Sudden cardiac arrest early warning device, equipment, storage medium and system

Through the cardiac arrest warning device, the CatBoost model is used to predict cardiac arrest and trigger response measures, solving the existing technology of central cardiac arrest warning and timely response problems, significantly improving the success rate of resuscitation and survival rate.

CN119069073APending Publication Date: 2024-12-03SUZHOU SENSUS MEDICAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411132158.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The prior art is difficult to effectively warn and respond to cardiac arrest in a timely manner, resulting in low resuscitation success rate and insufficient survival rate, especially in out-of-hospital and non-medical settings.

Method used

A cardiac arrest warning device was designed to obtain multiple medical data through the data acquisition device, such as blood flow peak velocity, blood flow velocity time integral, heart rate and shock index, and iterative training was used to predict the early warning of cardiac arrest. Category, and perform information interaction according to early warning categories, triggering response measures from hospitals or public emergency systems.

Benefits of technology

It improves the accuracy and timeliness of cardiac arrest prediction, enhances the treatment opportunities of target users, and significantly improves the recovery success rate and survival rate in out-of-hospital and non-medical settings.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119069073A_ABST
    Figure CN119069073A_ABST
Patent Text Reader

Abstract

The invention relates to a sudden cardiac arrest early warning device, equipment, a storage medium and a system, and belongs to the field of medical instruments. The cardiac arrest early warning device comprises an acquisition module used for acquiring first type medical data of a target user; the first type of medical data is a plurality of medical data related to cardiac arrest; the training module is used for inputting the acquired first type of medical data into a preset classification model and acquiring an early warning category for the cardiac arrest prediction condition of the target user through preset iterative training; and the interaction module is used for executing external information interaction according to the obtained early warning category. According to the technical scheme provided by the embodiment of the invention, the target user can be treated in time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of medical devices, and in particular to a cardiac arrest warning device, equipment, storage medium and system. Background Art

[0002] Cardiac arrest refers to the sudden cessation of the heart's ejection function, the disappearance of large artery pulsation and heart sounds, and severe ischemia and hypoxia of important organs (such as the brain), which ultimately leads to the end of life. The most common cause of cardiac arrest is ventricular fibrillation. If the patient does not respond to calling and does not respond to pressure above or below the orbital cavity, it can be determined that the patient is in a coma. Then pay attention to observe whether the patient's chest and abdomen have ups and downs and respiratory movements. If there is no pulsation when touching the carotid artery and femoral artery, and no heartbeat can be heard in the precordial area, it can be determined that the patient is in cardiac arrest.

[0003] The clinical course of cardiac arrest or sudden cardiac death can be divided into four periods: prodromal period, onset period, cardiac arrest period and death period.

[0004] 1. Prodromal stage

[0005] Many patients experience prodromal symptoms for days, weeks, or even months before cardiac arrest, such as worsening angina, shortness of breath, or palpitations, fatigue, and other non-specific complaints. These prodromal symptoms are not unique to sudden cardiac death, but are common before any heart attack. Data show that 50% of people who suffer sudden cardiac death have sought medical attention within a month before their sudden death, but their complaints are not necessarily related to the heart. Among survivors of cardiac arrest outside the hospital, 28% experienced worsening angina or shortness of breath before cardiac arrest. However, prodromal symptoms only indicate the risk of cardiovascular disease, but cannot identify subgroups that suffer sudden cardiac death.

[0006] 2. Onset period

[0007] That is, the period of acute cardiovascular changes before cardiac arrest usually does not exceed 1 hour. Typical manifestations include: prolonged angina pectoris or chest pain of acute myocardial infarction, acute dyspnea, sudden palpitations, continuous tachycardia, dizziness, etc. If cardiac arrest occurs instantly without any warning beforehand, 95% of them are cardiac in origin and have coronary artery disease. From the continuous electrocardiogram records obtained from patients with sudden cardiac death, it can be seen that there are often changes in cardiac electrical activity within a few hours or minutes before sudden death, among which the most common are increased heart rate and deterioration of ventricular premature beats. Those who die suddenly from ventricular fibrillation often have a continuous or non-continuous ventricular tachycardia first. Most electrocardiogram abnormalities are ventricular fibrillation. Some other patients develop circulatory failure and are in an inactive state or even comatose before cardiac arrest, and their onset period is long. Non-cardiac diseases often exist before cardiovascular changes at the end of life. Electrocardiogram abnormalities are more common in ventricular arrest than in ventricular fibrillation.

[0008] 3. Cardiac arrest

[0009] This stage is characterized by complete loss of consciousness. If not treated immediately, the patient will generally enter the death stage within a few minutes. Spontaneous reversal is rare.

[0010] Cardiac arrest is a sign of clinical death, and its symptoms and signs are as follows: ① Heart sounds disappear; ② Pulse cannot be felt and blood pressure cannot be measured; ③ Sudden loss of consciousness or accompanied by brief convulsions, which are often systemic and often occur within 10 seconds after cardiac arrest, sometimes accompanied by eye deviation; ④ Intermittent breathing, sighing, and then stopping. It often occurs within 20 to 30 seconds after cardiac arrest; ⑤ Coma, which often occurs 30 seconds after cardiac arrest; ⑥ Dilated pupils, which often appear 30 to 60 seconds after cardiac arrest. However, biological death has not yet occurred at this stage. If timely and appropriate rescue is given, resuscitation is possible.

[0011] 4. Biological death

[0012] The evolution of cardiac arrest to biological death mainly depends on the type of cardiac electrical activity and the timeliness of cardiac resuscitation. If cardiopulmonary resuscitation is not performed within 4 to 6 minutes in ventricular fibrillation or ventricular arrest, the prognosis is very poor. If cardiopulmonary resuscitation is not performed within 8 minutes, there is almost no chance of survival unless in special circumstances such as hypothermia. Summary of the invention

[0013] In view of this, the present application provides a cardiac arrest warning device, equipment, storage medium and system to solve at least one problem existing in the background technology.

[0014] To achieve the above purpose, the technical solution of this application is implemented as follows:

[0015] In a first aspect, an embodiment of the present application provides a cardiac arrest warning device, which is applied to a medical warning system, characterized in that the medical warning system comprises: a data acquisition device, the cardiac arrest warning device, a hospital interaction device, a public emergency interaction device and a networking device; the cardiac arrest warning device comprises:

[0016] An acquisition module, used for acquiring a first type of medical data of a target user; the first type of medical data is a plurality of medical data related to cardiac arrest;

[0017] A training module, used to input the acquired first type of medical data into a preset classification model, and obtain a warning category for a target user's cardiac arrest prediction situation through preset iterative training;

[0018] The interaction module is used to perform external information interaction according to the acquired warning category.

[0019] Optionally, the acquisition module is specifically used for:

[0020] Obtain the target user's blood flow peak velocity VPK, blood flow velocity time integral VTI, heart rate HR and shock index DSIvti.

[0021] Optionally, the training module is further used to:

[0022] In each iterative training, a first result of the prediction function and a second result of the loss function of the classification model are obtained;

[0023] The classification model is updated according to the first result and the second result to enter the next round of iteration.

[0024] Optionally, the classification model is a CatBoost model, and the training module is further used for:

[0025] Constructing a feature vector of a sample according to the first type of medical data and the CatBoost model;

[0026] The feature vector is input into the classification model to obtain the probability of each warning category.

[0027] Optionally, the training module is further used to obtain a second result of the loss function according to the following expression:

[0028]

[0029] Wherein: I(yi=c) is an indicator function, if y is equal to category c, the function result is 1, otherwise it is 0, and M is the total number of categories. 6. The cardiac arrest warning device according to claim 4, characterized in that the training module is also used to: update the classification model according to the following expression:

[0030] F m (x i )=F m-1 (x i )+ηh t (x i )

[0031] Wherein, Fm is the model after the mth round of iteration, η is the learning rate, and ht is the prediction result of the tth tree.

[0032] Optionally, the training module is further used to obtain the value of ht according to the following expression:

[0033]

[0034] Where: Jt is the number of leaf nodes in the tth tree, w tj is the weight of the jth leaf node of the tth tree, R tj is the feature space region of the jth leaf node of the tth tree, I(x∈Rtj ) is the indicator function. If x belongs to the feature space region R tj 1 if the value is true, 0 otherwise.

[0035] Optionally, the interaction module is further used for:

[0036] If the obtained warning category is the first category, sending a prompt message;

[0037] If the acquired warning category is the second category, pushing the first type of medical data of the target user to a preset hospital interaction device;

[0038] If the obtained warning category is the third category, the first type of medical data of the target user is pushed to a preset hospital interaction device and an alert is issued;

[0039] If the acquired warning category is the fourth category, the public emergency interaction device and / or the target user is contacted to provide emergency treatment to the target user through the public emergency system.

[0040] Optionally, the data acquisition device is a Doppler blood flow meter, and the acquisition module is further used for:

[0041] Acquiring blood flow dynamics data of the target user's carotid artery through the Doppler blood flow meter;

[0042] The first type of medical data is acquired according to the hemodynamic data.

[0043] In a second aspect, an embodiment of the present application provides a computing device, which is applied to a medical early warning system, wherein the medical early warning system includes: a data acquisition device, a cardiac arrest early warning device, a networking device, a hospital interaction device, and a public emergency interaction device; the computing device includes: a storage component, a communication bus, and a processing component, wherein:

[0044] The storage component is used to store the operating program of the cardiac arrest warning device;

[0045] The communication bus is used to realize the connection and communication between the storage component and the processing component;

[0046] The processing component is used to execute the operating program of the cardiac arrest warning device to achieve the following steps:

[0047] Acquire a first type of medical data of a target user; the first type of medical data is a plurality of medical data related to cardiac arrest;

[0048] Inputting the acquired first type of medical data into a preset classification model, and performing preset iterative training to obtain a warning category representing the probability of cardiac arrest of the target user;

[0049] According to the obtained warning category, external information interaction is performed.

[0050] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, which is applied to a medical early warning system, wherein the medical early warning system includes: a data acquisition device, a cardiac arrest early warning device, a networking device, a hospital interaction device, and a public emergency interaction device; an executable program is stored on the computer-readable storage medium, and when the executable program is executed by a processor, the following steps are implemented:

[0051] Acquire a first type of medical data of a target user; the first type of medical data is a plurality of medical data related to cardiac arrest;

[0052] Inputting the acquired first type of medical data into a preset classification model, and performing preset iterative training to obtain a warning category representing the probability of cardiac arrest of the target user;

[0053] According to the obtained warning category, external information interaction is performed.

[0054] In a fourth aspect, an embodiment of the present application provides a medical early warning system, including:

[0055] A data collection device, used for collecting a first type of medical data of a target user;

[0056] The cardiac arrest warning device described above;

[0057] A hospital interaction device, used for receiving data and warnings sent by the cardiac arrest warning device, and analyzing the data;

[0058] A public emergency response interactive device, used to receive the contact information sent by the cardiac arrest warning device to arrange emergency response tasks;

[0059] A networking device is used to connect the cardiac arrest warning device, the hospital interaction device and the public emergency interaction device for communication via the Internet.

[0060] The cardiac arrest warning device, equipment, storage medium and system provided in the embodiment of the present application include: an acquisition module for acquiring a first type of medical data of a target user; the first type of medical data is a plurality of medical data related to cardiac arrest; a training module for inputting the acquired first type of medical data into a preset classification model, and obtaining a warning category for the target user's cardiac arrest prediction situation through preset iterative training; an interaction module for performing external information interaction according to the acquired warning category. It can be seen that the cardiac arrest warning device, equipment, storage medium and system provided in the embodiment of the present application acquire the first type of medical data related to cardiac arrest, input the preset classification model, and perform iterative training, so as to obtain a more accurate warning category for the target user's cardiac arrest prediction situation, and perform external information interaction according to the warning category, so that the target user can receive timely treatment. Therefore, the cardiac arrest warning device, equipment, storage medium and system provided in the embodiment of the present application can obtain a more accurate warning category for the target user's cardiac arrest prediction situation, so that the target user can receive timely treatment.

[0061] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] 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:

[0063] Figure 1 A schematic diagram of the structure of a cardiac arrest warning device provided in an embodiment of the present application;

[0064] Figure 2 A schematic diagram of the structure of the t-th tree in the cardiac arrest warning device provided in an embodiment of the present application;

[0065] Figure 3 A schematic diagram of the process flow of the cardiac arrest warning device according to the embodiment of the present application;

[0066] Figure 4 A detailed flowchart of the execution process of the cardiac arrest warning device provided in the embodiment of the present application;

[0067] Figure 5 A schematic diagram of the structure of a computing device provided in an embodiment of the present application;

[0068] Figure 6 Schematic diagram of the medical warning system provided in the embodiment of the present application Figure 1 ;

[0069] Figure 7 Schematic diagram of the medical warning system provided in the embodiment of the present application Figure 2 ;

[0070] Figure 8 A schematic diagram of the structure of a data acquisition device in a medical early warning system provided in an embodiment of the present application.

[0071] Description of reference numerals:

[0072] 100. Cardiac arrest warning device; 101. Acquisition module; 102. Training module; 103. Interaction module; 500. Computing device; 501. Storage component; 502. Communication bus; 503. Processing component; 504. Input device; 505. Output device; 506. External communication interface; 601. Data acquisition device; 602. Networking device; 603. Hospital interaction device; 604. Public emergency interaction device. DETAILED DESCRIPTION

[0073] The exemplary embodiments disclosed in the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the specific embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope disclosed in the present application to those skilled in the art.

[0074] In the following description, a large number of specific details are given in order to provide a more thorough understanding of the present application. However, it is obvious to those skilled in the art that the present application can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present application, some technical features well known in the art are not described; that is, all features of the actual embodiments are not described here, and well-known functions and structures are not described in detail.

[0075] In order to thoroughly understand the present application, detailed steps and detailed structures will be presented in the following description to illustrate the technical solution of the present application. The preferred embodiments of the present application are described in detail below, but in addition to these detailed descriptions, the present application may also have other implementation methods.

[0076] The inventors of this application discovered during research and development, for example, by summarizing various cases and understanding medical information from various countries:

[0077] The success rate of resuscitation of cardiac arrest depends on: ① the time when resuscitation begins; ② the place where the cardiac arrest occurs; ③ the type of cardiac electrical activity disorder (ventricular fibrillation, ventricular tachycardia, electromechanical dissociation, ventricular standstill); ④ the clinical condition of the patient before the cardiac arrest. If the cardiac arrest occurs in a place where cardiopulmonary resuscitation can be performed immediately, the success rate of resuscitation is higher.

[0078] Under the condition that emergency treatment can be immediately performed in a hospital or intensive care unit, the success rate of resuscitation depends mainly on the patient's clinical condition before cardiac arrest: if it is an acute cardiac condition or a temporary metabolic disorder, the prognosis is better; if it is a chronic heart disease in the late stage or a serious non-cardiac condition (such as renal failure, pneumonia, sepsis, diabetes or cancer), the success rate of resuscitation is not higher than that of cardiac arrest occurring outside the hospital. The success rate of the latter depends mainly on the type of cardiac electrical activity during cardiac arrest, among which ventricular tachycardia has the best prognosis (success rate of 67%), followed by ventricular fibrillation (25%), and ventricular arrest and electromechanical dissociation have a very poor prognosis. Advanced age is also an important factor affecting the success of resuscitation.

[0079] According to statistics, immediate cardiopulmonary resuscitation and early defibrillation by witnesses are the key to avoiding biological death. The most common cause of death in hospital after cardiac resuscitation is damage to the central nervous system. Hypoxic brain damage and infection secondary to long-term use of ventilators account for 60% of the causes of death, low cardiac output accounts for 30% of the causes of death, and deaths due to recurrence of arrhythmias account for only 10%. The prognosis of cardiac arrest complicated by acute myocardial infarction depends on whether it is primary or secondary: in the former, there is no hemodynamic instability when cardiac arrest occurs; while in the latter, it is secondary to an unstable hemodynamic state. Therefore, if primary cardiac arrest can be resuscitated immediately, the success rate can reach 100%; while the prognosis of secondary cardiac arrest is poor, and the success rate of resuscitation is only about 30%.

[0080] A study involving 835 out-of-hospital cardiac arrest patients was published in the United States in 2015. The patients were aged 35 to 65 years old. 51% of them had suspicious symptoms one month before the cardiac arrest, including chest pain, chest pressure, palpitations, shortness of breath and abnormal heart rhythm. Among the symptomatic patients, 93% of them had symptoms again 24 hours before the onset of cardiac arrest. After the onset of symptoms, only 19% of the patients called the emergency service system. The survival rate of cardiac arrest patients who called for help was 32%, and the survival rate of patients who did not seek emergency services was only 6%.

[0081] Based on the above research results, the inventors obtained the following technical solution after further research and development.

[0082] Embodiment 1

[0083] The present application embodiment provides a cardiac arrest warning device 100, which is applied to a medical warning system, wherein the medical warning system comprises: a data acquisition device, the cardiac arrest warning device, a hospital interaction device, a public emergency interaction device, and a networking device; Figure 1 , the cardiac arrest warning device 100 comprises:

[0084] An acquisition module 101 is used to acquire a first type of medical data of a target user; the first type of medical data is a plurality of medical data related to cardiac arrest;

[0085] The training module 102 is used to input the acquired first type of medical data into a preset classification model, and obtain a warning category for the prediction of cardiac arrest of a target user through preset iterative training;

[0086] The interaction module 103 is used to perform external information interaction according to the acquired warning category.

[0087] It is understandable that the data acquisition device can be a monitoring device, a Doppler blood flow meter or a watch with monitoring function, etc. The hospital interactive device and the public emergency interactive device can be a terminal such as a computer, which can receive, process and forward the corresponding information, such as forwarding the information to a doctor, an ambulance, etc.

[0088] In the training module 102, it is understandable that there are many factors that affect cardiac arrest, and each factor affects each other, so it is impossible to predict cardiac arrest based on the situation of a single factor, and it is also impossible to manually give a fixed range of multiple factors as a basis for prediction. Therefore, the inventors use a method of building a data model to combine multiple medical data related to cardiac arrest for prediction.

[0089] In the acquisition module 101, it can be understood that the warning category of the target user's cardiac arrest prediction situation is obtained through a data model, that is, a classification model. Therefore, if the data processing capacity is sufficient, the types of the first type of medical data can be more, and the data type is not limited here.

[0090] External information interaction may include interaction with official medical networks, hospitals, the target user himself or the target user’s emergency contacts, etc., without limitation.

[0091] The cardiac arrest warning device 100, equipment, storage medium and system provided in the embodiment of the present application obtain the first type of medical data related to cardiac arrest, input the preset classification model, and perform iterative training, so as to obtain a more accurate warning category for the target user's cardiac arrest prediction situation, and perform external information interaction based on the warning category, so that the target user can receive timely treatment.

[0092] In some other embodiments of the present application, the acquisition module 101 is specifically used for:

[0093] Obtain the target user's blood flow peak velocity VPK, blood flow velocity time integral VTI, heart rate HR and shock index DSIvti.

[0094] After a long period of research and development and summary, the inventor concluded that the use of the above four medical data can not only accurately predict cardiac arrest, but also reduce the processing load of the computer, collect data from more users, or promote the miniaturization of servers and reduce costs.

[0095] In some other embodiments of the present application, the training module 102 is further used for:

[0096] In each iterative training, a first result of the prediction function and a second result of the loss function of the classification model are obtained;

[0097] The classification model is updated according to the first result and the second result to enter the next round of iteration.

[0098] During training, the loss function is used to:

[0099] Calculate the prediction error of the current model: For each sample, use the loss function to calculate the difference between the predicted probability and the true label.

[0100] Calculate gradients: Based on the loss function, calculate the gradient of each tree node split, which will guide how to adjust the tree splitting rule.

[0101] Update the weight of the tree: Use the gradient descent method to update the weight of the tree and reduce the loss function value.

[0102] That is, the second result includes the weight of the updated tree, so that the accuracy of the classification model can be gradually improved through the gradual correction of the loss function.

[0103] In some other embodiments of the present application, the classification model is a CatBoost model, and the training module 102 is further used for:

[0104] Constructing a feature vector of a sample according to the first type of medical data and the CatBoost model;

[0105] The feature vector is input into the classification model to obtain the probability of each warning category.

[0106] Suppose we have the following data and model parameters:

[0107] X: Feature matrix of ultrasonic blood flow data, including VPK (blood flow velocity), VTI (velocity time integral), HR (heart rate), DSIvti (shock index), etc.

[0108] T: The number of decision trees used in the CatBoost model.

[0109] F(x): The final prediction function of the CatBoost model.

[0110] Therefore, for each sample i, the feature vector can be expressed as:

[0111] x i =[VPK i , VTI i , HR i ,DSIvti i ] (1)

[0112] The prediction function F(x) of the CatBoost model can be based on the feature vector x i Give the probability of each warning type:

[0113]

[0114] The number of decision trees T can use the default value of 1000. Based on the particularity of this classification model, it can also be less than 1000, such as 500.

[0115] In some other embodiments of the present application, the training module 102 is further used to obtain a second result of the loss function according to the following expression:

[0116]

[0117] Wherein: I(yi=c) is an indicator function, if y is equal to category c, the function result is 1, otherwise it is 0, and M is the total number of categories.

[0118] It can be understood that the above expression (3) measures the difference between the model prediction and the true label through the cross entropy loss function.

[0119] In some other embodiments of the present application, the training module 102 is further used to update the classification model according to the following expression:

[0120] F m (x i )=F m-1 (x i )+ηh t (x i ) (4)

[0121] Wherein, Fm is the model after the mth round of iteration, η is the learning rate, and ht is the prediction result of the tth tree.

[0122] Among them, the tth tree is a new decision tree added. The new decision tree is trained based on the current prediction error, that is, the new decision tree is trained according to the loss function.

[0123] In some other embodiments of the present application, the training module 102 is further used to obtain the value of ht according to the following expression:

[0124]

[0125] Where: Jt is the number of leaf nodes in the tth tree, w tj is the weight of the jth leaf node of the tth tree, R tj is the feature space region of the jth leaf node of the tth tree, I(x∈R tj ) is the indicator function. If x belongs to the feature space region R tj 1 if the value is true, 0 otherwise.

[0126] Among them, training a new decision tree according to the loss function is to update w through the loss function tj achieved.

[0127] In some other embodiments of the present application, the interaction module is further used to:

[0128] If the obtained warning category is the first category, sending a prompt message;

[0129] If the acquired warning category is the second category, pushing the first type of medical data of the target user to a preset hospital interaction device;

[0130] If the obtained warning category is the third category, the first type of medical data of the target user is pushed to a preset hospital interaction device and an alert is issued;

[0131] If the acquired warning category is the fourth category, the public emergency interaction device and / or the target user is contacted to provide emergency treatment to the target user through the public emergency system.

[0132] It can be understood that each category of the warning category is related to the probability of cardiac arrest. For example, the probability of the first category is very low, and only a prompt message needs to be sent, such as asking the target user to pay a little attention. The probability of the second category is slightly higher, and it needs to be sent to the hospital, for example, for the doctor to judge. The probability of the third category is a bit high, not only is it sent to the hospital, but it also needs to be warned. The probability of the fourth category is very high, so it is very urgent, and it is necessary to contact the public emergency interaction device, such as 120 ambulance, for emergency treatment.

[0133] In some other embodiments of the present application, the data acquisition device is a Doppler blood flow meter, and the acquisition module 101 is further used for:

[0134] Acquiring blood flow dynamics data of the target user's carotid artery through the Doppler blood flow meter;

[0135] The first type of medical data is acquired according to the hemodynamic data.

[0136] The Doppler blood flow meter can obtain the above-mentioned VPK, VTI, HR, DSIvti and other data by acquiring the hemodynamic data of the target user's carotid artery. It can collect data non-invasively and for a long time, and is more accurate than smart watches.

[0137] In order to more clearly understand the cardiac arrest warning device 100 provided in the embodiment of the present application, a simple example is given below to illustrate.

[0138] Suppose there are 4 sample data:

[0139] Sample 1: VPK: 40cm / s; VTI: 18cm; HR: 75bpm; DSIvti: 8 Warning type: Prompt A;

[0140] Sample 2: VPK: 55cm / s; VTI: 22cm; HR: 80bpm; DSIvti: 10 Warning type: Warning B;

[0141] Sample 3: VPK: 35cm / s; VTI: 14cm; HR: 70bpm; DSIvti: 6 Warning type: Alarm C;

[0142] Sample 4: VPK: 50cm / s; VTI: 20cm; HR: 85bpm; DSIvti: 9 Warning type: SOS D.

[0143] The above-mentioned A, B, C, and D may correspond to the above-mentioned first category, second category, third category, and fourth category.

[0144] For each sample, the feature vector can be expressed as:

[0145] X1 = [40, 18, 75, 8];

[0146] X2 = [55, 22, 80, 10];

[0147] X3 = [35, 14, 70, 6];

[0148] X4 = [50, 20, 85, 9];

[0149] Then initialize the model and set the model parameters. Generally, they can be set as usual. For example, the learning rate η can be 0.1, and the other parameters are also the same. We will not elaborate on them here.

[0150] Each tree can give a prediction value based on the feature vector, see expression (5).

[0151] For greater clarity, the hypothetical structure diagram of the t-th tree is given below, and further introduced in conjunction with the hypothetical structure diagram:

[0152] See also Figure 2, assuming that the tth tree has two leaf nodes, the weights of the leaf nodes may be as follows:

[0153] Wt1 = 1.2 (corresponding to low blood flow velocity);

[0154] Wt2 = 0.5 (corresponding to high blood flow velocity);

[0155] Prediction calculation:

[0156] For sample 1 (x1), the blood flow velocity VPK is 40, so it belongs to the region Rt1 of leaf node 1. The indicator function I(x1∈R t1 )=1, that is, VPK<50. Similarly, for sample 2, the indicator function is 0 for leaf node 2, because VPK40 does not meet the condition of ≥50.

[0157] Therefore, ht's prediction for sample 1 is:

[0158] Ht(X1)=Wt1*I(x1∈R t1 )+Wt2I(x1∈R t2 )=1.2*1+0.5*0=1.2.

[0159] For sample 2, the blood flow velocity VPK is 55, so it belongs to the region of leaf node 2, the indicator function of leaf node 2 is 1, and the indicator function of leaf node 1 is 0.

[0160] Therefore, ht's prediction for sample 2 is:

[0161] Ht(X2)=Wt1*I(x2∈R t1 )+Wt2I(x2∈R t2 )=1.2*0+0.5*1=0.5.

[0162] The calculation of other samples is similar and will not be described in detail.

[0163] In each iteration, the model trains new decision trees based on the current prediction error and updates the overall model.

[0164] Assuming that the CatBoost model is trained, the predicted probability distribution for the feature vectors of these samples is as follows:

[0165]

[0166] Using the cross entropy loss function, calculate the loss for each sample:

[0167] L1 = -log(0.85) (the true label of sample 1 is A);

[0168] L2 = -log(0.80) (the true label of sample 2 is B);

[0169] L3 = -log(0.80) (the true label of sample 3 is C);

[0170] L4 = -log(0.80) (the true label of sample 4 is D);

[0171] Based on the result of the loss function, the model weights are updated. The learning rate is 0.1 and the prediction weight of the tree is:

[0172] w 1 (x 1 )=0.05;

[0173] w 1 (x 2 )=0.15;

[0174] w 1 (x 3 )=0.20;

[0175] w 1 (x 4 )=0.30;

[0176] Update model predictions:

[0177] F1(x 1 )=F0(x 1 )+0.1*0.05;

[0178] F1(x 2 )=F0(x 2 )+0.1*0.15;

[0179] F1(x 3 )=F0(x 3 )+0.1*0.20;

[0180] F1(x 4 )=F0(x 4 )+0.1*0.30;

[0181] The updated model continues to be iteratively trained until the predetermined number of iterations is reached or the model performance is no longer significantly improved.

[0182] After the last iteration, for each sample, the class with the highest probability is selected as the predicted class:

[0183] Sample 1 is predicted to be type A (because P(A) is the largest);

[0184] Sample 2 is predicted to be type B;

[0185] Sample 3 is predicted to be type C;

[0186] Sample 4 is predicted to be type D.

[0187] In order to more clearly understand the cardiac arrest warning device 100 provided in the embodiment of the present application, the execution process of the cardiac arrest warning device 100 provided in the embodiment of the present application will be introduced below. Figure 3 This is a flow chart of the execution process of the cardiac arrest warning device 100 provided in the embodiment of the present application, refer to Figure 3 As shown, the execution process may include:

[0188] Step 301: Acquire the first type of medical data of the target user; the first type of medical data is a plurality of medical data related to cardiac arrest;

[0189] Step 302: inputting the acquired first type of medical data into a preset classification model, and performing preset iterative training to obtain a warning category for a target user's cardiac arrest prediction situation;

[0190] Step 303: Execute external information interaction according to the acquired warning category.

[0191] Figure 4 A detailed flowchart of the execution process of the cardiac arrest warning device 100 provided in the embodiment of the present application is shown in FIG. Figure 4 As shown, the execution process may include:

[0192] Step 401: Start. The cardiac arrest warning device 100 is started and data is initialized.

[0193] Step 402: Data acquisition and preprocessing. Specifically, data acquisition and preprocessing can be performed by a Doppler blood flowmeter. The data acquisition and preprocessing process may include: collecting ultrasonic signals, digital filtering, fast Fourier transform, ultrasonic spectrum envelope calculation, etc. This is known to those skilled in the art and will not be described in detail.

[0194] Step 403: Calculate hemodynamic parameters such as VPK, VTI, HR, DSIvti, etc. According to the pre-processed data obtained in the previous step, corresponding calculations are performed to obtain hemodynamic parameters such as VPK, VTI, HR, DSIvti, etc.

[0195] Step 404: Calculate the local classification model to obtain the warning category. The local classification model calculation can be performed on the device that collects data. For example, a Doppler blood flowmeter also has a computing component that can run the classification model.

[0196] Step 405: Upload data to the cloud server. This is done simultaneously with the previous step.

[0197] Step 406: Calculate the cloud classification model to obtain the warning category. Compared with the calculation of the local classification model, the cloud computing power is more abundant and more flexible. For example, the computing power can be increased according to the specific situation. Therefore, more timely results can generally be obtained.

[0198] Step 407: prompt information. This is the result obtained after the classification model is calculated: the probability of cardiac arrest is relatively low, but it cannot be completely ruled out, so it is only a prompt. Whether it is a local classification model or a cloud classification model, prompt information can be sent and then displayed locally or in the cloud.

[0199] Step 408: Data is pushed to the hospital interaction device. This is a bit more likely than the previous step and needs to be sent to the hospital, for example, for the doctor to make a judgment.

[0200] Step 409: Data is pushed to the hospital interactive device and an alert is issued. This is a bit high probability, not only is it sent to the hospital, but an alert is also required.

[0201] Step 410: Call 120 to alert the corresponding hospital. This is a high probability, so it is very urgent and you need to call 120 directly.

[0202] Step 411: Diagnosed as requiring emergency treatment. If yes, proceed to step 413, i.e. the probability of the classification model's judgment is not very high, but the doctor diagnoses that emergency treatment is required based on his / her expertise. If no, return to step 406.

[0203] Step 412: Linking the 120 call system. Because of the doctor's diagnosis in the previous step, it is necessary to link the 120 call system.

[0204] Step 413: 120 contacts the target user or directly dispatches a vehicle. The target user may be contacted through a reserved contact method, or the target user's emergency contact may be contacted.

[0205] Step 414: Hospital treatment.

[0206] Each module included in this embodiment can be implemented by a processor in a computer; of course, it can also be implemented by a logic circuit in a computer. The processor can be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a central processing unit (CPU), a microprocessor (MPU) or any other conventional processor.

[0207] The computer here can be a local computer, such as integrated in the data acquisition device, or a cloud-based computer, which obtains data from the data acquisition device through a networking device. If the warning category obtained by the computer is local, it can be directly displayed in the local data acquisition device, and at the same time sent to the hospital interaction device and the public emergency interaction device through the networking device. If it is in the cloud, it can be returned to the data acquisition device through the networking device, and at the same time sent to the hospital interaction device and the public emergency interaction device through the networking device.

[0208] Embodiment 2

[0209] The present application embodiment provides a computing device 500, which is applied to a medical warning system, wherein the medical warning system comprises: a data acquisition device, the cardiac arrest warning device, a hospital interaction device, a public emergency interaction device, and a networking device. Figure 5 , the computing device 500 comprises: a storage component 501, a communication bus 502 and a processing component 503, wherein:

[0210] The storage component 501 is used to store the operating program of the cardiac arrest warning device 100;

[0211] The communication bus 502 is used to realize the connection and communication between the storage component 501 and the processing component 503;

[0212] The processing component 503 is used to execute the operating program of the cardiac arrest warning device 100 to implement the following steps:

[0213] Acquire a first type of medical data of a target user; the first type of medical data is a plurality of medical data related to cardiac arrest;

[0214] Inputting the acquired first type of medical data into a preset classification model, and performing preset iterative training to obtain a warning category representing the probability of cardiac arrest of the target user;

[0215] According to the obtained warning category, external information interaction is performed.

[0216] The type or structure of the storage component 501 can be found in the storage medium below, and will not be described in detail here.

[0217] The processing unit 503 may be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a central processing unit (CPU), a microprocessor (MPU), or any other conventional processor.

[0218] In some embodiments, the computing device 500 may further include: an input device 504, an output device 505, and an external communication interface 506, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown in the figure). In this embodiment, the input device 504 may be a network connector, an analog-to-digital converter, etc., and the output device 505 may be a display, a speaker, etc.

[0219] In some embodiments, the input device 504 may also include, for example, a keyboard, a mouse, a microphone, etc. The output device 505 may output various information to the outside, for example, in addition to the above-mentioned display and speaker, it may also be a printer, a projector, and a communication network and its connected remote output device, etc. The external communication interface 506 may be wired, such as a standard serial port (RS232), a general-purpose interface bus (GPIB) interface, an Ethernet interface, a universal serial bus (USB) interface, or may be wireless, such as wireless network communication technology (WiFi), Bluetooth, etc.

[0220] The description of the above device embodiment is similar to the description of the above apparatus embodiment, and has similar beneficial effects as the apparatus embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the apparatus embodiment in the present application for understanding.

[0221] Embodiment 3

[0222] The embodiment of the present application provides a computer-readable storage medium, which is applied to a medical warning system, and the medical warning system comprises: an executable program is stored on the computer-readable storage medium,

[0223] When the executable program is executed by the processor, the following steps are implemented:

[0224] Acquire a first type of medical data of a target user; the first type of medical data is a plurality of medical data related to cardiac arrest;

[0225] Inputting the acquired first type of medical data into a preset classification model, and performing preset iterative training to obtain a warning category representing the probability of cardiac arrest of the target user;

[0226] According to the obtained warning category, external information interaction is performed.

[0227] Exemplarily, the computer-readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The computer-readable storage medium is a tangible device that can hold and store instructions used by the instruction execution device. The readable storage medium can include, for example, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: portable computer disks, hard disks, random access memory (RAM, Random Access Memory), read-only memory (ROM, Read Only Memory), flash memory (Flash Memory), portable compact disc read-only memory (CD-ROM, Compact Disc Read-Only Memory), digital versatile disk (DVD, Digital Versatile Disc), memory stick, floppy disk, mechanical encoding device, such as a punch card or a protruding structure in a groove on which instructions are stored, and any suitable combination of the above. Wherein:

[0228] The RAM includes: static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAM bus random access memory (DRRAM, Direct Rambus Random Access Memory).

[0229] The ROM includes: a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), and an electrically erasable programmable read-only memory (EEPROM).

[0230] The computer-readable storage medium used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (for example, light pulses through a fiber optic cable), or an electrical signal transmitted through wires.

[0231] The description of the above computer-readable storage medium embodiment is similar to the description of the above device embodiment, and has similar beneficial effects as the device embodiment. For technical details not disclosed in the computer-readable storage medium embodiment of this application, please refer to the description of the device embodiment in this application for understanding.

[0232] Embodiment 4

[0233] The present application embodiment provides a medical early warning system, referring to Figure 6 , the medical warning system comprises:

[0234] The data collection device 601 is used to collect the first type of medical data of the target user;

[0235] The cardiac arrest warning device 100 described in Embodiment 1;

[0236] The hospital interaction device 603 is used to receive the data and warnings sent by the cardiac arrest warning device 100 and analyze the data;

[0237] The public emergency interaction device 604 is used to receive the contact information sent by the cardiac arrest warning device 100 to arrange emergency tasks;

[0238] The networking device 602 is used to connect the cardiac arrest warning device 100, the hospital interaction device 603 and the public emergency interaction device 604 through the Internet.

[0239] The architecture of the medical early warning system in specific implementation can be found in Figure 7 ,like Figure 7 As shown, the medical warning system includes:

[0240] The cloud server includes an intelligent warning module; the intelligent warning module is the same as the interaction module 103 mentioned above. It can be understood that the cloud server may include other modules in addition to the intelligent warning module, such as the acquisition module 101 mentioned above;

[0241] A blood flow monitoring device, used to collect first type medical data of target users, the target users are identified as user 1, user 2, ... user N in the accompanying drawings;

[0242] Interaction devices of hospitals, which are labeled as hospital 1, hospital 2, ... hospital N in the attached figure;

[0243] An interactive device for a public emergency dispatch center.

[0244] Among them, the cloud server and the blood flow monitoring equipment are connected through a public mobile communication system, which can be specifically the fifth-generation communication network, namely the 5G wireless communication network; the cloud server and each interactive device can be connected through Ethernet, namely a wired communication network such as optical fiber.

[0245] To understand the medical warning system in more detail, the data acquisition device 601 is further introduced below. Figure 8 The data acquisition device 601 includes: a processing device, an ultrasonic transmitting circuit, an ultrasonic transmitting chip, an ultrasonic receiving chip, an ultrasonic receiving signal conditioning, an analog-to-digital converter, a positioning component, a sound component, a display component and a communication interface, which are known to those skilled in the art and will not be described in detail.

[0246] The description of the above system embodiment is similar to the description of the above device embodiment, and has similar beneficial effects as the device embodiment. For technical details not disclosed in the system embodiment of the present application, please refer to the description of the device embodiment in the present application for understanding.

[0247] It should be noted that the apparatus, device, storage medium and system embodiments provided in the embodiments of the present application belong to the same concept; the technical features in the technical solutions recorded in each embodiment can be arbitrarily combined without conflict.

[0248] The present application embodiment can be a system, method and / or computer program product. The computer program product can include a computer-readable storage medium, which is loaded with a computer-readable program instruction for making a processor realize various aspects of the present application. The computer program product can be written in any combination of one or more programming languages ​​to perform the program code for performing the operation of the present application embodiment, and the programming language includes an object-oriented programming language, such as Java, C++, etc., and also includes a conventional procedural programming language, such as "C" language or similar programming language. The program code can be executed completely on the user's computer, partially on the user's device, as an independent software package, partially on the user's computer, partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer by any type of network-including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect to the Internet). In some embodiments, by utilizing the state information of computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions to implement various aspects of the present application.

[0249] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0250] Various aspects of the present application are described herein 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 box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0251] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0252] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0253] In the following description, the terms "first\second\..." are only used to distinguish similar objects and do not represent a specific order of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted.

[0254] The purpose of the terms used herein is only to describe specific embodiments and is not intended to be limiting of the present application. When used herein, the singular forms "one", "an" and "said / the" are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "consisting of" and / or "comprising", when used in this specification, determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0255] It should be understood that "one embodiment" or "some embodiments" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in some embodiments" appearing throughout the specification may not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned sequence numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments.

[0256] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or modules can be electrical, mechanical or other forms.

[0257] The modules described above as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules; they may be located in one place or distributed on multiple network modules; some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0258] In addition, all functional modules in the embodiments of the present application may be integrated into one processing module, or each functional module may be a separate module, or two or more functional modules may be integrated into one module; the above-mentioned integrated modules may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0259] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiment.

[0260] Alternatively, if the above-mentioned integrated module of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0261] The methods disclosed in several method embodiments provided in this application can be combined arbitrarily without conflict to obtain new method embodiments. The features disclosed in several product embodiments provided in this application can be combined arbitrarily without conflict to obtain new product embodiments.

[0262] In the above description, the terms "first\second\..." are only used to distinguish similar objects and do not represent a specific order of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence if permitted.

[0263] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0264] In the embodiments of the present application, unless otherwise specified and limited, the term "connection" should be understood in a broad sense. For example, it can be an electrical connection or internal connectivity between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.

[0265] The purpose of the terms used herein is only to describe specific embodiments and is not intended to be limiting of the present application. When used herein, the singular forms "one", "an" and "said / the" are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "consisting of" and / or "comprising", when used in this specification, determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0266] It should be understood that "one embodiment" or "some embodiments" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in some embodiments" appearing throughout the specification may not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned sequence numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments.

[0267] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or modules can be electrical, mechanical or other forms.

[0268] The modules described above as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules; they may be located in one place or distributed on multiple network modules; some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0269] In addition, all functional modules in the embodiments of the present application may be integrated into one processing module, or each functional module may be a separate module, or two or more functional modules may be integrated into one module; the above-mentioned integrated modules may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0270] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiment.

[0271] Alternatively, if the above-mentioned integrated module of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0272] The methods disclosed in several method embodiments provided in this application can be combined arbitrarily without conflict to obtain new method embodiments. The features disclosed in several product embodiments provided in this application can be combined arbitrarily without conflict to obtain new product embodiments.

[0273] It should be understood that the above embodiments are exemplary and are not intended to include all possible implementations included in the claims. Various modifications and changes may be made on the basis of the above embodiments without departing from the scope disclosed in the present application. Similarly, the various technical features of the above embodiments may be arbitrarily combined to form other embodiments of the present application that may not be explicitly described. Therefore, the above embodiments only express several implementations of the present application and do not limit the scope of protection of the patent of this application.

Claims

1. A cardiac arrest warning device, applied to a medical warning system, characterized in that: The medical warning system comprises: a data acquisition device, the cardiac arrest warning device, a hospital interaction device, a public emergency interaction device and a networking device; the cardiac arrest warning device comprises: An acquisition module, used for acquiring a first type of medical data of a target user; the first type of medical data is a plurality of medical data related to cardiac arrest; A training module, used to input the acquired first type of medical data into a preset classification model, and obtain a warning category for a target user's cardiac arrest prediction situation through preset iterative training; The interaction module is used to perform external information interaction according to the acquired warning category.

2. The cardiac arrest warning device according to claim 1, characterized in that: The acquisition module is specifically used for: Obtain the target user's blood flow peak velocity VPK, blood flow velocity time integral VTI, heart rate HR and shock index DSIvti.

3. The cardiac arrest warning device according to claim 1, characterized in that: The training module is also used to: In each iterative training, a first result of the prediction function and a second result of the loss function of the classification model are obtained; The classification model is updated according to the first result and the second result to enter the next round of iteration.

4. The cardiac arrest warning device according to claim 3, characterized in that: The classification model is a CatBoost model, and the training module is also used for: Constructing a feature vector of a sample according to the first type of medical data and the CatBoost model; The feature vector is input into the classification model to obtain the probability of each warning category.

5. The cardiac arrest warning device according to claim 4, characterized in that: The training module is also used to obtain a second result of the loss function according to the following expression: Wherein: I(yi=c) is an indicator function, if y is equal to category c, the function result is 1, otherwise it is 0, and M is the total number of categories.

6. The cardiac arrest warning device according to claim 4, characterized in that: The training module is also used to update the classification model according to the following expression: F m (x i )=F m-1 (x i )+ηh t (x i ) Wherein, Fm is the model after the mth round of iteration, η is the learning rate, and ht is the prediction result of the tth tree.

7. The cardiac arrest warning device according to claim 6, characterized in that: The training module is also used to obtain the value of ht according to the following expression: Where: Jt is the number of leaf nodes in the tth tree, w tj is the weight of the jth leaf node of the tth tree, R tj is the feature space region of the jth leaf node of the tth tree, I(x∈R tj ) is the indicator function. If x belongs to the feature space region R tj 1 if the value is true, 0 otherwise.

8. The cardiac arrest warning device according to any one of claims 1 to 7, characterized in that: The interaction module is also used for: If the obtained warning category is the first category, sending a prompt message; If the acquired warning category is the second category, pushing the first type of medical data of the target user to a preset hospital interaction device; If the obtained warning category is the third category, the first type of medical data of the target user is pushed to a preset hospital interaction device and an alert is issued; If the acquired warning category is the fourth category, the public emergency interaction device and / or the target user is contacted to provide emergency treatment to the target user through the public emergency system.

9. The cardiac arrest warning device according to any one of claims 1 to 7, characterized in that: The data acquisition device is a Doppler blood flow meter, and the acquisition module is also used for: Acquiring blood flow dynamics data of the target user's carotid artery through the Doppler blood flow meter; The first type of medical data is acquired according to the hemodynamic data.

10. A computing device, applied to a medical early warning system, characterized in that: The medical warning system includes: a data acquisition device, a cardiac arrest warning device, a networking device, a hospital interaction device and a public emergency interaction device; the computing device includes: a storage component, a communication bus and a processing component, wherein: The storage component is used to store the operating program of the cardiac arrest warning device; The communication bus is used to realize the connection and communication between the storage component and the processing component; The processing component is used to execute the operating program of the cardiac arrest warning device to achieve the following steps: Acquire a first type of medical data of a target user; the first type of medical data is a plurality of medical data related to cardiac arrest; Inputting the acquired first type of medical data into a preset classification model, and performing preset iterative training to obtain a warning category representing the probability of cardiac arrest of the target user; According to the obtained warning category, external information interaction is performed.

11. A computer-readable storage medium, applied to a medical early warning system, characterized in that: The medical warning system comprises: a data acquisition device, a cardiac arrest warning device, a networking device, a hospital interaction device and a public emergency interaction device; an executable program is stored on the computer-readable storage medium, and the executable program implements the following steps when executed by the processor: Acquire a first type of medical data of a target user; the first type of medical data is a plurality of medical data related to cardiac arrest; Inputting the acquired first type of medical data into a preset classification model, and performing preset iterative training to obtain a warning category representing the probability of cardiac arrest of the target user; According to the obtained warning category, external information interaction is performed.

12. A medical early warning system, characterized in that: include: A data collection device, used for collecting a first type of medical data of a target user; The cardiac arrest warning device according to any one of claims 1 to 9; A hospital interaction device, used for receiving data and warnings sent by the cardiac arrest warning device, and analyzing the data; A public emergency response interactive device, used to receive the contact information sent by the cardiac arrest warning device to arrange emergency response tasks; A networking device is used to connect the cardiac arrest warning device, the hospital interaction device and the public emergency interaction device for communication via the Internet.