CRRT remote early warning method, system and device and storage medium

Abstract

The invention provides a CRRT remote early warning method, system and device and a storage medium. The method comprises the steps of obtaining current characterization data of a patient to be monitored; setting a monitoring parameter range based on the current characterization data of the patient to be monitored; when the monitoring parameters of the patient to be monitored are abnormal, abnormal monitoring parameters are extracted; performing feature extraction on the abnormal monitoring parameters to obtain abnormal features; inputting the abnormal features into an abnormal classification model, obtaining an abnormal type of the to-be-monitored patient, and grading the abnormal degree based on the abnormal type; according to the abnormal degree grading result, remote early warning information is generated, and the early warning information is sent to medical staff, when the monitoring parameters do not reach the preset threshold value, early warning prompting is carried out on the abnormal condition in advance, the early warning efficiency of the abnormal condition is improved, and the occurrence probability of danger is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of remote warning, and specifically relates to a CRRT remote warning method, system, device and storage medium. Background Art

[0002] The current alarm mechanism of the continuous renal replacement therapy (CRRT) system is mainly based on the collection and analysis of real-time physiological data of the patient to be monitored. In this process, the system continuously monitors a series of key indicators such as blood flow rate, dialysate flow rate, electrolyte concentration, blood pressure, and heart rate to ensure the safety and effectiveness of the treatment process. When these real-time data exceed the preset safety range or show abnormal fluctuations, the system will automatically trigger the alarm mechanism and quickly notify medical staff in the form of sound, light signal or screen prompt, so that they can take corresponding measures in time to avoid the deterioration of the condition of the patient to be monitored or the occurrence of adverse events. However, although this alarm method based on real-time data plays an important role in improving treatment safety and response speed, it still has certain limitations. Specifically, this alarm mechanism is more of a passive response that intervenes when a problem has already occurred. This means that before the alarm is issued, the patient to be monitored may have experienced abnormal physiological indicators for a period of time. Although this abnormality may not have reached the threshold for triggering the alarm, it may still have an adverse impact on the health of the patient to be monitored.

[0003] Therefore, how to achieve a more forward-looking warning function on the basis of the existing technology has become an important topic in the current development of CRRT technology. Summary of the Invention

[0004] In order to overcome the above problems existing in the prior art, the present application provides a CRRT remote warning method, system, device and storage medium, and adopts the following technical solutions:

[0005] In the first aspect, the present application provides a CRRT remote warning method, including:

[0006] Obtaining the current characterization data of the patient to be monitored;

[0007] Setting the monitoring parameter range based on the current characterization data of the patient to be monitored;

[0008] When the monitoring parameters of the patient to be monitored are abnormal, extracting the abnormal monitoring parameters;

[0009] Extracting features of the abnormal monitoring parameters to obtain abnormal features;

[0010] Inputting the abnormal features into an abnormal classification model to obtain the abnormal type of the patient to be monitored, and grading the abnormal degree based on the abnormal type;

[0011] Generate a remote warning message based on the abnormal degree grading result, and send the warning message to medical staff.

[0012] Further, the obtaining of the current characterization data of the patient to be monitored includes the patient's basic information, renal function status, other underlying diseases, laboratory test results within a preset time period, existing clinical symptoms and signs.

[0013] Further, the setting of the monitoring parameter range based on the current characterization data of the patient to be monitored includes:

[0014] Obtain the historical characterization data of other patients;

[0015] Perform standardization processing on the historical characterization data to obtain standardized data;

[0016] Input the standardized data into the input layer of the neural network, where each neuron in the input layer of the neural network receives a feature value in the standardized data, and the neuron transmits the received feature value to the hidden layer;

[0017] Map the input feature values to a high-dimensional feature space through the neurons and connection weights in the hidden layer of the neural network;

[0018] After the feature processing of the hidden layer, based on the relationship between the historical characterization state of the patient and the monitoring parameters, output the range of each monitoring parameter through the output layer to complete the training of the neural network;

[0019] Input the standardized current characterization data of the patient to be monitored into the trained neural network, and the neural network obtains the monitoring parameter range of the patient to be monitored based on the newly input characterization state data of the patient to be monitored.

[0020] Further, when the monitoring parameters of the patient to be monitored are abnormal, it includes the abnormal change trend and abnormal fluctuation amplitude of one or several monitoring parameters.

[0021] Further, the method for judging abnormal change trend is:

[0022] The monitoring parameter is time series data. By fitting the time series data of the monitoring parameter through linear regression, the change trend line of the monitoring parameter is obtained. When the change rate of the change trend line of a certain monitoring parameter does not meet the preset threshold, the monitoring parameter is abnormal.

[0023] Further, the method for judging abnormal fluctuation amplitude is:

[0024] For different monitoring parameters, different time windows are preset. By calculating the difference between the maximum value and the minimum value of the monitoring parameter within its preset time window, the fluctuation range of the monitoring parameter is obtained. When the fluctuation range of a certain monitoring parameter exceeds the preset threshold, the monitoring parameter is abnormal.

[0025] Furthermore, mining the correlation between the abnormal monitoring parameters includes:

[0026] Converting the abnormal monitoring parameters into an abnormal matrix;

[0027] Obtaining the correlation coefficient matrix of the abnormal matrix;

[0028] Performing eigenvalue decomposition on the correlation coefficient matrix to obtain eigenvalues and corresponding eigenvectors, where the eigenvalue is the variance of the abnormal monitoring data on the corresponding eigenvector;

[0029] Obtaining the condition number based on the ratio of the maximum eigenvalue to the minimum eigenvalue;

[0030] Based on the condition number and eigenvalues, obtaining the abnormal monitoring parameters with strong correlation.

[0031] Furthermore, based on the correlation of the abnormal monitoring parameters, abnormal classification is performed, including:

[0032] Inputting the abnormal monitoring parameters with strong correlation into the multi-layer perceptron layer, calculating the probability of each abnormal type through the forward propagation of the multi-layer perceptron layer, and selecting the abnormal classification with the highest probability as the classification result.

[0033] In a second aspect, the present application also provides a CRRT remote warning system, including:

[0034] A current characterization data acquisition module for acquiring the current characterization data of the patient to be monitored;

[0035] A monitoring parameter range setting module for setting the monitoring parameter range based on the current characterization data of the patient to be monitored;

[0036] An abnormal monitoring parameter extraction module for extracting abnormal monitoring parameters when the monitoring parameters of the patient to be monitored are abnormal;

[0037] An abnormal feature acquisition module for extracting features of the abnormal monitoring parameters to obtain abnormal features;

[0038] An abnormal degree grading module for inputting the abnormal features into an abnormal classification model to obtain the abnormal type of the patient to be monitored, and grading the abnormal degree based on the abnormal type;

[0039] An early warning information generation module, configured to generate remote early warning information based on the abnormal degree classification result and send the early warning information to medical staff.

[0040] In a third aspect, the present application provides an electronic device, including:

[0041] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the device, cause the device to execute the method described in the first aspect.

[0042] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program that, when running on a computer, causes the computer to execute the method described in the first aspect.

[0043] In a fifth aspect, the present application provides a computer program that, when executed by a computer, is used to execute the method described in the first aspect.

[0044] In a possible design, the program in the fifth aspect can be stored in whole or in part on a storage medium packaged together with the processor, or can be stored in whole or in part on a memory not packaged together with the processor.

[0045] The present application has the following beneficial effects:

[0046] 1. The present application obtains the current characterization data of the patient to be monitored; sets the monitoring parameter range based on the current characterization data of the patient to be monitored, so that during the CRRT process of the patient, the monitoring parameters of the patient can be monitored, and the range of the monitoring parameters can be dynamically adjusted according to the dynamic change state of the monitoring parameters to meet the monitoring parameter changes required by different patients in different states.

[0047] 2. When the monitoring parameters of the patient to be monitored are abnormal, the present application extracts the abnormal monitoring parameters, mines the correlation between the abnormal monitoring parameters, and classifies the abnormalities based on the correlation of the abnormal monitoring parameters. The present application classifies the abnormalities according to the extracted abnormal monitoring parameters, generates remote early warning information based on the abnormal classification result, and sends the early warning information to medical staff, which can give early warning prompts for abnormal situations when the monitoring parameters do not reach the preset threshold, improve the early warning efficiency of abnormal situations, and reduce the probability of danger. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0049] Figure 2 Flow chart of the CRRT remote warning method according to an embodiment of the present application;

[0050] Figure 3 Flow chart of setting the monitoring parameter range according to an embodiment of the present application;

[0051] Figure 4 Flow chart of correlation analysis of abnormal monitoring parameters according to an embodiment of the present application;

[0052] Figure 5 System flow chart according to an embodiment of the present application;

[0053] Figure 6 Schematic diagram of a computer device according to an embodiment of the present application. Detailed implementation manners

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and not to describe a specific order.

[0055] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0056] In order to enable those skilled in the art of this technology to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the drawings.

[0057] As Figure 1 shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0058] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0059] Terminal devices 101, 102, and 103 can be various electronic devices with a display screen and supporting web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, and so on.

[0060] Server 105 can be a server that provides various services, such as a background server that provides support for the pages displayed on terminal devices 101, 102, and 103.

[0061] It should be noted that the CRRT remote warning method provided by the embodiments of the present application is generally executed by the server / terminal device. Correspondingly, the CRRT remote warning system is generally set in the server / terminal device.

[0062] It should be understood that Figure 1 the numbers of terminal devices, networks, and servers in

[0063] are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, and servers. Figure 2 Continuing to refer to

[0064] Step 201, obtain the current characterization data of the patient to be monitored.

[0065] In a possible implementation manner, the obtaining of the current characterization data of the patient to be monitored includes but is not limited to the basic information of the patient to be monitored: age, gender, weight; renal function status: serum creatinine, urine volume, etc.; other underlying diseases: heart disease, diabetes, etc.; laboratory test results within a preset time period; existing clinical symptoms and signs: edema, heart rate changes, etc.; blood purification-related parameters: blood flow rate; pressure parameters: arterial pressure, venous pressure, transmembrane pressure, electrolytes, acid-base balance indicators, coagulation function indicators, body temperature, blood oxygen saturation, etc.

[0066] Step 202: Set the monitoring parameter range based on the current characterization data of the patient to be monitored.

[0067] In a possible implementation, for the setting of the monitoring parameter range based on the current characterization data of the patient to be monitored, please refer to Figure 3 , and the specific content includes:

[0068] Step 31: Obtain the historical characterization data of other patients; where the historical characterization data of the other patients is the same as the current characterization data items of the patient to be monitored.

[0069] Step 32: Perform standardization processing on the historical characterization data to obtain standardized data; the standardization processing can be implemented by existing methods and will not be elaborated here.

[0070] Step 33: Input the standardized data into the input layer of the neural network. Each neuron in the input layer of the neural network receives a feature value in the standardized data, and the neuron passes the received feature value to the hidden layer.

[0071] Step 34: Through the neurons and connection weights in the hidden layer of the neural network, map the input feature values to a high-dimensional feature space. The hidden layer neurons close to the input layer learn the basic physiological feature combinations, and the hidden layer neurons close to the output layer learn the high-level feature representations related to the CRRT parameters.

[0072] Step 35: After the feature processing of the hidden layer, based on the relationship between the historical characterization data of the patient and the monitoring parameters, output the range of each monitoring parameter through the output layer to complete the training of the neural network.

[0073] Step 36: Input the standardized current characterization data of the patient to be monitored into the trained neural network. The neural network obtains the monitoring parameter range of the patient to be monitored based on the newly input characterization data of the patient to be monitored.

[0074] In a possible implementation, the standardization processing of the current characterization data of the patient to be monitored can be performed by existing methods and will not be elaborated here. In this application, the historical characterization data of other patients and the current characterization data of the patient to be monitored are standardized to a preset range, which can improve the efficiency of neural network training and the stability of data during neural network training and use.

[0075] Step 203: When the monitoring parameters of the patient to be monitored are abnormal, extract the abnormal monitoring parameters.

[0076] In a possible implementation, each monitoring parameter has a certain monitoring range. When the actual parameter value of a certain monitoring parameter is not within its monitoring range for a continuous period of time, it can be determined that the data of the monitoring parameter is abnormal, and then the monitoring parameter will be extracted for subsequent analysis. In this application, when the monitoring parameters of the patient to be monitored are abnormal, it includes the abnormal change trend and abnormal fluctuation range of one or several monitoring parameters.

[0077] In a possible implementation, the monitoring parameter is time series data. By fitting the time series data of the monitoring parameter through linear regression, the change trend line of the monitoring parameter is obtained. When the change rate of the change trend line of a certain monitoring parameter does not meet the preset threshold, the monitoring parameter is abnormal.

[0078] In a possible implementation, by performing linear regression for fitting to obtain the change trend line of the monitoring parameter, the specific content includes:

[0079] Taking the time of the monitoring parameter as the independent variable x and the value of the monitoring parameter as the dependent variable y i (i = 1, 2, 3,..., n, where n is the number of monitoring parameters);

[0080] For each monitoring parameter, a multiple linear regression model is constructed as y i = β i0 + β i1 x i + ε i , where β i0 is the intercept, β i1 is the slope corresponding to time x, and ε i is the error term.

[0081] The parameters β i0 and β i1 in the multiple linear regression model are estimated by the least squares method. The purpose of the least squares method is to find a set of parameters that minimize the sum of the squares of the errors between the observed value y i and the actual value , that is is minimized. By taking the partial derivatives of Q with respect to β i0 and β i1 respectively and setting the partial derivatives to 0, a system of equations for solving β i0 and β i1 can be obtained, and the parameter values are solved to obtain the change trend line of the monitoring parameter.

[0082] In a possible implementation, when the change rate of the change trend line of a certain monitoring parameter does not meet the preset threshold, the monitoring parameter is abnormal, including:

[0083] Quantify the change rate of each monitoring parameter through the slope of the change trend line of each monitoring parameter. When the change rate of a certain monitoring parameter is within the safety range of the monitoring parameter, the monitoring parameter is in a stable state; when the change rate of a certain monitoring parameter is not within the safety range of the monitoring parameter, that is, when the change rate is in an increasing or decreasing state, the monitoring parameter is in an abnormal state.

[0084] In this application, a multiple linear regression model is established for each monitoring parameter, and then the change trend of each monitoring parameter can be obtained, and the change trend of each monitoring parameter during the CRRT process can be analyzed more conveniently.

[0085] In a possible implementation manner, for different monitoring parameters, different time windows are preset. By calculating the difference between the maximum value and the minimum value of the monitoring parameter within its preset time window, the fluctuation amplitude of the monitoring parameter is obtained. When the fluctuation amplitude of a certain monitoring parameter exceeds the preset threshold, the monitoring parameter is abnormal.

[0086] In a possible implementation manner, when at least one of the change trend and the fluctuation amplitude of a certain monitoring parameter is abnormal, it is determined that the monitoring parameter is an abnormal monitoring parameter.

[0087] By analyzing the change trend and the fluctuation amplitude of the monitoring parameter in this application, when the monitoring parameter does not reach the warning threshold, the abnormal monitoring parameter can be determined through the abnormal information of the change trend and the fluctuation amplitude of the monitoring parameter, so as to pre-warn the abnormal information in advance, improve the efficiency of warning, and reduce the occurrence of danger.

[0088] Step 204, mine the correlation between the abnormal monitoring parameters, and perform abnormal classification based on the correlation between the abnormal monitoring parameters.

[0089] In a possible implementation manner, for mining the correlation between the abnormal monitoring parameters, please refer to Figure 4 , and the specific content includes:

[0090] Step 41, convert the abnormal monitoring parameters into an abnormal matrix A, where each column in the abnormal matrix A represents an abnormal monitoring parameter, and each row represents a time point.

[0091] Step 42, obtain the correlation coefficient matrix R of the abnormal matrix A, where m represents the number of abnormal monitoring parameters.

[0092] Step 43, perform eigenvalue decomposition on the correlation coefficient matrix R to obtain eigenvalues and corresponding eigenvectors, where the eigenvalue is the variance of the abnormal monitoring data on the corresponding eigenvector;

[0093] Step 44: Obtain the condition number based on the ratio of the maximum eigenvalue to the minimum eigenvalue;

[0094] Step 45: Based on the condition number and eigenvalues, obtain anomaly monitoring parameters with strong correlation. The determination condition for obtaining anomaly monitoring parameters with strong correlation is that the components of the corresponding eigenvectors of these anomaly monitoring parameters in the same direction satisfy a preset threshold, and the condition number satisfies a preset threshold, then it is determined that these anomaly monitoring parameters have strong correlation.

[0095] In a possible implementation manner, anomaly classification based on the correlation of the anomaly monitoring parameters includes:

[0096] Input the anomaly monitoring parameters with strong correlation into the multi-layer perceptron, calculate the probability of each anomaly type through the forward propagation of the multi-layer perceptron, and select the anomaly classification with the highest probability as the classification result.

[0097] In a possible implementation manner, calculating the probability of each anomaly type through the forward propagation of the multi-layer perceptron includes:

[0098] The input layer of the multi-layer perceptron receives the anomaly monitoring parameters with strong correlation;

[0099] Feature extraction is performed on the anomaly monitoring parameters with strong correlation through linear transformation and activation functions in the hidden layer of the multi-layer perceptron;

[0100] Calculate the probability of each anomaly type through the Softmax function in the output layer of the multi-layer perceptron.

[0101] Step 205: Generate remote warning information based on the anomaly classification result, and send the warning information to medical staff.

[0102] In a possible implementation manner, the warning information generated by this application includes the patient's basic information, the type and value of the abnormal data, and the time when the anomaly occurred.

[0103] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. This computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disc, a read-only memory (ROM), etc., or a random access memory (RAM), etc.

[0104] It should be understood that although the steps in the flowchart of the accompanying drawings are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this document, there is no strict order restriction for the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0105] Continuing to refer to Figure 5 , the CRRT remote warning system described in this embodiment includes:

[0106] The current characterization data acquisition module 501 is used to acquire the current characterization data of the patient to be monitored;

[0107] The monitoring parameter range setting module 502 is used to set the monitoring parameter range based on the current characterization data of the patient to be monitored;

[0108] The abnormal monitoring parameter extraction module 503 is used to extract the abnormal monitoring parameters when the monitoring parameters of the patient to be monitored are abnormal;

[0109] The abnormal degree classification module 504 is used to mine the correlation between the abnormal monitoring parameters and classify the abnormalities based on the correlation of the abnormal monitoring parameters;

[0110] The warning information generation module 505 is used to generate remote warning information based on the abnormal classification result and send the warning information to the medical staff.

[0111] To solve the above technical problems, the embodiments of the present application also provide a computer device. Specifically, please refer to Figure 6 , Figure 6 This is the basic structural block diagram of the computer device in this embodiment.

[0112] The computer device 6 includes a memory 6a, a processor 6b, and a network interface 6c that are communicatively connected to each other via a system bus. It should be noted that only the computer device 6 with components 6a - 6c is shown in the figure. However, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Among them, those skilled in the art of this technology can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0113] The computer device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device can perform human-computer interaction with users through means such as a keyboard, a mouse, a remote control, a touchpad, or a voice control device.

[0114] The memory 6a includes at least one type of readable storage medium. The readable storage medium includes flash memory, hard disks, multimedia cards, card-type memories (such as SD or DX memories, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memories, magnetic disks, optical discs, etc. In some embodiments, the memory 6a can be an internal storage unit of the computer device 6, such as the hard disk or memory of the computer device 6. In other embodiments, the memory 6a can also be an external storage device of the computer device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the computer device 6. Of course, the memory 6a can also include both the internal storage unit and the external storage device of the computer device 6. In this embodiment, the memory 6a is generally used to store the operating system and various application software installed on the computer device 6, such as the program code of the CRRT remote warning method. In addition, the memory 6a can also be used to temporarily store various data that have been output or will be output.

[0115] In some embodiments, the processor 6b may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 6b is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 6b is used to run the program code stored in the memory 6a or process data, such as running the program code of the CRRT remote warning method.

[0116] The network interface 6c may include a wireless network interface or a wired network interface, which is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0117] The present application also provides another implementation manner, that is, to provide a non-volatile computer-readable storage medium storing a program of the CRRT remote warning method, and the CRRT remote warning can be executed by at least one processor, so that the at least one processor executes the steps of the CRRT remote warning method as described above.

[0118] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation manner. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0119] Obviously, the above-described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The preferred embodiments of the present application are shown in the drawings, but do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure content of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing specific embodiments, or perform equivalent replacements for some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present application in other related technical fields shall be similarly within the scope of the patent protection of the present application.

Claims

1. A CRRT remote warning method, characterized in that, Including: Obtain the current characterization data of the patient to be monitored; Set the monitoring parameter range based on the current characterization data of the patient to be monitored; When the monitoring parameters of the patient to be monitored are abnormal, extract the abnormal monitoring parameters; Mine the correlation between the abnormal monitoring parameters, and perform abnormal classification based on the correlation of the abnormal monitoring parameters; Based on the abnormal classification result, generate a remote warning message and send the warning message to the medical staff.

2. The CRRT remote warning method according to claim 1, wherein, The obtaining of the current characterization data of the patient to be monitored includes the patient's basic information, renal function status, other underlying diseases, laboratory test results within a preset time period, existing clinical symptoms and signs.

3. The CRRT remote warning method according to claim 1, characterized in that, The setting of the monitoring parameter range based on the current characterization data of the patient to be monitored includes: Obtain the historical characterization data of other patients; Perform standardization processing on the historical characterization data to obtain standardized data; Input the standardized data into the input layer of the neural network, where each neuron in the input layer of the neural network receives a feature value in the standardized data, and the neuron transmits the received feature value to the hidden layer; Through the neurons and connection weights in the hidden layer of the neural network, map the input feature values to a high-dimensional feature space; After the feature processing of the hidden layer, based on the relationship between the historical characterization state of the patient and the monitoring parameters, output the range of each monitoring parameter through the output layer to complete the training of the neural network; Input the standardized current characterization data of the patient to be monitored into the trained neural network, and the neural network obtains the monitoring parameter range of the patient to be monitored based on the newly input characterization state data of the patient to be monitored.

4. The CRRT remote warning method according to claim 1, wherein When the monitoring parameters of the patient to be monitored are abnormal, it includes abnormal change trends and abnormal fluctuation amplitudes of one or several monitoring parameters.

5. The CRRT remote warning method according to claim 4, characterized in that, The method for judging abnormal change trends is: The monitoring parameter is time series data. By fitting the time series data of the monitoring parameter through linear regression, the change trend line of the monitoring parameter is obtained. When the change rate of the change trend line of a certain monitoring parameter does not meet the preset threshold, the monitoring parameter is abnormal.

6. The CRRT remote warning method according to claim 4, characterized in that, The method for judging abnormal fluctuation amplitudes is: For different monitoring parameters, different time windows are preset. By calculating the difference between the maximum value and the minimum value of the monitoring parameter within its preset time window, the fluctuation amplitude of the monitoring parameter is obtained. When the fluctuation amplitude of a certain monitoring parameter exceeds the preset threshold, the monitoring parameter is abnormal.

7. The CRRT remote warning method according to claim 1, characterized in that Mining the correlation between the abnormal monitoring parameters includes: Convert the abnormal monitoring parameters into an abnormal matrix; Obtain the correlation coefficient matrix of the abnormal matrix; Perform eigen decomposition on the correlation coefficient matrix to obtain eigenvalues and corresponding eigenvectors, where the eigenvalue is the variance of the abnormal monitoring data on the corresponding eigenvector; Obtain the condition number based on the ratio of the maximum eigenvalue to the minimum eigenvalue; Based on the condition number and eigenvalues, obtain the abnormal monitoring parameters with strong correlation.

8. The CRRT remote warning method according to claim 1, characterized in that Performing abnormal classification based on the correlation of the abnormal monitoring parameters includes: Input the anomaly monitoring parameters with strong correlation into the multi-layer perceptron layer, calculate the probability of each anomaly type through the forward propagation of the multi-layer perceptron layer, and select the anomaly classification with the highest probability as the classification result.

9. A CRRT remote warning system, characterized in that, It includes: The current characterization data acquisition module is used to acquire the current characterization data of the patient to be monitored; The monitoring parameter range setting module is used to set the monitoring parameter range based on the current characterization data of the patient to be monitored; The anomaly monitoring parameter extraction module is used to extract the anomaly monitoring parameters when the monitoring parameters of the patient to be monitored are abnormal; The anomaly degree grading module is used to mine the correlation between the anomaly monitoring parameters and classify the anomalies based on the correlation of the anomaly monitoring parameters; The early warning information generation module is used to generate remote early warning information based on the anomaly classification result and send the early warning information to the medical staff.

Images