A compression detection method, device and storage medium for cardiopulmonary resuscitation
By combining frequency domain and time domain analysis, reference signals during cardiopulmonary resuscitation (CPR) are obtained, solving the problem of sensor dependence and achieving efficient ECG signal filtering and compression quality feedback, thereby improving the emergency treatment effect of CPR.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN MINDRAY BIO MEDICAL ELECTRONICS CO LTD
- Filing Date
- 2021-12-23
- Publication Date
- 2026-06-16
AI Technical Summary
Existing CPR chest compression detection and filtering technologies rely on additional sensors, which increases costs and results in a poor user experience. The sensor's compression feel is also unsatisfactory, limiting its application scenarios.
By acquiring reference signals during cardiopulmonary resuscitation (CPR) and performing frequency and time domain analysis, and combining time and frequency domain features to obtain compression event markers, ECG signal filtering is performed to avoid false positives and false negatives, thereby improving the filtering performance of ECG signals.
It effectively improves the CPR filtering performance of ECG signals, reduces compression frequency errors, increases the success rate of emergency treatment, provides real-time compression quality feedback and ECG waveform observation, and guides emergency treatment operations.
Smart Images
Figure CN116801808B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of cardiopulmonary resuscitation (CPR) compression detection technology, and more specifically to a method, device, and storage medium for CPR compression detection. Background Technology
[0002] CPR chest compression detection and filtering technology can detect compression indicators such as compression frequency based on compression-related reference signals, providing emergency responders with feedback on compression quality. It can also filter out electrocardiogram (ECG) signal interference caused by CPR compressions based on the detection of compression events on the reference signal, thus restoring the original ECG waveform to some extent. In this way, during compressions, emergency responders can adjust the quality of their operations in a timely manner through compression quality feedback such as compression frequency, and can also observe the filtered ECG waveform to obtain information about the patient's physical condition, reducing CPR interruptions and improving the success rate of resuscitation. Furthermore, some rhythm analysis algorithms can also analyze the filtered ECG waveform to provide suggested defibrillation decisions.
[0003] Currently, research on CPR chest compression detection and filtering technology mainly relies on CPR sensors, requiring additional sensor signals as compression reference signals for compression detection and filtering. For example, some literature proposes using one or more sensor signals such as chest compression displacement / compression velocity / compression acceleration generated by CPR compressions as compression reference signals. Other literature proposes combining sensor signals and chest impedance transformation as reference signals, and using different filtering models to filter CPR interference from ECG signals. However, these methods require additional sensor accessories, increasing costs, and the sensor compression feel is unsatisfactory, limiting application scenarios and resulting in a poor user experience. Summary of the Invention
[0004] This application provides a method for detecting chest compressions during cardiopulmonary resuscitation (CPR). The method includes: acquiring a reference signal related to chest compressions during CPR on a target subject and an electrocardiogram (ECG) signal of the target subject; performing frequency domain analysis on the reference signal to obtain frequency domain compression features; performing time domain analysis on the reference signal to obtain time domain compression features; performing time domain compression detection on the reference signal based on the frequency domain compression features and the time domain compression features to obtain a time domain compression event marker for the reference signal; determining an instantaneous compression interval based on the time domain compression event marker; and filtering the ECG signal based on the instantaneous compression interval to obtain a filtered ECG signal.
[0005] In another aspect, this application provides a method for detecting chest compressions during cardiopulmonary resuscitation (CPR). The method includes: providing a first detection mode and a second detection mode; when in the first detection mode, acquiring and outputting the compression frequency detected by a CPR sensor during CPR on a target object; when in the second detection mode, acquiring a reference signal related to chest compressions during CPR on the target object, performing frequency domain analysis on the reference signal to obtain frequency domain compression features, determining the compression frequency based on the frequency domain compression features, and outputting feedback information on compression quality related to the compression frequency.
[0006] In another aspect, this application provides a cardiopulmonary resuscitation (CPR) compression detection device, which includes a memory and a processor. The memory stores a computer program that is executed by the processor, and the computer program performs the aforementioned CPR compression detection method when executed by the processor.
[0007] In another aspect, this application provides a storage medium storing a computer program that, when running, executes the above-described cardiopulmonary resuscitation compression detection method.
[0008] The cardiopulmonary resuscitation compression detection method and device according to the embodiments of this application obtains time-domain compression event markers through time-domain and frequency-domain combined analysis, which can avoid the problems of false detection and missed detection of compression events leading to incorrect compression frequency and ECG distortion after filtering. Based on the obtained valid compression event markers, CPR interference filtering is performed on the ECG signal, which can effectively improve the CPR filtering performance of the ECG signal and better guide emergency personnel to carry out emergency rescue. Attached Figure Description
[0009] Figure 1 A schematic flowchart of a cardiopulmonary resuscitation compression detection method according to an embodiment of this application is shown.
[0010] Figure 2 This diagram illustrates a time-domain example of a reference signal related to chest compressions acquired in a compression detection method for cardiopulmonary resuscitation according to an embodiment of this application.
[0011] Figure 3 This diagram illustrates a frequency domain example of a reference signal related to chest compressions obtained in a cardiopulmonary resuscitation compression detection method according to an embodiment of this application.
[0012] Figure 4 An example diagram showing the compression event location of a reference signal in a compression detection method for cardiopulmonary resuscitation according to an embodiment of this application is provided.
[0013] Figure 5 An example of a display interface for displaying parameters in a cardiopulmonary resuscitation compression detection method according to an embodiment of this application is shown.
[0014] Figure 6 Showing according to Figure 1 The illustrated embodiment provides an exemplary flowchart for CPR chest compression detection and filtering.
[0015] Figure 7 Showing according to Figure 1 Another exemplary flowchart for CPR chest compression detection and filtering in the illustrated embodiment.
[0016] Figure 8 A schematic flowchart of a compression detection method for cardiopulmonary resuscitation according to another embodiment of this application is shown.
[0017] Figure 9 A schematic block diagram of a compression detection device for cardiopulmonary resuscitation according to an embodiment of this application is shown. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of this application more apparent, exemplary embodiments according to this application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely a part of the embodiments of this application, and not all of the embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein. Based on the embodiments of this application described herein, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of this application.
[0019] The following description provides numerous specific details to offer a more thorough understanding of this application. However, it will be apparent to those skilled in the art that this application can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described to avoid confusion with this application.
[0020] It should be understood that this application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of this application to those skilled in the art.
[0021] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. When used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “compose” and / or “comprising,” when used in this specification, identify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term “and / or” includes any and all combinations of the associated listed items.
[0022] To fully understand this application, detailed steps and structures will be presented in the following description to illustrate the technical solutions proposed in this application. Preferred embodiments of this application are described in detail below; however, in addition to these detailed descriptions, this application may have other implementation methods.
[0023] First, refer to Figure 1 This application describes a method for detecting chest compressions during cardiopulmonary resuscitation according to one embodiment. Figure 1 A schematic flowchart of a cardiopulmonary resuscitation compression detection method 100 according to an embodiment of this application is shown. Figure 1 As shown, the compression detection method 100 for cardiopulmonary resuscitation may include the following steps:
[0024] In step S110, reference signals related to chest compressions during cardiopulmonary resuscitation of the target object and the target object's electrocardiogram signal are acquired.
[0025] In step S120, frequency domain analysis is performed on the reference signal to obtain frequency domain pressing characteristics.
[0026] In step S130, time-domain analysis is performed on the reference signal to obtain time-domain pressing characteristics.
[0027] In step S140, time-domain press detection is performed on the reference signal based on the frequency-domain press feature and the time-domain press feature to obtain the time-domain press event marker of the reference signal.
[0028] In step S150, the instantaneous compression interval is determined based on the time-domain compression event marker, and the ECG signal is filtered based on the instantaneous compression interval to obtain a filtered ECG signal.
[0029] In embodiments of this application, reference signals (hereinafter referred to as reference signals) related to chest compressions during cardiopulmonary resuscitation (CPR) on the target object are first acquired, such as at least one of the following: chest impedance signal, blood oxygen signal, respiratory signal, and signals sensed by a CPR sensor. The signals sensed by the CPR sensor may include, for example, at least one of pressure signal, displacement signal, velocity signal, and acceleration signal. After acquiring the above reference signals, frequency domain analysis and time domain analysis are performed on the reference signals to obtain the frequency domain compression characteristics and time domain compression characteristics of the reference signals, respectively. Here, although in Figure 1 The steps are shown as S120 and S130 respectively, but the order of these two steps is not necessary; they can be interchanged or performed simultaneously.
[0030] In the embodiments of this application, time-domain compression detection is performed on the reference signal based on frequency-domain compression characteristics and time-domain compression characteristics. That is, the time-domain compression event marker of the reference signal is obtained by combining time-domain and frequency-domain analysis. Since reference signals such as chest impedance signals are not as regularly stable as CPR sensor signals, but are easily affected by individuals and compression, significant morphological changes may occur within the same body or between different individuals. In some cases, compression causes the time-domain signal of chest impedance signals to exhibit low amplitude, double peaks, or even multi-peak patterns. Therefore, if compression detection is performed only on reference signals such as chest impedance signals in the time domain, compression events may be missed or falsely detected. On the other hand, if compression detection is performed only on reference signals such as chest impedance signals in the frequency domain, the detection results are not as accurate as those obtained in the time domain, and the compression detection and filtering performance cannot be guaranteed. Therefore, the compression detection method according to the embodiments of this application, through combined analysis in the time domain and frequency domain, can avoid the problems of false detection and missed detection of compression events in the time domain, such as low amplitude, double peak or even multi-peak shape of reference signals like chest impedance signals, which leads to incorrect compression frequency and ECG distortion after filtering. Based on the valid compression event markers on the obtained reference signal, CPR interference filtering can be used to effectively improve the CPR filtering performance of ECG signals.
[0031] The compression detection method 100 for cardiopulmonary resuscitation according to an embodiment of this application is described in more detail below.
[0032] In the embodiments of this application, after obtaining the reference signal, a bandpass filter can first be used to filter out unwanted signals outside the pressing frequency band (e.g., 100-120 times / minute (cpm)). Next, a Fast Fourier Transform (FFT) frequency domain calculation can be performed on the filtered reference signal to obtain the selected band spectrum, ultimately yielding the amplitude-frequency characteristics of the reference signal in the band of interest. Afterward, frequency domain pressing characteristics can be obtained based on such a spectrum, including at least one of the following: instantaneous pressing frequency, the spectral amplitude corresponding to the instantaneous pressing frequency, and at least one of the pressing harmonic component characteristics. Specifically, based on the spectrum of the reference signal, all frequency components within the pressing frequency band and their corresponding amplitudes can be detected. The frequency domain characteristics of each frequency component, such as its frequency position and amplitude, can be analyzed to determine the pressing fundamental frequency. The finally selected pressing fundamental frequency is the instantaneous pressing frequency, and the amplitude corresponding to this frequency can be called the frequency domain pressing peak amplitude. In addition, the characteristics of the pressing harmonic components can be obtained based on the frequency characteristic relationship between other frequency components and the pressing fundamental frequency, and the time-domain peak shape of the obtained reference signal (such as no pressing peak, single pressing peak, two pressing peaks, multiple pressing peaks, etc.) can be inferred from this.
[0033] Figure 2 and Figure 3Example diagrams of the time-domain waveform and spectrum of the reference signal (taking a multi-peak chest impedance signal as an example) acquired in the compression detection method according to embodiments of this application are shown. The reference signal is a chest impedance signal waveform collected from a cardiopulmonary resuscitation patient at a compression frequency of approximately 110 cpm, and the spectrum is obtained after FFT calculation. From the time-domain waveform, one CPR compression produces multiple peaks in the impedance waveform. If only the time-domain signal is analyzed, it is difficult to determine the actual compression frequency; however, from the spectrum analysis, there is a frequency component with a large spectral amplitude within the compression frequency band, referred to as the compression fundamental frequency (e.g., ...). Figure 3 The frequency components shown (where the x-axis is 1.758 and the y-axis is 0.2034) represent the actual pressing frequency. Furthermore, within the pressing frequency band, several frequency components with large spectral amplitudes are visible, each corresponding to a frequency that is a multiple of the fundamental pressing frequency. These are called pressing harmonics (such as...). Figure 3 The x-axis values shown are the compression harmonics at 3.589, 5.396, and 7.19, respectively. Therefore, although the chest impedance signal exhibits multiple peaks in the time domain, the fundamental frequency and harmonic components of the compression can be determined through frequency domain analysis, thus enabling frequency-domain compression feature-assisted time-domain compression peak detection (described below). Here, although described as compression peak detection, compression events may actually occur at troughs rather than peaks (described below). Therefore, the compression detection in this application is described as compression peak detection in some examples and compression trough detection in others; these are collectively referred to as compression event detection.
[0034] The above describes the process of obtaining frequency domain press features. The following describes time domain press features and the detection of time domain press events based on these features.
[0035] In the embodiments of this application, the time-domain compression features obtained by time-domain analysis of the reference signal may include at least one of the following: compression interval, compression amplitude, and duration of a single compression. Taking the chest impedance signal as an example, the chest impedance signal can be preprocessed using a bandpass filter to filter out irrelevant signals outside the compression frequency band (such as impedance fluctuations caused by breathing). The filtered chest impedance signal is then used to search for compression event (peak or trough) markers based on the time-domain compression features. Initially, the search can be based on prior knowledge of the time-domain compression features, which references information such as the range of impedance amplitude changes caused by compression, the range of impedance peak widths, and recommended compression frequencies proposed in the American Heart Association (AHA) cardiopulmonary resuscitation guidelines, published literature, or publicly available technologies. Later in the search, this prior knowledge can be combined to continuously learn from the previously searched time-domain compression features, ultimately optimizing and adjusting the compression event search strategy to detect time-domain compression event markers on the chest impedance signal.
[0036] Furthermore, in the embodiments of this application, during the time-domain press event search based on time-domain press features, it is also possible to determine whether the time-domain press event occurs at a time-domain peak or a time-domain trough based on the data characteristics of the reference signal. When it is determined that the time-domain press event occurs at a time-domain peak, the time-domain press event search includes a time-domain press peak search; when it is determined that the time-domain press event occurs at a time-domain trough, the time-domain press event search includes a time-domain press trough search. In this embodiment, the time-domain press event detection strategy will also automatically distinguish whether the peak or trough in the time-domain waveform of the reference signal represents the press event location (as mentioned above) based on the data characteristics of the reference signal over a period of time (including but not limited to time-domain peak amplitude and time-domain trough amplitude), thereby adjusting the time-domain press event detection strategy to search for peaks or troughs to obtain a more accurate press event location (i.e., time-domain press event marker). Figure 4 As shown in the figure, the upper part is the impedance waveform, and its trough is the same as the gold standard (the pressure signal collected by the sensor, i.e.) Figure 4 The peaks of the lower half of the waveform correspond one-to-one, and compared to the peaks of the impedance waveform, they better represent the timing of the pressing event. Therefore, in Figure 4 In the example shown, the time-domain press event detection detects the trough position of the reference signal's time-domain waveform.
[0037] As described above, in the embodiments of this application, time-domain press detection is performed on the reference signal based on frequency-domain press features and time-domain press features to obtain the time-domain press event markers of the reference signal. Specifically, time-domain press event search can be performed based on time-domain press features, and the time-domain press event search can be optimized and adjusted based on frequency-domain press features to obtain the time-domain press event markers of the reference signal. The time-domain press event search based on time-domain press features has been described above; the optimization and adjustment of the time-domain press event search based on frequency-domain press features is described below.
[0038] In the embodiments of this application, optimizing the press event search based on frequency domain press features may include at least one of the following: adjusting the threshold of the press interval of the time domain press event search based on the instantaneous press frequency; adjusting the threshold of the press amplitude of the time domain press event search based on the spectral amplitude corresponding to the instantaneous press frequency; and adjusting the threshold of the single press duration of the time domain press event search based on the instantaneous press frequency and the press harmonic component features. For example, by adjusting the interval threshold of the time-domain search for press peaks (valleys) using the press fundamental frequency, only one press event occurs within the interval threshold time window, i.e., only one peak (valley) represents a press. Similarly, by adjusting the threshold of the time-domain search for peak (valley) amplitude using the press fundamental frequency peak amplitude, peaks (valleys) with amplitudes below the threshold do not represent true press events and are therefore invalid peaks (valleys). Furthermore, by adjusting the threshold of the time-domain peak (valley) width using the press fundamental frequency and harmonic components, the duration of a single press event should be between the upper and lower thresholds, i.e., the width of an effective peak (valley) should be within the upper and lower limits. Overall, using frequency-domain press characteristics to assist time-domain press peak detection can reduce the occurrence of missed low-amplitude press peaks or false detections of double / multiple press peaks caused by press harmonics.
[0039] Finally, based on the time-domain compression event markers, the instantaneous compression interval can be determined, and the ECG signal of the target object can be filtered based on the instantaneous compression interval to obtain the filtered ECG signal. Since the effective compression event markers on the reference signal are obtained by combining the time-domain compression features and the frequency-domain compression features, the CPR interference filtering based on this can effectively improve the CPR filtering performance of the ECG signal. In the embodiments of this application, before filtering the ECG signal based on the instantaneous compression interval, a correlation analysis can be performed on the noise of the ECG signal and the reference signal, and the filtering mode can be determined based on the results of the correlation analysis for filtering. For example, in one example, a least mean square (LMS) adaptive filter is used to implement adaptive CPR interference filtering on the ECG signal; wherein, before implementing adaptive CPR interference filtering, a correlation analysis can be performed on the ECG waveform noise and the reference signal, and based on the noise state of the ECG waveform, it can be determined which filtering mode should be used for the ECG waveform, controlling the order of the adaptive filter, thereby achieving a better filtering effect. In the embodiments of this application, the ECG waveform after ECG anti-CPR interference filtering can be displayed on the user interface in real time, such as... Figure 5 The ECG waveform after CPR interference filtering shown in the lower left corner (the waveform before filtering can also be seen in...) Figure 5 As seen in, Figure 5 (As shown in the upper left corner) This helps emergency responders observe the patient's physical condition in real time during chest compressions, reducing the time spent interrupting chest compressions.
[0040] In the embodiments of this application, rhythm analysis can also be performed based on the filtered ECG signal; the rhythm state during the compression process can be obtained based on the results of the rhythm analysis; and a shock decision can be output based on the rhythm state. The ECG waveform after anti-CPR interference filtering can reflect the rhythm state of the real ECG waveform to a certain extent. Therefore, it can participate in rhythm analysis, obtain the rhythm state during the compression process, provide a shock decision, assist emergency personnel in performing emergency operations, and reduce compression interruption time.
[0041] In a further embodiment of this application, the pressing frequency can be determined based on frequency domain pressing characteristics, and feedback information on pressing quality related to the pressing frequency can be output, such as the numerical value of the pressing frequency and / or prompts on the pressing speed, for example... Figure 5 The display shows a press frequency of 146 cpm (in addition, as shown on the screen). Figure 5The displayed interface also shows information related to the ECG signal. Determining the compression frequency based on frequency domain compression characteristics can include: determining multiple instantaneous compression frequencies based on reference signals over multiple time periods; and determining the final compression frequency based on these multiple instantaneous compression frequencies. For example, a weighted average, geometric average, or median can be calculated from the multiple instantaneous compression frequencies to obtain the final compression frequency. In this embodiment, the compression frequency can be obtained using only frequency domain compression characteristics.
[0042] Furthermore, before determining the pressing frequency based on the frequency domain pressing characteristics, it can be determined whether the frequency domain pressing characteristics meet a reliability threshold. When the frequency domain pressing characteristics meet the reliability threshold condition, the pressing frequency is determined based on the frequency domain pressing characteristics. In this embodiment, the reliability of the frequency domain pressing characteristics is first detected, and the pressing frequency is determined based on the frequency domain pressing characteristics only when reliability is determined, which can improve the accuracy of the pressing frequency determination result.
[0043] When frequency-domain compression features do not meet the reliability threshold conditions, such as extremely small frequency-domain compression peak amplitude or unreasonable instantaneous compression frequency, these frequency-domain compression features are considered unreliable. In this case, the ECG signal of the target object can be analyzed to obtain ECG compression features (such as heart rate, heart rate frequency peak amplitude, heart rate band energy percentage, ECG compression frequency peak amplitude, and ECG compression band peak energy percentage, etc., at least one of these). Then, based on the ECG compression features, it is determined whether the frequency-domain compression features that do not meet the reliability threshold conditions are caused by compression. When it is determined that the frequency-domain compression features that do not meet the reliability threshold conditions are caused by compression, the frequency-domain compression features are modified based on the ECG compression features to make the modified frequency-domain compression features meet the reliability threshold conditions, and the compression frequency is determined based on the modified frequency-domain compression features. Conversely, when it is determined that a frequency domain pressing feature that does not meet the reliability threshold condition is not caused by pressing, the frequency domain pressing feature can be deleted; when it is impossible to determine whether a frequency domain pressing feature that does not meet the reliability threshold condition is caused by pressing, the frequency domain pressing feature can be retained, and the pressing frequency can be determined based on the frequency domain pressing feature.
[0044] The above describes an embodiment of determining the press frequency based on frequency domain press characteristics. In another embodiment, the press frequency can also be determined based on frequency domain press characteristics and time domain press event markers, and feedback information on press quality related to the press frequency can be output. Specifically, a first instantaneous press frequency can be determined based on frequency domain press characteristics; a second instantaneous press frequency can be determined based on time domain press event markers; reliability analysis can be performed on the first and second instantaneous press frequencies respectively; based on the results of the reliability analysis, the first instantaneous press frequency, the second instantaneous press frequency, or a combination of the two can be used as a third instantaneous press frequency; the above process is repeated for reference signals over multiple time periods to obtain multiple third instantaneous press frequencies; a weighted average, geometric average, or median can be calculated from the multiple third instantaneous press frequencies to obtain the final press frequency. In this embodiment, determining the press frequency based on frequency domain press characteristics and time domain press event markers can yield a more accurate press frequency.
[0045] The above exemplarily illustrates a compression detection method for cardiopulmonary resuscitation according to one embodiment of this application. To better understand this method, Figure 6 An exemplary flowchart of CPR chest compression detection and filtering is shown (using the reference signal as an impedance signal and the compression event as a compression peak as an example), which can help to better understand the content described above. Furthermore, Figure 7 Another exemplary flowchart for CPR chest compression detection and filtering is shown. This flowchart is similar to... Figure 6 Compared to the flowchart shown, there are some slight modifications, namely in Figure 6 The compression frequency is determined based on the frequency domain compression characteristics, while... Figure 7 The pressing frequency is determined based on the frequency domain pressing characteristics and the time domain pressing characteristics, which have been described in the previous text and will not be repeated here.
[0046] Based on the above description, the cardiopulmonary resuscitation compression detection method according to the embodiments of this application obtains time-domain compression event markers through combined analysis of the time and frequency domains. This avoids the problems of false detection and missed detection of compression events in the time domain, such as low amplitude, bi-peak, or even multi-peak morphology of reference signals like chest impedance signals, which can lead to incorrect compression frequency and ECG distortion after filtering. In addition, CPR interference filtering of ECG signals based on the obtained valid compression event markers can effectively improve the CPR filtering performance of ECG signals and better guide emergency personnel in carrying out emergency treatment.
[0047] The following is combined with Figure 8 A method 800 for detecting chest compressions during cardiopulmonary resuscitation according to another embodiment of this application is described. For example... Figure 8 As shown, the compression detection method 800 for cardiopulmonary resuscitation may include the following steps:
[0048] In step S810, a first detection mode and a second detection mode are provided.
[0049] In step S820, when in the first detection mode, the compression frequency detected by the cardiopulmonary resuscitation sensor during the cardiopulmonary resuscitation of the target object is acquired and output.
[0050] In step S830, when in the second detection mode, a reference signal related to chest compressions during cardiopulmonary resuscitation on the target object is acquired, frequency domain analysis is performed on the reference signal to obtain frequency domain compression features, the compression frequency is determined based on the frequency domain compression features, and feedback information on compression quality related to the compression frequency is output.
[0051] In this embodiment, two detection modes are provided. One detection mode obtains the compression frequency through a CPR sensor, while the other detection mode determines the compression frequency through the frequency domain compression characteristics of a reference signal (as described in the previous embodiment). Therefore, users can select different detection modes according to their needs, achieving flexible switching.
[0052] In a further embodiment of this application, a third detection mode may also be provided. In the third detection mode: a first compression frequency detected by a cardiopulmonary resuscitation (CPR) sensor during CPR on the target object is acquired; a reference signal related to chest compressions during CPR on the target object is acquired; frequency domain analysis is performed on the reference signal to obtain frequency domain compression features; a second compression frequency is determined based on the frequency domain compression features; a third compression frequency is determined based on the first and second compression frequencies; and feedback information on compression quality related to the third compression frequency is output. Exemplarily, determining the third compression frequency based on the first and second compression frequencies may include: averaging or weighted averaging the first and second compression frequencies to obtain the third compression frequency; or determining one of the first and second compression frequencies as the third compression frequency. In this embodiment, combining the compression frequencies obtainable in the first detection mode with those obtainable in the second detection mode yields a new compression frequency, resulting in a more accurate compression frequency.
[0053] In a further embodiment of this application, when in the second detection mode, time-domain analysis can be performed on the reference signal to obtain time-domain compression features; time-domain compression detection can be performed on the reference signal based on the frequency-domain compression features and the time-domain compression features to obtain the time-domain compression event marker of the reference signal; the instantaneous compression interval can be determined based on the time-domain compression event marker, and the ECG signal can be filtered based on the instantaneous compression interval to obtain the filtered ECG signal. This embodiment is combined with the foregoing description. Figure 1 The described embodiments are the same, and for the sake of brevity, they will not be repeated here.
[0054] Specifically, the step of performing time-domain press detection on the reference signal based on the frequency-domain press features and the time-domain press features to obtain the time-domain press event marker of the reference signal includes: performing time-domain press event search based on the time-domain press features, and optimizing and adjusting the time-domain press event search based on the frequency-domain press features to obtain the time-domain press event marker of the reference signal. The frequency domain press feature includes at least one of the following: instantaneous press frequency, spectral amplitude corresponding to the instantaneous press frequency, and press harmonic component features; the time domain press feature includes at least one of the following: single press duration, press amplitude, and press width; the optimization adjustment of the press event search based on the frequency domain press feature includes at least one of the following: adjusting the threshold of the press interval of the time domain press event search based on the instantaneous press frequency; adjusting the threshold of the press amplitude of the time domain press event search based on the spectral amplitude corresponding to the instantaneous press frequency; and adjusting the threshold of the single press duration of the time domain press event search based on the instantaneous press frequency and the press harmonic component features. Furthermore, during the time-domain compression event search based on the aforementioned compression characteristics, the data characteristics of the reference signal are used to determine whether the time-domain compression event occurs at a time-domain peak or a time-domain trough. When it is determined that the time-domain compression event occurs at a time-domain peak, the time-domain compression event search includes a time-domain compression peak search; when it is determined that the time-domain compression event occurs at a time-domain trough, the time-domain compression event search includes a time-domain compression trough search. Additionally, before filtering the ECG signal based on the instantaneous compression interval, a correlation analysis is performed on the noise of the ECG signal and the reference signal, and a filtering mode is determined based on the results of the correlation analysis for use in the filtering. The compression quality feedback information related to the compression frequency includes the numerical value of the compression frequency and / or prompts regarding the compression speed. Furthermore, the frequency domain compression features may include instantaneous compression frequencies. Determining the compression frequency based on the frequency domain compression features may include: determining multiple instantaneous compression frequencies based on the reference signals over multiple time periods; and determining the final compression frequency based on the multiple instantaneous compression frequencies. Furthermore, determining the final compression frequency based on the multiple instantaneous compression frequencies may include: performing a weighted average, geometric average, or median calculation on the multiple instantaneous compression frequencies to obtain the final compression frequency. Furthermore, the reference signals may include at least one of the following: chest impedance signal, blood oxygen signal, respiratory signal, and signals sensed by a cardiopulmonary resuscitation (CPR) sensor, wherein the signals sensed by the CPR sensor include at least one of pressure signal, displacement signal, velocity signal, and acceleration signal. Furthermore, the filtered electrocardiogram (ECG) signal can be displayed in real time. Furthermore, rhythm analysis can be performed based on the filtered ECG signal; the rhythmic state during compression can be obtained based on the results of the rhythm analysis; and a shock decision can be output based on the rhythmic state.All of the above content is combined with the preceding text. Figure 1 The embodiments described have already been described, and further details will not be repeated here.
[0055] The above exemplarily describes a compression detection method for cardiopulmonary resuscitation according to an embodiment of this application. The following, in conjunction with... Figure 9 Describes a compression detection device for cardiopulmonary resuscitation provided according to another aspect of this application. Figure 9 A schematic block diagram of a cardiopulmonary resuscitation compression detection device 900 according to an embodiment of this application is shown. Figure 9 As shown, the cardiopulmonary resuscitation (CPR) compression detection device 900 may include a memory 910 and a processor 920. The memory 910 stores a computer program executed by the processor 920. When executed by the processor 920, the computer program performs the CPR compression detection method described above according to the embodiments of this application. In a further embodiment of this application, the CPR compression detection device 900 may further include a signal acquisition device 930, which can be used to acquire reference signals related to chest compressions during CPR on a target object and transmit them to the processor 920, so that the processor 920 can execute the CPR compression detection method described above according to the embodiments of this application. Those skilled in the art can understand the structure and operation of the components of the CPR compression detection device according to the embodiments of this application in conjunction with the foregoing description; for the sake of brevity, further details are omitted here.
[0056] Furthermore, according to embodiments of this application, a storage medium is also provided, on which program instructions are stored. When the program instructions are executed by a computer or processor, they are used to perform the corresponding steps of the cardiopulmonary resuscitation compression detection method of this application. The storage medium may, for example, include a memory card of a smartphone, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. A computer-readable storage medium may be any combination of one or more computer-readable storage media.
[0057] Furthermore, according to embodiments of this application, a computer program is also provided, which can be stored on a cloud or local storage medium. When this computer program is run by a computer or processor, it is used to perform the corresponding steps of the cardiopulmonary resuscitation compression detection method of this application.
[0058] Based on the above description, the cardiopulmonary resuscitation (CPR) compression detection method and device according to the embodiments of this application obtains time-domain compression event markers through combined time-domain and frequency-domain analysis. This avoids the problems of false detection and missed detection of compression events in the time domain, such as low amplitude, bi-peak, or even multi-peak patterns of reference signals like chest impedance signals, which can lead to incorrect compression frequency and ECG distortion after filtering. Furthermore, CPR interference filtering of the ECG signal based on the obtained valid compression event markers effectively improves the CPR filtering performance of the ECG signal, better guiding emergency personnel in performing first aid. In addition, the CPR compression detection method and device according to the embodiments of this application can provide two detection modes: one mode obtains the compression frequency through a CPR sensor, and the other mode determines the compression frequency through the frequency-domain compression characteristics of the reference signal. Users can select different detection modes according to their needs, achieving flexible switching.
[0059] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of this application. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of this application. All such changes and modifications are intended to be included within the scope of this application as claimed in the appended claims.
[0060] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0061] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed.
[0062] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.
[0063] Similarly, it should be understood that, in order to streamline this application and aid in understanding one or more of the various inventive aspects, features of this application may sometimes be grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of this application. However, this approach should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, its inventive point lies in solving the corresponding technical problem with features fewer than all features of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of this application.
[0064] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus so disclosed can be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.
[0065] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of this application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.
[0066] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules according to the embodiments of this application. This application can also be implemented as an apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such an implementation of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.
[0067] It should be noted that the above embodiments are illustrative of this application and not limiting of it, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.
[0068] The above are merely specific embodiments or descriptions of specific embodiments of this application. The scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. The scope of protection of this application shall be determined by the scope of the claims.
Claims
1. A compression detection device for cardiopulmonary resuscitation, characterized in that, The device includes a memory and a processor, the memory storing a computer program executed by the processor, the computer program performing the following steps when run by the processor: Acquire reference signals related to chest compressions during cardiopulmonary resuscitation of the target subject, as well as the target subject's electrocardiogram signal; Frequency domain analysis is performed on the reference signal to obtain frequency domain pressing characteristics; The reference signal is subjected to time-domain analysis to obtain time-domain pressing characteristics; Based on the frequency domain pressing features and the time domain pressing features, the reference signal is subjected to time domain pressing detection to obtain the time domain pressing event marker of the reference signal; The instantaneous compression interval is determined based on the time-domain compression event marker, and the ECG signal is filtered based on the instantaneous compression interval to obtain a filtered ECG signal. The step of performing time-domain press detection on the reference signal based on the frequency-domain press features and the time-domain press features to obtain the time-domain press event marker of the reference signal includes: performing time-domain press event search based on the time-domain press features, and optimizing and adjusting the time-domain press event search based on the frequency-domain press features to obtain the time-domain press event marker of the reference signal. The frequency domain press feature includes at least one of the following: instantaneous press frequency, spectral amplitude corresponding to the instantaneous press frequency, and press harmonic component features; the time domain press feature includes at least one of the following: press interval, press amplitude, and duration of a single press; the optimization adjustment of the press event search based on the frequency domain press feature includes at least one of the following: adjusting the threshold of the press interval of the time domain press event search based on the instantaneous press frequency; adjusting the threshold of the press amplitude of the time domain press event search based on the spectral amplitude corresponding to the instantaneous press frequency; and adjusting the threshold of the duration of a single press of the time domain press event search based on the instantaneous press frequency and the press harmonic component features.
2. The apparatus according to claim 1, characterized in that, When the computer program is run by the processor, it also performs the following steps: The pressing frequency is determined based on the frequency domain pressing characteristics, and feedback information on the pressing quality related to the pressing frequency is output.
3. The apparatus according to claim 2, characterized in that, When the computer program is run by the processor, it also performs the following steps: Before determining the pressing frequency based on the frequency domain pressing characteristics, it is determined whether the frequency domain pressing characteristics meet a reliability threshold. When the frequency domain pressing feature meets the reliability threshold condition, the pressing frequency is determined based on the frequency domain pressing feature.
4. The apparatus according to claim 3, characterized in that, When the computer program is run by the processor, it also performs the following steps: When the frequency domain compression feature does not meet the reliability threshold condition, the electrocardiogram signal of the target object is analyzed to obtain the electrocardiogram compression feature; Based on the ECG compression characteristics, determine whether the frequency domain compression characteristics that do not meet the reliability threshold condition are caused by compression; When it is determined that the frequency domain compression feature that does not meet the reliability threshold condition is caused by compression, the frequency domain compression feature is modified based on the ECG compression feature so that the modified frequency domain compression feature meets the reliability threshold condition, and the compression frequency is determined based on the modified frequency domain compression feature.
5. The apparatus according to claim 4, characterized in that, When the computer program is run by the processor, it also performs the following steps: When it is determined that the frequency domain pressing feature that does not meet the reliability threshold condition is not caused by pressing, the frequency domain pressing feature is deleted; and / or When it cannot be determined whether the frequency domain pressing feature that does not meet the reliability threshold condition is caused by pressing, the frequency domain pressing feature is retained, and the pressing frequency is determined based on the frequency domain pressing feature.
6. The apparatus according to claim 4, characterized in that, The ECG compression features include at least one of the following: heart rate, heart rate frequency peak amplitude, heart rate frequency band energy percentage, ECG compression frequency peak amplitude, and ECG compression frequency band peak energy percentage.
7. The apparatus according to claim 2, characterized in that, Feedback information on the quality of pressure related to the pressure frequency includes a numerical value of the pressure frequency and / or a prompt indicating the speed of pressure.
8. The apparatus according to claim 2, characterized in that, The frequency domain press feature includes an instantaneous press frequency, and the determination of the press frequency based on the frequency domain press feature, executed by the computer program when run by the processor, includes: Multiple instantaneous press frequencies are determined based on the reference signals over multiple time periods; The final pressing frequency is determined based on the multiple instantaneous pressing frequencies.
9. The apparatus according to claim 8, characterized in that, The computer program, executed by the processor, determines the final press frequency based on the plurality of instantaneous press frequencies, including: The final compression frequency is obtained by weighting the multiple instantaneous compression frequencies, using a geometric mean, or by taking the median.
10. The apparatus according to claim 1, characterized in that, When the computer program is run by the processor, it also performs the following steps: During the search for time-domain compression events based on the time-domain compression features, it is determined whether the time-domain compression event occurs at a time-domain peak or a time-domain trough based on the data characteristics of the reference signal. When it is determined that a time-domain press event occurs at a time-domain peak position, the time-domain press event search includes a time-domain press peak search; When it is determined that a time-domain press event occurs at a time-domain trough, the time-domain press event search includes a time-domain press trough search.
11. The apparatus according to claim 10, characterized in that, The data characteristics of the reference signal include the time-domain peak amplitude and / or time-domain trough amplitude of the reference signal.
12. The apparatus according to claim 1, characterized in that, When the computer program is run by the processor, it also performs the following steps: Before filtering the ECG signal based on the instantaneous compression interval, a correlation analysis is performed on the noise of the ECG signal and the reference signal, and a filtering mode is determined based on the results of the correlation analysis for use in the filtering.
13. The apparatus according to claim 1, characterized in that, When the computer program is run by the processor, it also performs the following steps: The pressing frequency is determined based on the frequency domain pressing characteristics and the time domain pressing event markers, and feedback information on pressing quality related to the pressing frequency is output.
14. The apparatus according to claim 13, characterized in that, The computer program, executed by the processor, determines the press frequency based on the frequency domain press characteristics and the time domain press event markers, including: The first instantaneous pressing frequency is determined based on the frequency domain pressing characteristics; The second instantaneous press frequency is determined based on the time-domain press event marker; Reliability analysis was performed on the first instantaneous pressing frequency and the second instantaneous pressing frequency respectively; Based on the results of the reliability analysis, the first instantaneous pressing frequency, the second instantaneous pressing frequency, or a combination of the two are used as the third instantaneous pressing frequency; The above process is repeated for the reference signals over multiple time periods to obtain multiple third instantaneous pressing frequencies; The final compression frequency is obtained by weighting the multiple third instantaneous compression frequencies, using a geometric mean, or by taking the median.
15. The apparatus according to any one of claims 1-14, characterized in that, The reference signal includes at least one of the following: chest impedance signal, blood oxygen signal, respiratory signal, and signal sensed by the cardiopulmonary resuscitation sensor, wherein the signal sensed by the cardiopulmonary resuscitation sensor includes at least one of pressure signal, displacement signal, velocity signal, and acceleration signal.
16. The apparatus according to any one of claims 1-14, characterized in that, When the computer program is run by the processor, it also performs the following steps: displaying the filtered electrocardiogram signal in real time.
17. The apparatus according to any one of claims 1-14, characterized in that, When the computer program is run by the processor, it also performs the following steps: Rhythm analysis is performed based on the filtered electrocardiogram signal; The rhythmic state during the compression process is obtained based on the results of the rhythm analysis. Based on the rhythmic state, an electric shock decision is recommended.
18. A compression detection device for cardiopulmonary resuscitation, characterized in that, The device includes a memory and a processor, the memory storing a computer program executed by the processor, the computer program performing the following steps when run by the processor: Provides a first detection mode and a second detection mode; When in the first detection mode, the compression frequency detected by the cardiopulmonary resuscitation sensor during the cardiopulmonary resuscitation of the target object is acquired and output. When in the second detection mode, a reference signal related to chest compressions during cardiopulmonary resuscitation on the target object is acquired, the reference signal is analyzed in the frequency domain to obtain the frequency domain compression characteristics, the compression frequency is determined based on the frequency domain compression characteristics, and feedback information on the compression quality related to the compression frequency is output. When the computer program is run by the processor, it further performs the following steps: providing a third detection mode, wherein in the third detection mode: acquiring a first compression frequency detected by a cardiopulmonary resuscitation sensor during cardiopulmonary resuscitation of the target object; acquiring a reference signal related to chest compressions during cardiopulmonary resuscitation of the target object, performing frequency domain analysis on the reference signal to obtain frequency domain compression features, determining a second compression frequency based on the frequency domain compression features; determining a third compression frequency based on the first compression frequency and the second compression frequency, and outputting feedback information on compression quality related to the third compression frequency; When the computer program is run by the processor, it also performs the following steps: In the second detection mode, the reference signal is analyzed in the time domain to obtain the time domain compression features; based on the frequency domain compression features and the time domain compression features, the reference signal is subjected to time domain compression detection to obtain the time domain compression event marker of the reference signal; based on the time domain compression event marker, the instantaneous compression interval is determined, and the ECG signal is filtered based on the instantaneous compression interval to obtain the filtered ECG signal; The step of performing time-domain press detection on the reference signal based on the frequency-domain press features and the time-domain press features to obtain the time-domain press event marker of the reference signal includes: performing time-domain press event search based on the time-domain press features, and optimizing and adjusting the time-domain press event search based on the frequency-domain press features to obtain the time-domain press event marker of the reference signal; The frequency domain pressing feature includes at least one of the following: instantaneous pressing frequency, the spectral amplitude corresponding to the instantaneous pressing frequency, and pressing harmonic component features; The time-domain press feature includes at least one of the following: single press duration, press amplitude, and press width; the optimization adjustment of the press event search based on the frequency-domain press feature includes at least one of the following: adjusting the threshold of the press interval of the time-domain press event search based on the instantaneous press frequency; adjusting the threshold of the press amplitude of the time-domain press event search based on the spectral amplitude corresponding to the instantaneous press frequency; adjusting the threshold of the single press duration of the time-domain press event search based on the instantaneous press frequency and the press harmonic component feature.
19. The apparatus according to claim 18, characterized in that, The computer program, executed by the processor, determines a third pressing frequency based on the first pressing frequency and the second pressing frequency, including: The third pressing frequency is obtained by weighted averaging the first pressing frequency and the second pressing frequency; or The third pressing frequency is determined by either the first pressing frequency or the second pressing frequency.
20. The apparatus according to claim 18, characterized in that, When the computer program is run by the processor, it also performs the following steps: During the search for time-domain compression events based on the time-domain compression features, it is determined whether the time-domain compression event occurs at a time-domain peak or a time-domain trough based on the data characteristics of the reference signal. When it is determined that a time-domain press event occurs at a time-domain peak position, the time-domain press event search includes a time-domain press peak search; When it is determined that a time-domain press event occurs at a time-domain trough, the time-domain press event search includes a time-domain press trough search.
21. The apparatus according to claim 18, characterized in that, When the computer program is run by the processor, it also performs the following steps: Before filtering the ECG signal based on the instantaneous compression interval, a correlation analysis is performed on the noise of the ECG signal and the reference signal, and a filtering mode is determined based on the results of the correlation analysis for use in the filtering.
22. The apparatus according to claim 18, characterized in that, Feedback information on the quality of pressure related to the pressure frequency includes a numerical value of the pressure frequency and / or a prompt indicating the speed of pressure.
23. The apparatus according to claim 18, characterized in that, The frequency domain press feature includes an instantaneous press frequency. The computer program, executed by the processor, determines the press frequency based on the frequency domain press feature, including: Multiple instantaneous press frequencies are determined based on the reference signals over multiple time periods; The final pressing frequency is determined based on the multiple instantaneous pressing frequencies.
24. The apparatus according to claim 23, characterized in that, The computer program, executed by the processor, determines the final press frequency based on the plurality of instantaneous press frequencies, including: The final compression frequency is obtained by weighting the multiple instantaneous compression frequencies, using a geometric mean, or by taking the median.
25. The apparatus according to any one of claims 18-24, characterized in that, The reference signal includes at least one of the following: chest impedance signal, blood oxygen signal, respiratory signal, and signal sensed by the cardiopulmonary resuscitation sensor, wherein the signal sensed by the cardiopulmonary resuscitation sensor includes at least one of pressure signal, displacement signal, velocity signal, and acceleration signal.
26. The apparatus according to claim 18, characterized in that, When the computer program is run by the processor, it also performs the following steps: displaying the filtered electrocardiogram signal in real time.
27. The apparatus according to claim 18, characterized in that, When the computer program is run by the processor, it also performs the following steps: Rhythm analysis is performed based on the filtered electrocardiogram signal; The rhythmic state during the compression process is obtained based on the results of the rhythm analysis. Based on the rhythmic state, an electric shock decision is recommended.
28. The pressure detection device according to claim 1 or 18, characterized in that, The compression detection device also includes a signal acquisition device, which is used to acquire reference signals related to chest compressions during cardiopulmonary resuscitation on the target object.
29. The pressure detection device according to claim 28, characterized in that, The pressure detection device is a defibrillator.
30. A storage medium, characterized in that, The storage medium stores a computer program that, when executed, performs the function of the cardiopulmonary resuscitation compression detection device as described in any one of claims 1-29.