MEWS combined early warning symptom and electrocardiogram prediction sudden cardiac arrest method
By combining electrocardiogram data based on MEWS, samples and training models are constructed to predict the occurrence of cardiac arrest in the hospital, the problem of insufficient prediction accuracy and timeliness in the existing technology is solved, and higher prediction accuracy and timeliness are achieved.
Patent Information
- Application Number
- CN202411946981.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-27
- Publication Date
- 2025-04-25
AI Technical Summary
The prior art is insufficient in predicting the occurrence of cardiac arrest in the hospital, and the early warning symptoms cannot be identified based on vital signs alone, resulting in the timeliness and accuracy of the predictions that need to be improved.
Using a combination of MEWS combined early warning symptoms and electrocardiogram, a long and short-term memory model was trained by constructing the first and second samples based on historical data, combining MEWS and electrocardiogram data to predict the risk of cardiac arrest for users.
The accuracy and timeliness of prediction of cardiac arrest are improved, especially when vital signs are stable, and the accuracy of prediction is enhanced through the diagnostic value of electrocardiogram.
Smart Images
Figure CN119889685A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of data processing suitable for management, supervision or prediction purposes, and in particular to a method for predicting cardiac arrest by combining MEWS with early warning symptoms and electrocardiogram. Background Art
[0002] In-hospital cardiac arrest (IHCA) is a serious clinical event with a high mortality rate, which puts tremendous pressure on both medical staff and patients.
[0003] Many countries have tried to establish CA warning scoring models and conduct clinical trials to predict the occurrence of IHCA. For example, the Modified Early Warning Score (MEWS) and the National Early Warning Score (NEWS). MEWS converts the dynamic changes of vital signs into visual scores. The higher the total score, the higher the probability of IHCA in the patient. The increase in the score also represents the continuous deterioration of the patient's physiological state, requiring emergency room, hospitalization or admission to the ICU (Intensive Care Unit, ICU) for treatment.
[0004] However, it is inaccurate to judge the severity of a patient's condition only from their vital signs. Before a patient suffers cardiac arrest (CA), warning symptoms often occur. Early identification of warning symptoms can predict whether the patient will suffer from CA, and timely initiation of effective intervention measures can improve the patient's prognosis. How to improve the accuracy of predicting cardiac arrest based on MEWS has become an urgent problem to be solved. Summary of the invention
[0005] The embodiments of the present application provide a method for predicting cardiac arrest by combining MEWS with warning symptoms and electrocardiogram, so as to at least partially solve the above technical problems.
[0006] The present application embodiment adopts the following technical solutions:
[0007] In a first aspect, an embodiment of the present application provides a method for predicting cardiac arrest using a MEWS combined with warning symptoms and an electrocardiogram, the method comprising:
[0008] Constructing a first sample based on historical data; the first sample includes data for characterizing the following items: blood pressure, body temperature, respiratory rate, heart rate, and state of consciousness;
[0009] Obtaining a first target classification model for predicting whether a user will suffer from cardiac arrest based on the first sample;
[0010] Constructing second samples based on the historical data; each of the second samples includes a second sample input and a second sample label corresponding to the second sample input; the second sample includes data for characterizing the following items at each moment in a preset time series: blood pressure, body temperature, respiratory rate, heart rate, state of consciousness, and electrocardiogram; the second sample label is used to characterize the moment when the user corresponding to the second sample suffers from cardiac arrest;
[0011] Using the second sample to train the preset long short-term memory model to be trained to obtain a target prediction model;
[0012] Inputting the user data to be analyzed into the first target classification model to obtain a first result, where the first result is used to characterize the probability of cardiac arrest;
[0013] Inputting the user data to be analyzed into the target prediction model to obtain a second result, where the second result is used to characterize the probability of cardiac arrest occurring at a certain moment;
[0014] When both the first result and the second result indicate that the user to which the to-be-analyzed user data belongs is at risk of cardiac arrest, the first result and the second result are used as predicted target results.
[0015] In an optional embodiment of this specification, the method further includes:
[0016] When the time at which the probability of cardiac arrest represented by the second result is greater than a preset probability threshold and the time from the current time is greater than a preset time threshold, it is determined that the second result indicates that the user is not at risk of cardiac arrest.
[0017] In an optional embodiment of this specification, the method further includes:
[0018] The duration threshold used when a warning symptom occurs within a specified historical time period is greater than the duration threshold used when the warning symptom does not occur within the specified historical time period.
[0019] In an optional embodiment of this specification, the method further includes:
[0020] The warning symptoms include at least one of the following: chest pain, dyspnea, syncope, and palpitations.
[0021] In an optional embodiment of this specification, the method further includes:
[0022] Constructing third samples based on the historical data; each of the third samples includes a third sample input and a third sample label corresponding to the third sample input;
[0023] The third sample includes data for characterizing the following items: blood pressure, body temperature, respiratory rate, heart rate, state of consciousness, and medical history; the third sample label is used to characterize whether the user corresponding to the third sample has suffered a cardiac arrest;
[0024] Using the third sample to train the preset classification model to be trained to obtain a second target classification model;
[0025] Inputting the user data to be analyzed into the second target classification model to obtain a third result, wherein the third result is used to characterize the probability of cardiac arrest;
[0026] The duration threshold when the probability represented by the third result is greater than the probability represented by the first result is greater than the duration threshold when the probability represented by the third result is not greater than the probability represented by the first result.
[0027] In an optional embodiment of this specification, the method further includes:
[0028] The past medical history includes at least one of the following: hypertension, coronary heart disease, diabetes, cerebral infarction, hyperlipidemia, and renal insufficiency.
[0029] In an optional embodiment of this specification, the method further includes:
[0030] When the first result indicates that the user is at risk of cardiac arrest, and the second result indicates that the user is not at risk of cardiac arrest, increasing the frequency of collecting the user data to be analyzed;
[0031] The prediction is continued with the user data to be analyzed obtained after the collection frequency is increased.
[0032] In an optional embodiment of this specification, the method further includes:
[0033] When the second result indicates that the user is at risk of cardiac arrest, and the first result indicates that the user is not at risk of cardiac arrest, an emergency risk alarm is triggered.
[0034] In an optional embodiment of this specification, the method further includes:
[0035] The first target classification model is a probabilistic statistical model; or,
[0036] The first target classification model is a support vector machine.
[0037] In a second aspect, an embodiment of the present application further provides a device for predicting cardiac arrest using a MEWS combined with warning symptoms and an electrocardiogram, for implementing the method steps in the first aspect.
[0038] In a third aspect, an embodiment of the present application further provides an electronic device, including:
[0039] Processor; and
[0040] A memory arranged to store computer executable instructions which, when executed, cause the processor to perform the method steps described in the first aspect.
[0041] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the method steps described in the first aspect.
[0042] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:
[0043] The method in this specification combines the user's physical signs expressed by the user's electrocardiogram on the basis of MEWS to predict the risk of cardiac arrest in the user. Since the electrocardiogram also has a high diagnostic value in predicting the occurrence of IHCA in critically ill patients, especially for patients with stable vital signs and no obvious changes, the prediction made by the method in this application has a high accuracy. In addition, the first target classification model and the target prediction model used in this specification use different training samples containing data. When the information represented by the electrocardiogram is fully expressed, it can also be combined with the information represented by the data used by MEWS to improve the accuracy and the timeliness of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0045] Figure 1 A schematic diagram of a method for predicting cardiac arrest using a combination of MEWS and warning symptoms and an electrocardiogram provided in an embodiment of this specification;
[0046] Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION
[0047] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present application better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present application are not shown or described in the specification, and this is to avoid the core part of the present application being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.
[0048] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.
[0049] The serial numbers of the components in this document, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning. The "connection" and "coupling" mentioned in this application, unless otherwise specified, include direct and indirect connections (couplings).
[0050] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0051] like Figure 1 As shown, the method of predicting cardiac arrest by combining MEWS with warning symptoms and electrocardiogram in this manual includes the following steps:
[0052] S100: Construct a first sample based on historical data.
[0053] The samples in this specification are samples that correspond to users one by one. That is, a sample is constructed based on the data collected from a certain user. There are multiple first samples in this specification. The first sample contains data used to characterize the following items: blood pressure, body temperature, respiratory rate, heart rate, and state of consciousness. Since the users targeted by the method in this specification are patients in an environment with relatively sufficient medical conditions such as a hospital, these data are available for collection.
[0054] S102: Obtaining a first target classification model for predicting whether a user will suffer from cardiac arrest based on the first sample.
[0055] Any model that can predict whether a user will suffer from cardiac arrest based on the first sample can be used as the first target classification model in this specification.
[0056] In an optional embodiment of the present specification, the first target classification model is a probabilistic statistical model.
[0057] In another optional embodiment of the present specification, the first target classification model is a support vector machine (SVM). In this case, each of the first samples includes a first sample input and a first sample label corresponding to the first sample input; the first sample label is used to characterize whether the user corresponding to the first sample has a cardiac arrest. The first target classification is obtained through supervised training.
[0058] S104: Construct a second sample based on the historical data.
[0059] The data used to construct the first sample and the second sample in this specification can come from the same data source.
[0060] Each of the second samples includes a second sample input and a second sample label corresponding to the second sample input. The second sample includes data for characterizing the following items at each moment in a preset time series: blood pressure, body temperature, respiratory rate, heart rate, state of consciousness, and electrocardiogram; the second sample label is used to characterize the moment when the user corresponding to the second sample has a cardiac arrest. The preset time series is, for example, a node with one moment per second and a sequence with time continuation.
[0061] It can be seen that the second sample in this specification has more data for characterizing the electrocardiogram than the first sample. The electrocardiogram is more distinct from data such as blood pressure. For example, the electrocardiogram can directly characterize the state of the heart, and it can be said that it has a direct relationship with the symptom of cardiac arrest. However, this is not the case with heart rate. Vigorous exercise can also cause abnormal heart rate, and emotional fluctuations can also cause abnormal heart rate, which may not necessarily be a precursor to cardiac arrest.
[0062] In the long period of time (e.g., one day, e.g., 12 hours) before the user suffers from cardiac arrest, the electrocardiogram may not necessarily show abnormalities. However, diseases such as high blood pressure may accompany the user for a long time and may also cause cardiac arrest to a certain extent, and the hidden dangers of cardiac arrest are long-term and lasting.
[0063] In addition, other data shown on the electrocardiogram may not necessarily be conveyed. For example, at the moment of sudden cardiac arrest, physical signs such as consciousness and respiratory rate may not change.
[0064] That is to say, compared with other data, the ECG may be different in the way, timing and content of information expression. Therefore, it is necessary to clarify this difference and reflect it in the prediction results. In addition, an abnormal ECG may also be a palpitation, not necessarily a precursor to cardiac arrest. Therefore, it is not possible to rely solely on the ECG to make a prediction, and other data must be referred to.
[0065] On the one hand, the method in this manual highlights the role of the electrocardiogram in prediction through differentiated sample design; on the other hand, it also fully and accurately identifies and characterizes the information of the electrocardiogram by combining the electrocardiogram with other data.
[0066] S106: Using the second sample to train the preset long short-term memory model to be trained to obtain a target prediction model.
[0067] The LSTM model is a subtype of the RNN that can learn the characteristics of temporal representation. The method in this specification uses the LSTM model to learn the characteristics of different data over time, and can also highlight the sudden information shown in the electrocardiogram, thereby making the prediction results more timely.
[0068] S108: Input the user data to be analyzed into the first target classification model to obtain a first result.
[0069] The first result in this specification is used to characterize the probability of cardiac arrest. The first result can express the risk of cardiac arrest of the user to a certain extent, but may not be able to predict the time of cardiac arrest, and thus there is a certain inaccuracy.
[0070] S110: Inputting the user data to be analyzed into the target prediction model to obtain a second result.
[0071] The second result in this specification is used to characterize the probability of cardiac arrest occurring at a certain moment.
[0072] S112: When the first result and the second result both indicate that the user to which the to-be-analyzed user data belongs is at risk of cardiac arrest, the first result and the second result are used as predicted target results.
[0073] In an optional embodiment of the present specification, a probability threshold may be set in advance (the probability threshold may be set for the first result and the second result separately, or a unified probability threshold may be set for both), and when the probability represented by the result is greater than the probability threshold, it is determined that there is a risk of cardiac arrest. The probability threshold may be an empirical value. For the second result, since it expresses the probability of cardiac arrest occurring at a certain moment, optionally, when the moment of cardiac arrest it expresses is relatively far away from now (e.g., one week, etc.), it may be considered that it expresses that cardiac arrest will not occur.
[0074] The target outcome is the final result and is used to guide the care provided to the user.
[0075] The method in this specification combines the user's physical signs expressed by the user's electrocardiogram on the basis of MEWS to predict the risk of cardiac arrest in the user. Since the electrocardiogram also has a high diagnostic value in predicting the occurrence of IHCA in critically ill patients, especially for patients with stable vital signs and no obvious changes, the prediction made by the method in this application has a high accuracy. In addition, the first target classification model and the target prediction model used in this specification use different training samples containing data. When the information represented by the electrocardiogram is fully expressed, it can also be combined with the information represented by the data used by MEWS to improve the accuracy and the timeliness of the prediction.
[0076] In an optional embodiment of the present specification, when the time from the moment when the probability of cardiac arrest represented by the second result is greater than a preset probability threshold to the current moment is greater than a preset time threshold, it is determined that the second result indicates that the user is not at risk of cardiac arrest.
[0077] In an optional embodiment of the present specification, the duration threshold may be an empirical value, obtained based on experience, such that the duration threshold used when a warning symptom occurs within a specified historical time period is greater than the duration threshold used when the warning symptom does not occur within the specified historical time period. The specified historical time period may be an empirical value, which may be positively correlated with the age of the user. The warning symptom includes at least one of the following: chest pain, dyspnea, syncope, palpitations.
[0078] In an optional embodiment of the present specification, it can also be determined by a second target classification model. In this embodiment, a third sample is constructed based on the historical data; each of the third samples includes a third sample input and a third sample label corresponding to the third sample input. The third sample includes data for characterizing the following items: blood pressure, body temperature, respiratory rate, heart rate, state of consciousness, and past history. The third sample label is used to characterize whether the user corresponding to the third sample has a cardiac arrest. The third sample is used to train a preset classification model to be trained (which can be a support vector machine) to obtain a second target classification model. The user data to be analyzed is input into the second target classification model to obtain a third result, and the third result is used to characterize the probability of cardiac arrest. The time threshold when the probability represented by the third result is greater than the probability represented by the first result is greater than the time threshold when the probability represented by the third result is not greater than the probability represented by the first result. So that the impact of past history on cardiac arrest is reflected in the target result, so as to further improve the accuracy of the target result.
[0079] The past medical history in this specification includes at least one of the following: hypertension, coronary heart disease, diabetes, cerebral infarction, hyperlipidemia, and renal insufficiency. There is no direct correlation between different diseases. For example, diabetes may not cause hypertension or cardiac arrest. The results obtained directly as the first sample or the second sample may not reflect it. However, its role in cardiac arrest cannot be ignored. This role is long-term rather than instantaneous. Therefore, it can be used to determine the duration threshold.
[0080] In an optional embodiment of the present specification, when the first result indicates that the user is at risk of cardiac arrest and the second result indicates that the user is not at risk of cardiac arrest, indicating that there is indeed a risk of cardiac arrest but the possibility of it happening now is small, the frequency of collecting the user data to be analyzed is increased; and the prediction is continued using the user data to be analyzed obtained after the collection frequency is increased.
[0081] When the second result indicates that the user is at risk of cardiac arrest, and the first result indicates that the user is not at risk of cardiac arrest, an emergency risk alarm is triggered. This indicates that cardiac arrest is highly sudden. The emergency risk alarm is used to inform the guardian that emergency measures should be taken.
[0082] If both the first result and the second result indicate that there is no risk, the user data to be analyzed continues to be collected, and the first result and the second result continue to be produced to perform analysis and judgment.
[0083] Figure 2This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.
[0084] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0085] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.
[0086] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a device for combining MEWS with warning symptoms and electrocardiogram to predict cardiac arrest at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the aforementioned methods for combining MEWS with warning symptoms and electrocardiogram to predict cardiac arrest.
[0087] The above application Figure 1The method of combining MEWS warning symptoms and electrocardiogram prediction of cardiac arrest disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in software form. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
[0088] The electronic device may also perform Figure 1 A method for predicting cardiac arrest by combining MEWS with warning symptoms and electrocardiogram, and achieving Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.
[0089] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple applications, any one of the aforementioned MEWS combined warning symptoms and electrocardiogram prediction methods for cardiac arrest is executed.
[0090] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0091] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0092] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0094] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0095] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0096] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0097] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0098] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0099] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A method for predicting cardiac arrest using MEWS combined with warning symptoms and electrocardiogram, characterized in that: The method comprises: Constructing a first sample based on historical data; the first sample includes data for characterizing the following items: blood pressure, body temperature, respiratory rate, heart rate, and state of consciousness; Obtaining a first target classification model for predicting whether a user will suffer from cardiac arrest based on the first sample; Constructing second samples based on the historical data; each of the second samples includes a second sample input and a second sample label corresponding to the second sample input; the second sample includes data for characterizing the following items at each moment in a preset time series: blood pressure, body temperature, respiratory rate, heart rate, state of consciousness, and electrocardiogram; the second sample label is used to characterize the moment when the user corresponding to the second sample suffers from cardiac arrest; Using the second sample to train the preset long short-term memory model to be trained to obtain a target prediction model; Inputting the user data to be analyzed into the first target classification model to obtain a first result, where the first result is used to characterize the probability of cardiac arrest; Inputting the user data to be analyzed into the target prediction model to obtain a second result, where the second result is used to characterize the probability of cardiac arrest occurring at a certain moment; When both the first result and the second result indicate that the user to which the to-be-analyzed user data belongs is at risk of cardiac arrest, the first result and the second result are used as predicted target results.
2. The method according to claim 1, characterized in that: The method further comprises: When the time at which the probability of cardiac arrest represented by the second result is greater than a preset probability threshold and the time from the current time is greater than a preset time threshold, it is determined that the second result indicates that the user is not at risk of cardiac arrest.
3. The method according to claim 2, characterized in that: The method further comprises: The duration threshold used when a warning symptom occurs within a specified historical time period is greater than the duration threshold used when the warning symptom does not occur within the specified historical time period.
4. The method according to claim 3, characterized in that: The method further comprises: The warning symptoms include at least one of the following: chest pain, dyspnea, syncope, and palpitations.
5. The method according to claim 2, characterized in that: The method further comprises: Constructing third samples based on the historical data; each of the third samples includes a third sample input and a third sample label corresponding to the third sample input; The third sample includes data for characterizing the following items: blood pressure, body temperature, respiratory rate, heart rate, state of consciousness, and medical history; the third sample label is used to characterize whether the user corresponding to the third sample has suffered a cardiac arrest; Using the third sample to train the preset classification model to be trained to obtain a second target classification model; Inputting the user data to be analyzed into the second target classification model to obtain a third result, wherein the third result is used to characterize the probability of cardiac arrest; The duration threshold when the probability represented by the third result is greater than the probability represented by the first result is greater than the duration threshold when the probability represented by the third result is not greater than the probability represented by the first result.
6. The method according to claim 5, characterized in that The method further comprises: The past medical history includes at least one of the following: hypertension, coronary heart disease, diabetes, cerebral infarction, hyperlipidemia, and renal insufficiency.
7. The method according to claim 1, characterized in that: The method further comprises: When the first result indicates that the user is at risk of cardiac arrest, and the second result indicates that the user is not at risk of cardiac arrest, increasing the frequency of collecting the user data to be analyzed; The prediction is continued with the user data to be analyzed obtained after the collection frequency is increased.
8. The method according to claim 1, characterized in that: The method further comprises: When the second result indicates that the user is at risk of cardiac arrest, and the first result indicates that the user is not at risk of cardiac arrest, an emergency risk alarm is triggered.
9. The method according to claim 1, characterized in that: The method further comprises: The first target classification model is a probabilistic statistical model; or, The first target classification model is a support vector machine.
10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute any one of the methods of claims 1 to 9.