration of multiple wave peaks with smaller amplitudes.

[0065] Next, a specific implementation manner for determining multiple consecutive target wave peaks is given. Please refer to Figure 4 , the above step S301 may include the following sub-steps:

[0066] Sub-step S3011: Perform peak searching on the cardiac shock signal to determine adjacent first and second wave peaks, where the time corresponding to the first wave peak is less than the time corresponding to the second wave peak.

[0067] In this embodiment, the amplitude corresponding to each moment in the cardiac shock signal can be expressed as x(1), x(2),..., x(n). If x(m - 1) < x(m) and x(m + 1) < x(m), it means that x(m) is the amplitude of a wave peak, and m is the moment where the wave peak is located. By searching for the amplitudes of each wave peak in the cardiac shock signal, two consecutive wave peaks, that is, adjacent first and second wave peaks, can be found. For example, m and m + p are the moments corresponding to adjacent first and second wave peaks respectively, and m < m + p, and x(m) and x(m + p) are the amplitudes of the first and second wave peaks respectively.

[0068] In this embodiment, when searching for peaks in a ballistocardiogram signal, the electronic device may search for two consecutive peaks in chronological order. In this embodiment, the preceding peak of the two adjacent peaks is referred to as the first peak, and the succeeding peak is referred to as the second peak. After finding the adjacent first and second peaks, the amplitudes of the first and second peaks are compared. If the ratio between the amplitudes of the first and second peaks is greater than a preset ratio, sub-step S3012 is executed. If the ratio between the amplitudes of the first and second peaks is not greater than the preset ratio, the peak search is repeated, i.e., the second peak is used as the new first peak, and the next peak adjacent to the new first peak is searched for, until the ratio between the amplitudes of the preceding and succeeding peaks of the two adjacent peaks is greater than the preset ratio. For example, assuming that the amplitudes of the first peak and the second peak are x(m) and x(m+p) respectively, and the preset ratio is 80, when x(m) and x(m+p) satisfy x(m)≤80x(m+p), the peak search action is repeated; when x(m)>80x(m+p), sub-step S3012 is executed.

[0069] Sub-step S3012: If the ratio between the amplitude of the first peak and the amplitude of the second peak is greater than a preset ratio, then search for at least one consecutive third peak after the moment corresponding to the second peak, until the ratio between the amplitude of the next peak after the third peak and the amplitude of the third peak is greater than the preset ratio; wherein, for each third peak and the amplitude of the adjacent previous peak, the ratio between the larger amplitude and the smaller amplitude is less than or equal to the preset ratio.

[0070] In this embodiment, if the ratio between the amplitude of the first peak and the amplitude of the second peak of the two adjacent peaks found is greater than a preset ratio, the time at which the second peak is located is determined, and the search for at least one third peak is continued after the time corresponding to the second peak. The amplitude of the third peak found is compared with the amplitude of the previous peak adjacent to the third peak. If the ratio between the larger amplitude and the smaller amplitude of the amplitudes of the third peak and the previous peak is less than or equal to the preset ratio, the search for a third peak is continued after the time corresponding to the third peak. When the ratio between the amplitude of the next peak after the third peak found and the amplitude of the third peak is greater than the preset ratio, the peak search is stopped.

[0071] For example, after the time m+p corresponding to the second peak, one or more consecutive third peaks are searched, where the ratio of the larger amplitude to the smaller amplitude of each third peak relative to the amplitude of the adjacent previous peak is less than or equal to 80. Assume that the third peak currently found is at time m+q and has an amplitude of x(m+q), and the next peak adjacent to the third peak is at time m+h and has an amplitude of x(m+h). If x(m+q) and x(m+h) satisfy x(m+h)>80x(m+q), peak search stops and sub-step S3013 is executed.

[0072] Sub-step S3013: determining the second peak and all third peaks as target peaks, and obtaining a plurality of continuous target peaks.

[0073] In this embodiment, the second peak is the first target peak among the plurality of consecutive target peaks, and the last third peak is the last target peak among the plurality of consecutive target peaks. Since the ratio between the amplitude of the first peak and the amplitude of the second peak is greater than a preset ratio, and for all third peaks consecutive to the second peak, the ratio between the larger amplitude and the smaller amplitude of each third peak and the amplitude of the adjacent preceding peak is less than or equal to the preset ratio, and the ratio between the amplitude of the peak following the last third peak and the amplitude of the last third peak is greater than the preset ratio, by determining the second peak and all third peaks as target peaks, a plurality of consecutive peaks with smaller amplitudes can be determined between the two peaks with larger amplitudes, the first peak and the peak following the last third peak, thereby obtaining a plurality of consecutive target peaks.

[0074] Alternatively, see Figure 5 , the above-mentioned step S102 may include the following sub-steps:

[0075] Sub-step S1021 , determining a time period in which the time domain characteristics of the ballistocardiographic signal meet the first apnea condition.

[0076] That is, when it is determined that the time domain characteristics of the ballistocardi signal meet the first apnea condition, it is necessary to determine in which time period the time domain characteristics of the ballistocardi signal meet the first apnea condition.

[0077] In one embodiment, the time period can be determined based on the moments of the aforementioned multiple consecutive target peaks. For example, when the moment of the first target peak among the multiple consecutive target peaks is m+p, and the moment of the last target peak among the multiple consecutive target peaks is m+q, it can be determined that the time period during which the time domain characteristics of the ballistocardi signal meet the first apnea condition is (m+p) to (m+q), and the duration of the multiple consecutive target peaks is (m+q)-(m+p).

[0078] Sub-step S1022 , calculating the frequency spectrum of the ballistocardiographic signal within the time period; the frequency domain features include the amplitude of each peak in the frequency spectrum.

[0079] In this embodiment, the electronic device can obtain the frequency domain characteristics of the ballistocardi signal by calculating the frequency spectrum of the ballistocardi signal in the time period and extracting the amplitude of each peak in the frequency spectrum.

[0080] In one embodiment, a Fourier transform may be performed on the ballistocardi signal within a time period to obtain a spectrum of the ballistocardi signal within the time period. For example, when it is determined that the time period in which the time domain characteristics of the ballistocardi signal meet the first apnea condition is (m+p) to (m+q), a continuous Fourier transform or a discrete Fourier transform may be performed on the ballistocardi signal within this time period to obtain a spectrum of the ballistocardi signal within this time period.

[0081] In this embodiment, the spectrum of the cardiac impact signal in this time period may include the spectrum of the heartbeat frequency band and the spectrum of the respiratory frequency band, wherein the heartbeat frequency band may be 40Hz to 120Hz, and the respiratory frequency band may be 6Hz to 30Hz. Considering that under normal respiratory rhythm, in the spectrum of the cardiac impact signal, not only the spectrum of the heartbeat frequency band will have a peak with a large amplitude, but also the spectrum of the respiratory frequency band will have a peak with a large amplitude; but in the spectrum of the cardiac impact signal in apnea, only the spectrum of the heartbeat frequency band will have a peak with a large amplitude, and the spectrum of the respiratory frequency band will not have a peak with a large amplitude. Therefore, in this embodiment, it can be determined whether the second apnea condition is met based on the spectrum of the cardiac impact signal in this time period. Please refer to Figure 6 Before step S103, the apnea detection method may further include:

[0082] Step S601 : Calculate a first average value of the amplitudes of all the peaks corresponding to the heartbeat frequency band, and a second average value of the amplitudes of all the peaks corresponding to the respiratory frequency band.

[0083] In this embodiment, after calculating the spectrum of the cardiac impact signal in the above-mentioned time period, the electronic device extracts the amplitudes of all peaks in the spectrum of the heartbeat frequency band and performs average calculation to obtain the average value (i.e., the first average value) of the amplitudes of all peaks corresponding to the heartbeat frequency band; and extracts the amplitudes of all peaks in the spectrum of the respiratory frequency band and performs average calculation to obtain the average value (i.e., the second average value) of the amplitudes of all peaks corresponding to the respiratory frequency band.

[0084] Step S602: If there is at least one peak in the heartbeat frequency band whose amplitude is greater than a first preset multiple of the first average value, and there is no peak in the respiratory frequency band whose amplitude is greater than a second preset multiple of the second average value, it is determined that the frequency domain feature meets the second apnea condition.

[0085] In this embodiment, specific values of the first preset multiple and the second preset multiple can be set according to actual conditions. The first preset multiple and the second preset multiple can be the same or different.

[0086] For example, the first preset multiple and the second preset multiple can both be 2. Then, when there is a peak with an amplitude greater than 2 times the first average value in the heartbeat frequency band, and there is no peak with an amplitude greater than 2 times the second average value in the respiratory frequency band, it indicates that in the spectrum of the cardiac signal in this time period, there is a peak with a larger amplitude in the heartbeat frequency band, while there is no peak with a larger amplitude in the respiratory frequency band. The cardiac signal appears as apnea in the frequency domain, so it is determined that the frequency domain characteristics of the cardiac signal meet the second apnea condition.

[0087] The apnea detection method provided by an embodiment of the present invention calculates a first average value of the amplitudes of all peaks corresponding to the heartbeat frequency band and a second average value of the amplitudes of all peaks corresponding to the respiratory frequency band, determines whether there is a peak with a large amplitude in the heartbeat frequency band based on the first average value, and determines whether there is a peak with a large amplitude in the respiratory frequency band based on the second average value. When there is a peak with a large amplitude in the heartbeat frequency band and there is no peak with a large amplitude in the respiratory frequency band, it is determined that the frequency domain characteristics of the cardiopulmonary bypass signal meet the second apnea condition, thereby achieving accurate determination of whether the cardiopulmonary bypass signal in the time period manifests as apnea in the frequency domain, and eliminating interference with the apnea determination in the case of heart arrest.

[0088] In order to implement the corresponding steps in the above embodiments and various possible methods, a method for implementing an apnea detection device is given below. Figure 7 , which is a functional block diagram of an apnea detection device 700 provided in an embodiment of the present invention. It should be noted that the basic principles and technical effects of the apnea detection device 700 provided in this embodiment are the same as those in the aforementioned embodiments. For the sake of brevity, any details not mentioned in this embodiment are referred to the corresponding contents in the aforementioned embodiments. The apnea detection device 700 includes a time-domain feature extraction module 710, a frequency-domain feature extraction module 720, and a respiration detection module 730.

[0089] The time domain feature extraction module 710 is used to extract the time domain features of the collected ballistocardial signals.

[0090] It can be understood that the time domain feature extraction module 710 can execute the above step S101.

[0091] The frequency domain feature extraction module 720 is configured to extract the frequency domain feature of the ballistocardi signal when the time domain feature of the ballistocardi signal meets the first apnea condition.

[0092] It can be understood that the frequency domain feature extraction module 720 can execute the above step S102.

[0093] The respiration detection module 730 is configured to determine the presence of an apnea event when the frequency domain feature meets the second apnea condition.

[0094] It can be understood that the breathing detection module 730 can execute the above step S103.

[0095] Optionally, the frequency domain feature extraction module 720 can be used to determine the time period in which the time domain feature of the ballistocardi signal meets the first apnea condition, and calculate the spectrum of the ballistocardi signal within the time period; the frequency domain feature includes the amplitude of each peak in the spectrum.

[0096] The frequency domain feature extraction module 720 is specifically configured to perform Fourier transform on the ballistocardia signal within a time period to obtain a frequency spectrum of the ballistocardia signal within the time period.

[0097] It can be understood that the frequency domain feature extraction module 720 can execute the above steps S1021 to S1022.

[0098] Alternatively, see Figure 8 The time domain feature includes the amplitude of each peak in the ballistocardiographic signal. The apnea detection device 700 may further include a first determination module 740 and a second determination module 750.

[0099] The first determination module 740 is used to determine multiple continuous target peaks based on the time domain characteristics of the cardiac ballistogram signal; wherein, among the multiple continuous target peaks, the ratio between the amplitude of the peak before the first target peak and the amplitude of the first target peak is greater than a preset ratio, the ratio between the amplitude of the peak after the last target peak and the amplitude of the last target peak is greater than a preset ratio, and among the amplitudes of any two adjacent target peaks, the ratio between the larger amplitude and the smaller amplitude is less than or equal to the preset ratio; if the duration of the multiple continuous target peaks is greater than or equal to the preset time, it is determined that the time domain characteristics of the cardiac ballistogram signal meet the first apnea condition.

[0100] The duration is the difference between the time when the first target peak is located and the time when the last target peak is located.

[0101] In this embodiment, the first determination module 740 is specifically used to search for peaks in the cardiac ballistogram signal, determine adjacent first and second peaks, and the time corresponding to the first peak is less than the time corresponding to the second peak; if the ratio between the amplitude of the first peak and the amplitude of the second peak is greater than a preset ratio, then search for at least one continuous third peak after the time corresponding to the second peak until the ratio between the amplitude of the next peak after the third peak and the amplitude of the third peak is greater than the preset ratio; wherein, in the amplitude of each third peak and the adjacent previous peak, the ratio between the larger amplitude and the smaller amplitude is less than or equal to the preset ratio; the second peak and all third peaks are determined as target peaks, and multiple continuous target peaks are obtained.

[0102] It can be understood that the first determination module 740 can execute the above steps S301 to S302 and sub-steps S3011 to S3013.

[0103] In this embodiment, the spectrum includes a spectrum of a heartbeat frequency band and a spectrum of a respiratory frequency band. The second determination module 750 is used to calculate a first average value of the amplitudes of all peaks corresponding to the heartbeat frequency band, and a second average value of the amplitudes of all peaks corresponding to the respiratory frequency band. If there is at least one peak in the heartbeat frequency band whose amplitude is greater than a first preset multiple of the first average value, and there is no peak in the respiratory frequency band whose amplitude is greater than a second preset multiple of the second average value, it is determined that the frequency domain feature meets the second apnea condition.

[0104] It can be understood that the second determination module 750 can execute the above steps S601 to S602.

[0105] The apnea detection device 700 provided in an embodiment of the present invention uses a time domain feature extraction module 710 to extract the time domain features of the collected cardiopulmonary bypass signal. A frequency domain feature extraction module 720 extracts the frequency domain features of the cardiopulmonary bypass signal when the time domain features of the cardiopulmonary bypass signal meet a first apnea condition. A respiration detection module 730 determines the presence of an apnea event when the frequency domain features meet a second apnea condition. In this way, the time domain and frequency domain features of the cardiopulmonary bypass signal are combined to determine the presence of an apnea event when apnea is determined in both the time and frequency domains. This effectively reduces the possibility of misjudgment and improves the accuracy of apnea event detection. The entire detection process does not require manual judgment, and the acquisition of the cardiopulmonary bypass signal is relatively convenient, improving the operational simplicity of apnea event detection.

[0106] The electronic device provided in an embodiment of the present invention may include a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the apnea detection method provided in the above method embodiment.

[0107] The memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required for functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory can include a high-speed random access memory and a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory can also include a memory controller to provide the processor with access to the memory.

[0108] Figure 9 FIG. 1 is a schematic diagram of a hardware structure of an electronic device 100 provided in an embodiment of the present invention. Figure 9 As shown, the electronic device 100 may have relatively large differences due to different configurations or performances, and may include one or more processors (Processing Units, CPU) 111 (the processor 111 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 113 for storing data, and one or more storage media 112 for storing application programs 1123 or data 1122 (for example, one or more mass storage devices). Among them, the memory 113 and the storage medium 112 can be temporary storage or permanent storage. The program stored in the storage medium 112 may include one or more modules, each module may include a series of instruction operations on the electronic device 100. Furthermore, the processor 111 can be configured to communicate with the storage medium 112 to execute a series of instruction operations in the storage medium 112 on the electronic device 100. The electronic device 100 may also include one or more power supplies 116, one or more wired or wireless network interfaces 115, one or more input and output interfaces 114, and / or one or more operating systems 1121, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0109] The input / output interface 114 can be used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by a communications provider of the electronic device 100. In one embodiment, the input / output interface 114 includes a network adapter (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one embodiment, the input / output interface 114 can be a radio frequency (RF) module for wirelessly communicating with the Internet.

[0110] It can be understood by those skilled in the art that Figure 9 The structure shown is only for illustration and does not limit the structure of the electronic device 100. For example, the electronic device 100 may further include Figure 9 More or fewer components than shown, or with Figure 9 Different configurations shown.

[0111] The electronic device provided by an embodiment of the present invention extracts the time domain features of a collected cardiac ballistocardi signal. When the time domain features of the cardiac ballistocardi signal meet a first apnea condition, it extracts the frequency domain features of the cardiac ballistocardi signal. When the frequency domain features meet a second apnea condition, it determines the presence of an apnea event. In this way, the time domain and frequency domain features of the cardiac ballistocardi signal are combined, and the presence of an apnea event is determined when apnea is determined in both the time and frequency domains. This effectively reduces the possibility of misjudgment and improves the accuracy of apnea event detection. The entire detection process does not require manual judgment, and the acquisition of cardiac ballistocardi signals is relatively convenient, improving the operational simplicity of apnea event detection.

[0112] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the various processes of the aforementioned apnea detection method embodiment and achieves the same technical effects. To avoid repetition, the details are omitted here. The computer-readable storage medium may be, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a portion of code, and the module, program segment or a portion of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0114] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0115] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0116] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A method for detecting apnea, characterized in that: The method comprises: Extracting the time domain features of the collected cardiac ballistic signals; Determining a plurality of continuous target peaks according to the time domain characteristics of the ballistocardi signal; the time domain characteristics include the amplitude of each peak in the ballistocardi signal; If the duration of the plurality of consecutive target peaks is greater than or equal to a preset time, it is determined that the time domain feature of the ballistocardi signal meets the first apnea condition; In a case where the time domain characteristics of the cardiac ballistic signal meet the first apnea condition, determining a time period in which the time domain characteristics of the cardiac ballistic signal meet the first apnea condition; calculating a spectrum of the cardiac ballistic signal within the time period, and extracting a frequency domain characteristic of the cardiac ballistic signal; the spectrum including a spectrum of a heartbeat frequency band and a spectrum of a respiratory frequency band, and the frequency domain characteristic including an amplitude of each peak in the spectrum; Calculating a first average value of the amplitudes of all peaks of the spectrum corresponding to the heartbeat frequency band, and a second average value of the amplitudes of all peaks of the spectrum corresponding to the respiratory frequency band; If the amplitude of at least one spectrum peak in the heartbeat frequency band is greater than a first preset multiple of the first average value, and the amplitude of no spectrum peak in the respiratory frequency band is greater than a second preset multiple of the second average value, then it is determined that the frequency domain feature meets the second apnea condition; When the frequency domain feature meets the second apnea condition, it is determined that an apnea event exists.

2. The method according to claim 1, characterized in that Before the step of extracting the frequency domain features of the ballistocardi signal when the time domain features of the ballistocardi signal meet the first apnea condition, the method further includes: Among the multiple consecutive target peaks, the ratio of the amplitude of the previous peak of the first target peak to the amplitude of the first target peak is greater than a preset ratio, the ratio of the amplitude of the next peak of the last target peak to the amplitude of the last target peak is greater than the preset ratio, and among the amplitudes of any two adjacent target peaks, the ratio between the larger amplitude and the smaller amplitude is less than or equal to the preset ratio.

3. The method according to claim 2, characterized in that The determining of a plurality of continuous target peaks according to the time domain characteristics of the ballistocardi signal comprises: Perform peak searching on the ballistocardiographic signal to determine a first wave peak and a second wave peak that are adjacent to each other, wherein the time corresponding to the first wave peak is less than the time corresponding to the second wave peak; If the ratio between the amplitude of the first peak and the amplitude of the second peak is greater than the preset ratio, searching for at least one consecutive third peak after the moment corresponding to the second peak until the ratio between the amplitude of the next peak after the third peak and the amplitude of the third peak is greater than the preset ratio; wherein, for each third peak and the amplitude of the adjacent previous peak, the ratio between the larger amplitude and the smaller amplitude is less than or equal to the preset ratio; The second peak and all third peaks are determined as target peaks to obtain multiple continuous target peaks.

4. The method according to claim 2, characterized in that The duration is the difference between the time when the first target peak is located and the time when the last target peak is located.

5. The method according to claim 1, wherein The calculating the frequency spectrum of the ballistocardi signal within the time period includes: Performing Fourier transform on the ballistocardi signal within the time period to obtain a frequency spectrum of the ballistocardi signal within the time period.

6. An apnea detection device, characterized in that: The device comprises: A time domain feature extraction module is used to extract the time domain features of the collected cardiac ballistometry signal; a first determination module, configured to determine a plurality of continuous target peaks based on a time domain feature of the ballistocardi signal, wherein the time domain feature includes an amplitude of each peak in the ballistocardi signal; and determine that the time domain feature of the ballistocardi signal meets a first apnea condition if a duration of the plurality of continuous target peaks is greater than or equal to a preset time; A frequency domain feature extraction module is configured to, when the time domain feature of the cardiac ballistic signal meets the first apnea condition, determine a time period in which the time domain feature of the cardiac ballistic signal meets the first apnea condition; calculate a spectrum of the cardiac ballistic signal within the time period, and extract the frequency domain feature of the cardiac ballistic signal; the spectrum includes a spectrum of a heartbeat frequency band and a spectrum of a respiratory frequency band, and the frequency domain feature includes the amplitude of each peak in the spectrum; a second determination module, configured to calculate a first average value of the amplitudes of all peaks of the spectrum corresponding to the heartbeat frequency band, and a second average value of the amplitudes of all peaks of the spectrum corresponding to the respiratory frequency band; if the amplitude of at least one spectrum peak in the heartbeat frequency band is greater than a first preset multiple of the first average value, and if the amplitude of no spectrum peak in the respiratory frequency band is greater than a second preset multiple of the second average value, then determining that the frequency domain feature meets the second apnea condition; The breathing detection module is used to determine the presence of an apnea event when the frequency domain feature meets the second apnea condition.

7. An electronic device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the apnea detection method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the apnea detection method according to any one of claims 1 to 5.

Images