Cardiopulmonary resuscitation quality evaluation method and decision making system based on cardiopulmonary brain coupling

Abstract

According to the cardiopulmonary resuscitation quality evaluation and decision-making system based on cardiopulmonary brain coupling, the physiological status of the patient is evaluated by calculating the multivariable multi-scale discrete entropy of the ECG, PetCO2 and EEG signals, the physiological status of each patient can be accurately evaluated, and corresponding pressing suggestions are provided; the individualized pressing strategy not only can help to improve the success rate of cardio-pulmonary resuscitation, but also can help to reduce complications caused by improper pressing.

Description

Technical Field

[0001] This invention belongs to the field of medical emergency technology, and in particular relates to a method and decision system for assessing the quality of cardiopulmonary resuscitation based on cardiopulmonary-brain coupling. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Cardiac arrest (CA) is the sudden cessation of the heart's normal mechanical activity, leading to the loss of the heart's pumping function and subsequently causing an interruption of blood supply to all organs of the body, resulting in severe ischemia, hypoxia, and organ failure. It is characterized by its sudden onset, high morbidity, and high mortality rate, and has become a major public health problem worldwide.

[0004] Without any intervention, the survival rate decreases by 10% for every minute of cardiac arrest. Given the severe consequences of cardiac arrest, early, high-quality cardiopulmonary resuscitation (CPR) is crucial for saving lives and reducing organ damage. CPR, through chest compressions, artificial ventilation, and defibrillation, aims to restore the heart's diastolic and systolic functions and pumping capacity, ultimately achieving recovery of spontaneous circulation (ROSC). Continuous circulatory support is a key factor in the success of CPR.

[0005] However, in practice, rescuers need to perform continuous, high-intensity chest compressions, which can easily lead to fatigue and a decrease in compression frequency and depth, thus affecting the effectiveness of CPR. Furthermore, current CPR procedures lack effective feedback mechanisms. Rescuers struggle to accurately assess the appropriateness of their resuscitation strategy and cannot adjust parameters such as compression and ventilation frequency and depth based on the patient's actual response in a timely manner. This can result in poor resuscitation outcomes or even delays in receiving optimal treatment. Therefore, real-time monitoring and evaluation of CPR quality is of paramount importance. Studies have shown that CPR quality assessment incorporating physiological parameter feedback is crucial for improving patient survival and prognosis. In traditional cardiopulmonary resuscitation (CPR), rescuers often rely on their experience to assess the patient's physiological condition, a method inherently subjective and uncertain. Physiological parameter feedback devices can monitor and provide real-time feedback on CPR-related physiological parameters, helping rescuers to more accurately perform chest compressions and ventilation during the emergency phase. Currently, clinical assessments of CPR quality use physiological indicators such as blood oxygen saturation, pulse waveform, end-expiratory carbon dioxide partial pressure, and arterial pressure. Coronary artery perfusion pressure is considered the "gold standard" for CPR quality assessment because it directly reflects the blood perfusion of the coronary arteries and is a key factor in restoring spontaneous circulation. However, monitoring coronary artery perfusion pressure is an invasive procedure requiring arterial catheterization, which is difficult to implement quickly in real-world emergency situations and increases the risk of trauma to the patient.

[0006] During cardiopulmonary resuscitation (CPR), there are complex interactions between critical organs such as the heart, lungs, and brain. Effective chest compressions require oxygen exchange through lung ventilation, and adequate oxygenation is crucial for maintaining heart and brain function. However, current physiological monitoring often focuses only on the functional status of individual organs, failing to comprehensively reflect the interactions between these critical organs and their overall functional status during CPR. This leads to numerous difficulties for physicians in assessing the patient's physiological state, making it difficult to make accurate and comprehensive judgments, lacking effective feedback and guidance on the current compression strategy, and ultimately affecting the effectiveness of CPR. Summary of the Invention

[0007] To overcome the shortcomings of the prior art, this invention provides a cardiopulmonary resuscitation quality assessment method and decision system based on cardiopulmonary-brain coupling. It uses multivariate multiscale discrete entropy calculation of ECG, PetCO2 and EEG signals to assess the patient's physiological state, and can accurately assess the physiological state of each patient.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for assessing the quality of cardiopulmonary resuscitation based on cardiopulmonary-brain coupling, comprising: Acquire electrocardiogram (ECG) signals, electroencephalogram (EEG) signals, and end-tidal carbon dioxide partial pressure (UTC) signals of individuals awaiting cardiopulmonary resuscitation (CPR). The time series signals of each channel corresponding to multiple signals are coarsely processed, and a nonlinear mapping function is used to map the signal amplitude to a predefined category; Extract the embedding vector from the mapping sequence of each channel corresponding to different signals, and combine the embedding vectors of different channels corresponding to the signals into a multivariate embedding vector. Generate a pattern string from the elements in the multivariate embedding vector, so that each embedding vector is mapped to a discrete model. Calculate the relative frequency of each discrete pattern in all embedded vectors, calculate the multivariate multiscale discrete entropy based on the calculated relative frequency of the discrete patterns, and evaluate the quality of cardiopulmonary resuscitation based on the multivariate multiscale discrete entropy.

[0009] Secondly, this invention provides a cardiopulmonary resuscitation quality assessment and decision-making system based on cardiopulmonary-brain coupling, including: The acquisition module is configured to acquire the electrocardiogram (ECG) signal, electroencephalogram (EEG) signal, and end-tidal carbon dioxide partial pressure signal of the person undergoing cardiopulmonary resuscitation. The coarse-graining module is configured to: perform coarse-graining processing on the time series signals of each channel corresponding to multiple signals, and use a nonlinear mapping function to map the signal amplitude to a predefined category; The discrete processing module is configured to: extract the embedding vector from the mapping sequence of each channel corresponding to different signals, form a multivariate embedding vector from the embedding vectors of different channels corresponding to the signals, generate a pattern string from the elements in the multivariate embedding vector, and map each embedding vector to the discrete model. The evaluation module is configured to: calculate the relative frequency of each discrete pattern in all embedded vectors, calculate the multivariate multiscale discrete entropy based on the calculated relative frequency of the discrete patterns, and evaluate the quality of cardiopulmonary resuscitation based on the multivariate multiscale discrete entropy.

[0010] Thirdly, the present invention provides an electronic device including a memory and a processor, and computer instructions stored in the memory and running on the processor, wherein the computer instructions, when executed by the processor, perform the method described in the first aspect.

[0011] Fourthly, the present invention provides a computer-readable storage medium for storing computer instructions, which, when executed by a processor, perform the method described in the first aspect.

[0012] The above one or more technical solutions have the following beneficial effects: In this invention, the complexity, dynamism, and mutual coupling of ECG, PetCO2, and EEG signals can comprehensively reflect the coordinated working state between the heart, lungs, and brain, thereby comprehensively reflecting the patient's physiological state. During cardiac arrest and cardiopulmonary resuscitation, changes in the cardiopulmonary-brain coupling state are an important manifestation of changes in the human body's physiological state. This invention uses the multivariate, multi-scale discrete entropy of ECG, PetCO2, and EEG signals to assess the patient's physiological state, accurately assessing the physiological state of each patient and providing corresponding compression suggestions. This individualized compression strategy can not only help improve the success rate of cardiopulmonary resuscitation but also help reduce complications caused by improper compression.

[0013] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0014] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0015] Figure 1 This is a schematic diagram of the relevant equipment involved in Embodiment 1 of the present invention; Figure 2 This is a flowchart of the patient physiological state assessment and pressure feedback process according to an embodiment of the present invention; Figure 3 This is a flowchart illustrating the intelligent pressure decision-making process according to an embodiment of the present invention. Figure 4 This is a flowchart of the mvMDE calculation process according to an embodiment of the present invention; Figure 5 This is a flowchart illustrating the on-site rescue process according to an embodiment of the present invention; In the diagram, 1: EEG signal acquisition electrode; 2: PetCO2 signal acquisition breathing mask; 3: ECG signal acquisition electrode; 4: Multi-channel physiological parameter monitor; 5: Cardiopulmonary resuscitation chest compression device. Detailed Implementation

[0016] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0017] It should be noted that the terminology used herein is for the purpose of describing particular implementations only and is not intended to limit the exemplary implementations of the present invention.

[0018] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0019] Example 1 This embodiment discloses a method for assessing the quality of cardiopulmonary resuscitation based on cardiopulmonary-brain coupling, including: Acquire electrocardiogram (ECG) signals, electroencephalogram (EEG) signals, and end-tidal carbon dioxide partial pressure (UTC) signals of individuals awaiting cardiopulmonary resuscitation (CPR). The time series signals of each channel corresponding to multiple signals are coarsely processed, and a nonlinear mapping function is used to map the signal amplitude to a predefined category; Extract the embedding vector from the mapping sequence of each channel corresponding to different signals, and combine the embedding vectors of different channels corresponding to the signals into a multivariate embedding vector. Generate a pattern string from the elements in the multivariate embedding vector, so that each embedding vector is mapped to a discrete model. Calculate the relative frequency of each discrete pattern in all embedded vectors, calculate the multivariate multiscale discrete entropy based on the calculated relative frequency of the discrete patterns, and evaluate the quality of cardiopulmonary resuscitation based on the multivariate multiscale discrete entropy.

[0020] This embodiment uses multivariate, multiscale discrete entropy calculations of ECG, PetCO2, and EEG signals to assess the patient's physiological state. It can accurately assess the physiological state of each patient and provide corresponding compression suggestions. This individualized compression strategy can not only help improve the success rate of cardiopulmonary resuscitation, but also help reduce complications caused by improper compression.

[0021] First, the device for implementing this embodiment will be described in detail, such as... Figure 1As shown, an integrated multi-channel physiological parameter monitor 4 was used to simultaneously acquire the patient's electrocardiogram (ECG), end-tidal carbon dioxide partial pressure (UTC), and electroencephalogram (EEG) signals. The ECG signal acquisition electrode 3 consisted of three electrodes: the right upper limb electrode (RA), the left upper limb electrode (LA), and the left lower limb electrode (LL), acquiring ECG signals at a frequency of 1000 Hz. These three electrodes formed leads I and II. Lead I, formed between LA (positive) and RA (negative), primarily reflected the heart's electrical activity in the horizontal direction. Lead II, formed between LL (positive) and RA (negative), primarily reflected the heart's electrical activity in the vertical direction. The EEG signal acquisition electrode 1 consisted of four brain electrodes: T3, T4, P3, and P4, acquiring EEG signals at a frequency of 1000 Hz. PetCO2 signal acquisition mask 2 acquires carbon dioxide signals in exhaled airflow at a frequency of 1000 Hz through the airway interface. The signal is transmitted to an infrared sensor via the airflow guide tubing. After the infrared sensor detects the absorption of carbon dioxide molecules in a specific infrared band, it is converted into an analog electrical signal. All signals are preprocessed and used to calculate the mvMDE, which is then fed back to the cardiopulmonary resuscitation chest compression device 5. The cardiopulmonary resuscitation chest compression device 5 assesses the patient's physiological state in real time based on the mvMDE and adaptively adjusts the compression strategy accordingly.

[0022] The following is combined Figures 2-4 The cardiopulmonary resuscitation quality assessment method based on cardiopulmonary-brain coupling proposed in this embodiment is described in detail below: Step 1: Acquire ECG, PetCO2, and EEG signals from the person undergoing cardiopulmonary resuscitation and preprocess them.

[0023] The system collects EEG signals at a frequency of 1000 Hz using four brain electrodes (T3, T4, P3, P4). The signals are then input through the circuit and transmitted to the amplifier via the lead connection cable. After analog amplification and filtering in the amplifier, the signals are converted from analog to digital and transmitted to the cardiopulmonary resuscitation chest compression device via a USB communication cable.

[0024] ECG signals are acquired at a frequency of 1000 Hz using three electrodes: right upper limb electrode (RA), left upper limb electrode (LA), and left lower limb electrode (LL). These three electrodes form leads I and II. Lead I, formed between LA (positive) and RA (negative), primarily reflects the heart's electrical activity in the horizontal direction. Lead II, formed between LL (positive) and RA (negative), primarily reflects the heart's electrical activity in the vertical direction. The signal is preamplified and then passed to a secondary amplifier. In the secondary amplifier, it undergoes programmable gain amplification, analog filtering, and is then converted from analog to digital before being transmitted to a cardiopulmonary resuscitation (CPR) chest compression device via a USB communication cable.

[0025] The PetCO2 signal monitoring module acquires carbon dioxide signals from exhaled airflow at 1000 Hz via the airway interface. The signal is transmitted to an infrared sensor via an airflow guide tube. After the sensor detects the absorption of carbon dioxide molecules in a specific infrared band, it converts the signal into an analog electrical signal. This signal then enters a signal conditioning circuit for amplification and filtering to remove noise interference and enhance the target signal amplitude. After analog-to-digital conversion, it becomes a digital signal and is finally transmitted to a cardiopulmonary resuscitation (CPR) chest compression device via a USB communication cable.

[0026] After being acquired by electrodes, the EEG signal is processed by a filter to remove power frequency interference, and the signal components are analyzed using an independent principal component analysis algorithm to remove interference such as electromyography, electrooculography, and motion artifacts. The ECG and PetCO2 signals are processed by filters after acquisition to remove baseline drift and high and low frequency noise.

[0027] Step 2: Calculate mvMDE based on the preprocessed ECG, PetCO2, and EEG signals; Step 21: Use the moving average coarse-grained method, one Time series of each channel Formula (1) is used to divide the time series of each channel into lengths based on time scale factors. The non-overlapping segments are analyzed, and the average value of each segment is calculated to generate a coarse-grained time series.

[0028] (1) in, This is the original time series of the k-th channel. It is the original signal length. i p represents the channel length, and p is the number of channels. It is a time scale factor. The channel length is obtained from the coarsening process.

[0029] in, Each channel refers to the synthesis of ECG, PetCO2, and EEG signals into one. Each signal occupies one channel.

[0030] Step 22: Apply the mapping function. Apply a nonlinear mapping function, such as the Normal Cumulative Distribution Function (NCDF), to the coarse-grained time series of each channel to map the signal amplitude to a predefined category, i.e., 1, 2, ..., c.

[0031] For example, the predefined categories are 1, 2, 3, 4, 5, i.e. c=5. The amplitude of a signal is converted into five integers 1, 2, 3, 4, 5. The conversion method is achieved by formula (2) and formula (3).

[0032] The mean and standard deviation of the original non-coarse-grained time series are used and kept constant throughout the mapping of all time scale factors, as shown in Equation (2): (2) in, and These are the mean and standard deviation of the original time series of the k-th channel, respectively.

[0033] Then, a linear algorithm is used to... Assigning integers from 1 to c is achieved using formula (3): (3) Step 23: Multivariate embedding vector construction. Embedding vectors are extracted from the mapping sequence of each channel, and the embedding vectors from different channels are serially concatenated to form a multivariate embedding vector. As shown in formula (4): (4) in, It is the embedded dimension. It's a time delay. It is the starting index of the embedding vector. p It refers to the number of channels.

[0034] It should be noted that each channel z obtained in formula (3) is embedded into a vector of length m and time delay d, and these vectors are connected in series to form a multivariate embedding vector, resulting in the result of formula (4).

[0035] Step 24: Discrete pattern mapping. Each embedding vector is mapped to a discrete pattern, and the pattern string is generated by combining the elements of the embedding vectors. As shown in formula (5): (5) in, Represents discrete patterns. Indicates the channel index.

[0036] Step 25: Calculate the relative frequency of each discrete mode in all embedding vectors, and access Equation (4). Z(j) The m subset has a total of The possible combinations are shown in formula (6): (6) Where # is the symbol representing the cardinality of the set. Representing discrete modes The number of discrete patterns assigned to the multivariate embedding vector Z(j) is counted. jFor example, when c=3, m=2, d=1, there are a total of Discrete modes ,like ={3,3}, then it will be mapped to In discrete mode, The mapping is performed sequentially, and the relative frequencies are calculated sequentially. .

[0037] Step 26: Calculate the mvMDE. Using the relative frequencies of the discrete modes, calculate the mvMDE of the time series X, and then divide by... Normalize to the range of 0 to 1. As shown in formula (7): (7) Step 3: Based on the calculated mvMDE, determine whether the patient's multiscale discrete entropy value under the current compression strategy is increasing compared to the previously calculated mvMDE; Step 4: If the patient's multiscale discrete entropy value continues to increase under the current compression strategy, feedback is sent to the CPR chest compression device to continue compressions until it exceeds the set value. At this point, compressions are paused, and the patient's multiscale discrete entropy value is observed to stabilize above the set value within 5 minutes. If so, compressions are continued, and steps 3-5 are repeated. If the patient's multiscale discrete entropy value does not increase under the current compression strategy, proceed to step 5. Step 5: Adjust the pressing frequency and pressing depth according to the PID adaptive controller, and repeat steps 3-5.

[0038] In step 5 of this embodiment, adjusting the pressing frequency and pressing depth according to the PID adaptive controller specifically includes: Based on the patient's current mvMDE (multivariate multiscale discrete entropy), the difference e(t) between the target entropy value and the current entropy value is calculated, as shown in formula (8): (8) in, K p For proportional gain, K i For integral gain, K d For integral gain, the initial parameters are set to .

[0039] Simultaneously, the parameters are adaptively adjusted and updated. Depth is the current pressing depth, as shown in formulas (9), (10), and (11): (9) (10) (11) The real-time adjustment amount is calculated based on the updated parameters. The adjustment amounts for pressing depth and pressing frequency are shown in formulas (12) and (13), respectively: (12) (13) Adjust the pressing strategy according to the adjustment amount, and adjust the current pressing depth and pressing frequency as shown in formula (14) and formula (15) respectively: (14) (15) Figure 5 This is a flowchart of the on-site rescue process according to an embodiment of the present invention. After discovering a patient with cardiac arrest, the first step is to determine whether defibrillation is possible. If defibrillation is possible, it is performed directly. If defibrillation is not possible, standard CPR is initiated. During CPR, the patient's EEG, PetCO2, and ECG signals are collected in real time to calculate the mvMDE and dynamically assess the patient's physiological state. The system determines whether the patient's physiological state improves during compressions and feeds this information back to the chest compression device. If so, the current compression depth and frequency are appropriate, and the current compression strategy is maintained. Otherwise, the compression strategy is adjusted to increase the mvMDE until it exceeds a set value. When it exceeds the set value, compressions are stopped, and it is observed whether the mvMDE can stabilize above the set value within 5 minutes. If the mvMDE drops below the set value after compressions are stopped, compressions should continue until it exceeds the set value, and the above steps are repeated.

[0040] This invention utilizes mvMDE, which comprehensively reflects the coordinated working state between the heart, lungs, and brain by analyzing the complexity, dynamics, and coupling relationships of ECG, PetCO2, and EEG signals, thus providing a holistic reflection of the patient's physiological state. During cardiac arrest and cardiopulmonary resuscitation (CPR), changes in the cardiopulmonary-brain coupling state are crucial indicators of changes in the body's physiological state. mvMDE is highly sensitive to these changes under different physiological conditions, and therefore can be used to assess the patient's physiological state, provide quantitative indicators of CPR quality, determine whether the patient has regained spontaneous circulation, and guide compression strategies. mvMDE also enables individualized compressions. By monitoring the patient's physiological state in real time and analyzing their cardiopulmonary-brain coupling, it can accurately assess each patient's physiological state and provide corresponding compression suggestions. This individualized compression strategy not only improves the success rate of CPR but also reduces complications caused by improper compressions.

[0041] Example 2 The purpose of this embodiment is to provide a cardiopulmonary resuscitation quality assessment and decision-making system based on cardiopulmonary-brain coupling, including: The acquisition module is configured to acquire the electrocardiogram (ECG) signal, electroencephalogram (EEG) signal, and end-tidal carbon dioxide partial pressure signal of the person undergoing cardiopulmonary resuscitation. The coarse-graining module is configured to: perform coarse-graining processing on the time series signals of each channel corresponding to multiple signals, and use a nonlinear mapping function to map the signal amplitude to a predefined category; The discrete processing module is configured to: extract the embedding vector from the mapping sequence of each channel corresponding to different signals, form a multivariate embedding vector from the embedding vectors of different channels corresponding to the signals, generate a pattern string from the elements in the multivariate embedding vector, and map each embedding vector to the discrete model. The evaluation module is configured to: calculate the relative frequency of each discrete pattern in all embedded vectors, calculate the multivariate multiscale discrete entropy based on the calculated relative frequency of the discrete patterns, and evaluate the quality of cardiopulmonary resuscitation based on the multivariate multiscale discrete entropy.

[0042] In further embodiments, the following is also provided: An electronic device includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor. When executed by the processor, the computer instructions perform the method described in Embodiment 1. For brevity, further details are omitted here.

[0043] It should be understood that in this embodiment, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0044] Memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of memory may also include non-volatile random access memory. For example, memory may also store information about the device type.

[0045] A computer-readable storage medium for storing computer instructions, which, when executed by a processor, perform the method described in Embodiment 1.

[0046] The method in Embodiment 1 can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor. The software modules can reside in readily available storage media in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not provided here.

[0047] A computer program product includes a computer program that, when executed by a processor, implements the method described in Embodiment 1.

[0048] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, which execute in a device on a target real or virtual processor to perform the processes / methods described above. Typically, program modules include routines, programs, libraries, objects, classes, components, data structures, etc., that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of program modules can be combined or divided among program modules as needed. The machine-executable instructions for the program modules can execute within a local or distributed device. In a distributed device, the program modules can reside in both local and remote storage media.

[0049] The computer program code used to implement the methods of the present invention may be written in one or more programming languages. This computer program code may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the computer or other programmable data processing device, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a computer, partially on a computer, as a stand-alone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0050] In the context of this invention, computer program code or related data may be carried by any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and the like. Examples of signals may include electrical, optical, radio, sound, or other forms of propagation signals, such as carrier waves, infrared signals, etc.

[0051] Those skilled in the art will recognize that the units and algorithm steps described in conjunction with the embodiments 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.

[0052] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for assessing the quality of cardiopulmonary resuscitation based on cardiopulmonary-brain coupling, characterized in that, include: Acquire electrocardiogram (ECG) signals, electroencephalogram (EEG) signals, and end-tidal carbon dioxide partial pressure (UTC) signals of individuals awaiting cardiopulmonary resuscitation (CPR). The time series signals of each channel corresponding to multiple signals are coarsely processed, and a nonlinear mapping function is used to map the signal amplitude to a predefined category; Extract the embedding vector from the mapping sequence of each channel corresponding to different signals, and combine the embedding vectors of different channels corresponding to the signals into a multivariate embedding vector. Generate a pattern string from the elements in the multivariate embedding vector, so that each embedding vector is mapped to a discrete model. Calculate the relative frequency of each discrete pattern in all embedded vectors, calculate the multivariate multiscale discrete entropy based on the calculated relative frequency of the discrete patterns, and evaluate the quality of cardiopulmonary resuscitation based on the multivariate multiscale discrete entropy.

2. The cardiopulmonary resuscitation quality assessment method based on cardiopulmonary-brain coupling as described in claim 1, characterized in that, The time series of each channel is divided into non-overlapping segments with a length equal to the time scale factor. The average value of each segment is calculated to obtain the coarse-grained result of the time series signal of each channel.

3. The cardiopulmonary resuscitation quality assessment method based on cardiopulmonary-brain coupling as described in claim 1, characterized in that, A nonlinear mapping function is used to map the signal amplitude to a predefined category, specifically as follows: ； ； in, and and are the mean and standard deviation of the original time series of the k-th channel, respectively; c is an integer.

4. The cardiopulmonary resuscitation quality assessment method based on cardiopulmonary-brain coupling as described in claim 1, characterized in that, Calculate the relative frequency of each discrete mode across all embedding vectors, specifically: ； Where # is the symbol representing the cardinality of the set. Representing discrete modes Assigned to multivariate embedding vectors Z(j) quantity ； The channel length is obtained from the coarsening process. It is the embedded dimension; Indicates the number of possible combinations. It's a time delay.

5. The cardiopulmonary resuscitation quality assessment method based on cardiopulmonary-brain coupling as described in claim 1, characterized in that, The multivariable, multiscale discrete entropy is calculated based on the relative frequencies of the calculated discrete modes, specifically as follows: ； in, It is the embedded dimension. It represents the time delay, c is the number of predefined categories; X represents the time series. Indicates relative frequency.

6. The cardiopulmonary resuscitation quality assessment method based on cardiopulmonary-brain coupling as described in claim 1, characterized in that, The quality of cardiopulmonary resuscitation is assessed based on the aforementioned multivariate, multiscale discrete entropy, specifically as follows: If the multivariate multiscale discrete entropy calculated by the CPR person under the current compression strategy is not greater than the multivariate multiscale discrete entropy calculated previously, then adjust the compression frequency and compression depth. If the multivariate multiscale discrete entropy calculated by the CPR person under the current compression strategy is greater than the multivariate multiscale discrete entropy calculated previously, then the current compression strategy should be maintained.

7. The cardiopulmonary resuscitation quality assessment method based on cardiopulmonary-brain coupling as described in any one of claims 6, characterized in that, The pressing frequency and pressing depth are adjusted by a PID adaptive controller.

8. A cardiopulmonary resuscitation quality assessment and decision-making system based on cardiopulmonary-brain coupling, characterized in that, include: The acquisition module is configured to acquire the electrocardiogram (ECG) signal, electroencephalogram (EEG) signal, and end-tidal carbon dioxide partial pressure signal of the person undergoing cardiopulmonary resuscitation. The coarse-graining module is configured to: perform coarse-graining processing on the time series signals of each channel corresponding to multiple signals, and use a nonlinear mapping function to map the signal amplitude to a predefined category; The discrete processing module is configured to: extract the embedding vector from the mapping sequence of each channel corresponding to different signals, combine the embedding vectors of different channels corresponding to the signals into a multivariate embedding vector, generate a pattern string from the elements in the multivariate embedding vector, and map each embedding vector to the discrete model. The evaluation module is configured to: calculate the relative frequency of each discrete pattern in all embedded vectors, calculate the multivariate multiscale discrete entropy based on the calculated relative frequency of the discrete patterns, and evaluate the quality of cardiopulmonary resuscitation based on the multivariate multiscale discrete entropy.

9. An electronic device, characterized in that, It includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, which, when executed by the processor, perform the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, Used to store computer instructions, which, when executed by a processor, perform the method described in any one of claims 1-7.

Images