Clinical monitoring management method and system

By obtaining and processing patient data in the medical monitoring system, establishing a database and using preprocessing and drug prediction models, automated drug supply and monitoring are realized, and the problems of alarm fatigue, information silos and irregular drug management in the existing technology are solved. Improves the efficiency and security of the monitoring system.

CN119028608APending Publication Date: 2024-11-26SHANGHAI RAIN MEDICAL EQUIP CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411121339.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing medical monitoring system has problems such as alarm fatigue, information silos and irregular drug management, resulting in high false alarm rates, difficulty in sharing information and inaccurate drug use.

Method used

By obtaining the patient's personal information and monitoring equipment data, establishing connection information and building a database, using preprocessing models and drug prediction recommendation models to calculate recommended drug encoding, obtaining life characteristic data in real time for comparison, and generating adaptive signals to control the syringe pump and supply Oxygen machine realizes automated supply and monitoring of drugs.

Benefits of technology

Real-time monitoring of patient status and information sharing are realized, false alarm rate is reduced, the problem of inaccurate medication is solved, the automatic supply of drugs is ensured, and the aggravation of the disease caused by untimely human labor processing is avoided.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119028608A_ABST
    Figure CN119028608A_ABST
Patent Text Reader

Abstract

The invention relates to a clinical monitoring management method and system, and belongs to the technical field of medical monitoring. The method comprises the following steps: acquiring personal information data, a diagnosis code, an operation code and a historical medication code, and establishing a database table according to a connection relationship between the personal information data and monitoring equipment information; feature vector data are obtained through the preprocessing model, and according to the feature vector data, a recommended medicine use code is obtained through calculation of a medicine prediction recommendation model; acquiring vital sign data through the monitoring equipment, and storing the vital sign data into a database according to the connection information; searching a database according to the recommended medication codes to obtain required calculation data, and calculating through a pump speed algorithm to obtain pump speed data of the injection pump; the intelligent terminal compares the degreased body weight, the heart rate, the basic characteristic data and the blood oxygen with a preset threshold value to obtain a comparison result, and the infusion pump and the oxygen supply machine are controlled to operate according to the comparison result. Intelligent drug recommendation, control and patient state real-time monitoring are realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of medical monitoring, and in particular relates to a clinical monitoring management method and system. Background Art

[0002] In modern medical environments, especially in high-risk departments such as intensive care units and cardiovascular medicine departments, real-time monitoring and medication management of patients are essential. Existing monitoring systems usually rely on manual monitoring of multiple physiological parameters such as electrocardiograms, blood pressure, and pulse oximetry in real time. This monitoring method has the following problems:

[0003] (1) Alarm fatigue: Due to the independent analysis of multiple physiological parameters, the false alarm rate is high, which increases the workload of medical staff and may also affect patient safety.

[0004] (2) Information islands: The lack of effective data integration and sharing mechanisms among various monitoring devices makes it difficult for doctors to fully understand the patient's condition.

[0005] (3) Irregular medication management: Currently, rational medication use mainly relies on the experience and expertise of medical personnel, which is subject to subjective limitations and often results in time-consuming and risky outcomes. Summary of the invention

[0006] In order to solve the above problems existing in the prior art, the present invention provides a clinical monitoring management method and system.

[0007] The purpose of the present invention can be achieved by the following technical solutions:

[0008] S1: Obtain the patient's personal information data and code, establish a connection relationship between the personal information data and the monitoring device information data to form connection information, and establish a database table according to the connection information;

[0009] S2: Calculate feature vector data through a preprocessing model according to the code, calculate recommended medication code through a drug prediction and recommendation model according to the feature vector data, and transmit the recommended medication code to a human-computer interaction interface through an intelligent terminal;

[0010] S3: acquiring the patient's vital characteristic data in real time through the monitoring device, and storing the vital characteristic data in the database table according to the connection information, wherein the vital characteristic data includes body weight, fat-free body weight, heart rate, basic characteristic data, and blood oxygen;

[0011] S4: the intelligent terminal retrieves the database table according to the recommended medication code to obtain the required drug dosage data, obtains the syringe capacity data and the drug dosage data, and then calculates the pump speed data through the pump speed model according to the body weight, the required drug dosage data, the syringe capacity data and the drug dosage data. The intelligent terminal generates an adaptive signal according to the pump speed data and issues a syringe pump control instruction;

[0012] S5: The smart terminal compares the lean body weight, the heart rate, and the basic characteristic data with a preset threshold value to obtain a comparison result, and generates an adaptive signal according to the comparison result to control an infusion pump to inject the drug; the smart terminal compares the blood oxygen with a preset blood oxygen threshold to obtain a blood oxygen comparison result, generates an adaptive signal according to the blood oxygen comparison result to issue an oxygen supply machine control instruction, and generates an alarm signal according to the comparison result and the blood oxygen comparison result.

[0013] Specifically, the body resistance and reactance measurement results are obtained by a bioelectrical impedance spectrum meter, and the lean body mass is calculated based on the reactance and the resistance. The lean body mass calculation formula is:

[0014]

[0015] Wherein, FFM is fat-free body mass, H is reactance, R is resistance, a is body weight, and b is gender. When the gender is male, b=1; when the gender is female, b=0.

[0016] Specifically, the preprocessing model obtains representation data by performing feature representation through a Transformer module according to the coding, and the representation data includes diagnostic coding representation data, surgical coding representation data, and historical medication representation data. Feature vector data is constructed according to the representation data. The expressions of the diagnostic coding representation data, the surgical coding representation data, and the historical medication representation data are respectively:

[0017]

[0018] Among them, V d represents the surgical coding data, V p Represents diagnostic code representation data, V m Represents historical drug characterization data, C d Indicates the surgical code, C P Indicates the diagnosis code, C m Indicates historical medication code.

[0019] Specifically, the specific calculation steps of the drug prediction and recommendation model are as follows:

[0020] S401: performing mean aggregation on each of the feature vector data, and then concatenating the last diagnosis code representation data and the surgery code representation data to obtain concatenated data,

[0021] S402: transmitting the series data to the prediction layer of the fully connected network and calculating the predicted medication vector through a prediction algorithm;

[0022] S403: Construct a drug distribution adjacency matrix according to the predicted drug usage vector. The drug distribution adjacency matrix is ​​expressed as: I = Y*Y T , where I is the drug distribution adjacency matrix, Y is the predicted drug vector, and Y T Transpose the vector for predicting medication;

[0023] S404: Obtain the recommended medication code according to the drug distribution adjacency matrix through the ReLu activation function, and the ReLu activation function expression is: Q=ReLu(A*I*W), wherein Q is the recommended medication code, A is a defined transition probability matrix, which represents the relationship between drugs in the knowledge graph, I is the drug distribution adjacency matrix, and W is the parameter of the fully connected layer.

[0024] Specifically, the pump speed model calculates the pump speed data according to the body weight, the required drug dosage data, the syringe capacity data, and the drug dosage data through a pump speed calculation formula, and the pump speed calculation formula is:

[0025]

[0026] Among them, Y is the pump speed, A represents the required drug dose, B represents the body weight, C represents the syringe capacity data, and D represents the drug dose.

[0027] Specifically, the prediction algorithm expression is:

[0028]

[0029] Among them, Y is the predicted medication vector, W is a learnable transformation matrix as the parameter of the fully connected network, t is the number of historical diagnoses, a is the variable parameter, and V d represents the surgical coding data, V p Represents diagnostic code representation data, V m represents the historical drug characterization data, and b is the adjustment parameter.

[0030] Specifically, the drug knowledge graph construction process is as follows:

[0031] S701: collecting drug-related data from a public database, and preprocessing the drug-related data to obtain preprocessed data;

[0032] S702: Obtaining entity information through natural language processing technology according to the pre-processed data;

[0033] S703: extracting entity relationship data through a relationship joint extraction model according to the pre-processed data;

[0034] S704: Perform entity alignment and linking according to the entity information to obtain connection entity data;

[0035] S705: Constructing entity relationships for the connection entity data and the entity relationship data according to a resource description framework to obtain the drug knowledge graph.

[0036] A clinical monitoring management system, comprising: an information acquisition module, a preprocessing module, a characteristic data acquisition module, a pump speed calculation module, and a comparison module;

[0037] The information acquisition module is used to acquire the patient's personal information data and code, establish a connection relationship between the personal information data and the monitoring device information data to form connection information, and establish a database table according to the connection information;

[0038] The preprocessing module is used to calculate feature vector data through a preprocessing model according to the code, calculate a recommended medication code through a drug prediction and recommendation model according to the feature vector data, and transmit the recommended medication code to a human-computer interaction interface through an intelligent terminal;

[0039] The characteristic data acquisition module is used to acquire the patient's vital characteristic data in real time through the monitoring device, and store the vital characteristic data in the database table according to the connection information, wherein the vital characteristic data includes body weight, fat-free body weight, heart rate, basic characteristic data, and blood oxygen;

[0040] The pump speed calculation module is used for the smart terminal to retrieve the database according to the recommended medication code to obtain the required drug dosage data, obtain the syringe milliliter data and the drug dosage data, and then calculate the pump speed data through the pump speed algorithm according to the body weight, the required drug dosage data, the syringe milliliter data and the drug dosage data. The smart terminal generates an adaptive signal according to the pump speed data to control the injection pump to inject the drug at the pump speed;

[0041] The comparison module is used for the intelligent terminal to compare the lean body weight, the heart rate, and the basic characteristic data with a preset threshold value to obtain a comparison result, and to generate an adaptive signal according to the comparison result to control an infusion pump to inject medicine; the intelligent terminal compares the blood oxygen with a preset blood oxygen threshold to obtain a blood oxygen comparison result, generates an adaptive signal according to the blood oxygen comparison result to issue an oxygen supply machine control instruction, and generates an alarm signal according to the comparison result and the blood oxygen comparison result.

[0042] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a clinical monitoring management method as described above is implemented.

[0043] A storage medium containing computer executable instructions, characterized in that the computer executable instructions are used to execute a clinical monitoring management method as described above when executed by a computer processor.

[0044] The beneficial effects of the present invention are:

[0045] (1) Obtain the patient's personal information data and monitoring equipment information data, and establish a relationship between the two to obtain connection information. Create a database table based on the connection information, and store the patient's vital signs data collected by the monitoring equipment into the database table based on the connection information. The intelligent terminal transmits the patient information, vital signs data, and equipment information data to the human-computer interaction interface, realizing real-time monitoring of the patient's status and information sharing, and solving the problem of high false alarm rate due to personnel fatigue when relying solely on human monitoring of equipment.

[0046] (2) The feature vector is calculated by the preprocessing model based on the diagnosis code, surgery code, and historical medication code, and then the feature vector is input into the drug prediction and recommendation model to calculate the recommended medication code, thus solving the problems of inaccurate and untimely medication due to subjective limitations such as the experience and professional knowledge of medical personnel.

[0047] (3) By comparing the acquired vital sign data with the preset threshold value to obtain the comparison result, the intelligent terminal generates an adaptive signal based on the comparison result to control the injection pump and infusion pump to supply the drug, thus realizing the automatic supply and control of the drug and avoiding the problem of worsening of the patient's condition due to untimely human handling in the event of an emergency. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0049] Figure 1 The figure is a flow chart of a clinical monitoring management method of the present invention. DETAILED DESCRIPTION

[0050] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0051] See also Figure 1 , a clinical monitoring management method

[0052] S1: Obtain the patient's personal information data and code, establish a connection relationship between the personal information data and the monitoring equipment information data to form connection information, and establish a database table according to the connection information, wherein the code includes a diagnosis code, a surgery code, and a historical medication code;

[0053] S2: Calculate feature vector data through a preprocessing model according to the code, calculate recommended medication code through a drug prediction and recommendation model according to the feature vector data, and transmit the recommended medication code to a human-computer interaction interface through an intelligent terminal;

[0054] S3: acquiring the patient's vital characteristic data in real time through the monitoring device, and storing the vital characteristic data in the database table according to the connection information, wherein the vital characteristic data includes body weight, fat-free body weight, heart rate, basic characteristic data, and blood oxygen;

[0055] S4: the intelligent terminal retrieves the database table according to the recommended medication code to obtain the required drug dosage data, obtains the syringe capacity data and the drug dosage data, and then calculates the pump speed data through the pump speed model according to the body weight, the required drug dosage data, the syringe capacity data and the drug dosage data. The intelligent terminal generates an adaptive signal according to the pump speed data and issues a syringe pump control instruction;

[0056] S5: The smart terminal compares the lean body weight, the heart rate, and the basic characteristic data with a preset threshold value to obtain a comparison result, and generates an adaptive signal according to the comparison result to control an infusion pump to inject the drug; the smart terminal compares the blood oxygen with a preset blood oxygen threshold to obtain a blood oxygen comparison result, generates an adaptive signal according to the blood oxygen comparison result to issue an oxygen supply machine control instruction, and generates an alarm signal according to the comparison result and the blood oxygen comparison result.

[0057] In this embodiment, the monitoring device information includes the monitoring device number, the monitoring device type, the diagnosis code, the surgery code, and the historical medication code, which are encoded by a coding system. The medication code includes the drug name, drug serial number, and treatment range. The surgery code usually includes detailed information such as the type, site, method, and equipment used of the surgery. These codes help ensure the consistency and accuracy of medical procedures and play an important role in improving medical quality, promoting medical safety, and supporting medical decision-making. The basic characteristic data include blood pressure, blood sugar, blood lipids, etc.

[0058] As a preferred technical solution of the present invention, the lean body mass is measured by a bioelectrical impedance spectrum meter and the human body resistance and reactance measurement results at a frequency of 50 kHz are extracted, and the lean body mass is calculated according to the reactance and the resistance by a lean body mass calculation formula, and the lean body mass calculation formula is:

[0059]

[0060] Wherein, FFM is fat-free body mass, H is reactance, R is resistance, a is body weight, and b is gender. When the gender is male, b=1; when the gender is female, b=0.

[0061] In this embodiment, the comparison result is obtained by comparing the acquired vital sign data with the preset threshold value. The intelligent terminal generates an adaptive signal according to the comparison result to control the injection pump and the infusion pump to supply the drug, thereby realizing the automatic supply and control of the drug and avoiding the problem of worsening of the patient's condition due to untimely human handling in emergency situations.

[0062] Specifically, the preprocessing model obtains representation data by performing feature representation through a Transformer module according to the coding, and the representation data includes diagnostic coding representation data, surgical coding representation data, and historical medication representation data. Feature vector data is constructed according to the representation data. The expressions of the diagnostic coding representation data, the surgical coding representation data, and the historical medication representation data are respectively:

[0063]

[0064] Among them, V d represents the surgical coding data, V p Represents diagnostic code representation data, V m Represents historical drug characterization data, C d Indicates the surgical code, C P Indicates the diagnosis code, C m Indicates historical medication code.

[0065] Specifically, the specific calculation steps of the drug prediction and recommendation model are as follows:

[0066] S401: performing mean aggregation on each of the feature vector data, and then concatenating the last diagnosis code representation data and the surgery code representation data to obtain concatenated data,

[0067] S402: transmitting the series data to the prediction layer of the fully connected network and calculating the predicted medication vector through a prediction algorithm;

[0068] S403: Construct a drug distribution adjacency matrix according to the predicted drug usage vector. The drug distribution adjacency matrix is ​​expressed as: I = Y*Y T , where I is the drug distribution adjacency matrix, Y is the predicted drug vector, and Y T Transpose the vector for predicting medication;

[0069] S404: Obtain the recommended medication code according to the drug distribution adjacency matrix through the ReLu activation function, and the ReLu activation function expression is: Q=ReLu(A*I*W), wherein Q is the recommended medication code, A is a defined transition probability matrix, which represents the relationship between drugs in the knowledge graph, I is the drug distribution adjacency matrix, and W is the parameter of the fully connected layer.

[0070] In this embodiment, a feature vector is calculated through a preprocessing model based on the diagnosis code, surgery code, and historical medication code, and then the feature vector is input into a drug prediction and recommendation model to calculate the recommended medication code, thereby solving problems such as inaccurate and untimely medication due to subjective limitations such as the experience and expertise of medical personnel.

[0071] Specifically, the pump speed model calculates the pump speed data according to the body weight, the required drug dosage data, the syringe capacity data, and the drug dosage data through a pump speed calculation formula, and the pump speed calculation formula is:

[0072]

[0073] Among them, Y is the pump speed, A represents the required drug dose, B represents the body weight, C represents the syringe capacity data, and D represents the drug dose.

[0074] Specifically, the prediction algorithm expression is:

[0075]

[0076] Among them, Y is the predicted medication vector, W is a learnable transformation matrix as the parameter of the fully connected network, t is the number of historical diagnoses, a is the variable parameter, and V d represents the surgical coding data, V p Represents diagnostic code representation data, Vm represents the historical drug characterization data, and b is the adjustment parameter.

[0077] Specifically, the drug knowledge graph construction process is as follows:

[0078] S701: collecting drug-related data from a public database, and preprocessing the drug-related data to obtain preprocessed data;

[0079] S702: Obtaining entity information through natural language processing technology according to the pre-processed data;

[0080] S703: extracting entity relationship data through a relationship joint extraction model according to the pre-processed data;

[0081] S704: aligning and linking entities according to entity information to obtain connected entity data;

[0082] S705: Constructing entity relationships for the connection entity data and the entity relationship data according to a resource description framework to obtain the drug knowledge graph.

[0083] In this embodiment, the preprocessing includes removing noise, filling missing values ​​and unifying the format, and the entity information includes drug entities, disease entities, and gene entities.

[0084] A clinical monitoring management system, comprising: an information acquisition module, a preprocessing module, a characteristic data acquisition module, a pump speed calculation module, and a comparison module;

[0085] The information acquisition module is used to acquire the patient's personal information data, diagnosis code, operation code, and historical medication code, and establish a connection relationship between the personal information data and the monitoring device information data to form connection information and store it in the database;

[0086] The preprocessing module is used to calculate feature vector data according to the diagnosis code, the operation code, and the historical medication code through a preprocessing model, and then input the feature vector data into a drug prediction and recommendation model to calculate and obtain a recommended medication code, and transmit the recommended medication code to a human-computer interaction interface through an intelligent terminal;

[0087] The characteristic data acquisition module is used to acquire the patient's vital characteristic data in real time through the monitoring device, and store the vital characteristic data in the database according to the connection information; the vital characteristic data includes body weight, fat-free body weight, heart rate, basic characteristic data, and blood oxygen;

[0088] The pump speed calculation module is used for the smart terminal to retrieve the database according to the recommended medication code to obtain the required drug dosage data, obtain the syringe milliliter data and the drug dosage data, and then calculate the pump speed data through the pump speed algorithm according to the body weight, the required drug dosage data, the syringe milliliter data and the drug dosage data. The smart terminal generates an adaptive signal according to the pump speed data to control the injection pump to inject the drug at the pump speed;

[0089] The comparison module is used for the intelligent terminal to compare the lean body weight, the heart rate, and the basic characteristic data with a preset threshold value to obtain a comparison result, and to generate an adaptive signal according to the comparison result to control an infusion pump to inject nutrient solution and cardiotonic agent; the intelligent terminal compares the blood oxygen with a preset blood oxygen threshold to obtain a blood oxygen comparison result, and then generates an adaptive signal according to the blood oxygen comparison result to control the oxygen supply machine to supply oxygen, and generates an alarm signal according to the comparison result and the blood oxygen comparison result.

[0090] In this embodiment, the comparison result is obtained by comparing the acquired vital sign data with the preset threshold value. The intelligent terminal generates an adaptive signal according to the comparison result to control the injection pump and the infusion pump to supply the drug, thereby realizing the automatic supply and control of the drug and avoiding the problem of worsening of the patient's condition due to untimely human handling in emergency situations.

[0091] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a clinical monitoring management method as described above is implemented.

[0092] A storage medium containing computer executable instructions, characterized in that the computer executable instructions are used to execute a clinical monitoring management method as described above when executed by a computer processor.

[0093] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0094] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0095] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and 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 through 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 through the Internet).

[0096] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A clinical monitoring management method, characterized in that: include: S1: Obtain the patient's personal information data and code, establish a connection relationship between the personal information data and the monitoring device information data to form connection information, and establish a database table according to the connection information; S2: Calculate feature vector data through a preprocessing model according to the code, calculate recommended medication code through a drug prediction and recommendation model according to the feature vector data, and transmit the recommended medication code to a human-computer interaction interface through an intelligent terminal; S3: acquiring the patient's vital characteristic data in real time through the monitoring device, and storing the vital characteristic data in the database table according to the connection information, wherein the vital characteristic data includes body weight, fat-free body weight, heart rate, basic characteristic data, and blood oxygen; S4: the intelligent terminal retrieves the database table according to the recommended medication code to obtain the required drug dosage data, obtains the syringe capacity data and the drug dosage data, and then calculates the pump speed data through the pump speed model according to the body weight, the required drug dosage data, the syringe capacity data and the drug dosage data. The intelligent terminal generates an adaptive signal according to the pump speed data and issues a syringe pump control instruction; S5: The smart terminal compares the lean body weight, the heart rate, and the basic characteristic data with a preset threshold value to obtain a comparison result, and generates an adaptive signal according to the comparison result to control an infusion pump to inject the drug; the smart terminal compares the blood oxygen with a preset blood oxygen threshold to obtain a blood oxygen comparison result, generates an adaptive signal according to the blood oxygen comparison result to issue an oxygen supply machine control instruction, and generates an alarm signal according to the comparison result and the blood oxygen comparison result.

2. The clinical monitoring management method according to claim 1, characterized in that: The body resistance and reactance measurement results are obtained by using a bioelectrical impedance spectrum meter, and the lean body mass is calculated based on the reactance and the resistance. The lean body mass calculation formula is: Wherein, FFM is fat-free body mass, H is reactance, R is resistance, a is body weight, and b is gender. When the gender is male, b=1; when the gender is female, b=0.

3. The clinical monitoring management method according to claim 1, characterized in that: The preprocessing model obtains representation data by performing feature representation through a Transformer module according to the coding, and the representation data includes diagnostic coding representation data, surgical coding representation data, and historical medication representation data. Feature vector data is constructed according to the representation data. The expressions of the diagnostic coding representation data, the surgical coding representation data, and the historical medication representation data are respectively: Among them, V d represents the surgical coding data, V p Represents diagnostic code representation data, V m Represents historical drug characterization data, C d Indicates the surgical code, C P Indicates the diagnosis code, C m Indicates historical medication code.

4. The clinical monitoring management method according to claim 1, characterized in that: The specific calculation steps of the drug prediction and recommendation model are as follows: S401: performing mean aggregation on each of the feature vector data, and then concatenating the last diagnosis code representation data and the surgery code representation data to obtain concatenated data, S402: transmitting the series data to the prediction layer of the fully connected network and calculating the predicted medication vector through a prediction algorithm; S403: Construct a drug distribution adjacency matrix according to the predicted drug usage vector. The drug distribution adjacency matrix is ​​expressed as: I = Y*Y T , where I is the drug distribution adjacency matrix, Y is the predicted drug vector, and Y T Transpose the vector for predicting medication; S404: Obtain the recommended medication code according to the drug distribution adjacency matrix through the ReLu activation function, and the ReLu activation function expression is: Q=ReLU(A*I*W), wherein Q is the recommended medication code, A is a defined transition probability matrix, which represents the relationship between drugs in the knowledge graph, I is the drug distribution adjacency matrix, and W is the parameter of the fully connected layer.

5. The clinical monitoring management method according to claim 1, characterized in that: The pump speed model calculates the pump speed data according to the body weight, the required drug dosage data, the syringe capacity data, and the drug dosage data through a pump speed calculation formula. The pump speed calculation formula is: Among them, Y is the pump speed, A represents the required drug dose, B represents the body weight, C represents the syringe capacity data, and D represents the drug dose.

6. The clinical monitoring management method according to claim 4, characterized in that: The prediction algorithm expression is: Among them, Y is the predicted medication vector, W is a learnable transformation matrix as the parameter of the fully connected network, t is the number of historical diagnoses, a is the variable parameter, and V d represents the surgical coding data, V p Represents diagnostic code representation data, V m represents the historical drug characterization data, and b is the adjustment parameter.

7. The clinical monitoring management method according to claim 4, characterized in that: The drug knowledge graph construction process is as follows: S701: collecting drug-related data from a public database, and preprocessing the drug-related data to obtain preprocessed data; S702: Obtaining entity information through natural language processing technology according to the pre-processed data; S703: extracting entity relationship data through a relationship joint extraction model according to the pre-processed data; S704: Perform entity alignment and linking according to the entity information to obtain connection entity data; S705: Constructing entity relationships for the connection entity data and the entity relationship data according to a resource description framework to obtain the drug knowledge graph.

8. A clinical monitoring management system, characterized in that: include: Information acquisition module, preprocessing module, characteristic data acquisition module, pump speed calculation module, comparison module; The information acquisition module is used to acquire the patient's personal information data and code, establish a connection relationship between the personal information data and the monitoring device information data to form connection information, and establish a database table according to the connection information; The preprocessing module is used to calculate feature vector data through a preprocessing model according to the code, calculate a recommended medication code through a drug prediction and recommendation model according to the feature vector data, and transmit the recommended medication code to a human-computer interaction interface through an intelligent terminal; The characteristic data acquisition module is used to acquire the patient's vital characteristic data in real time through the monitoring device, and store the vital characteristic data in the database table according to the connection information, wherein the vital characteristic data includes body weight, fat-free body weight, heart rate, basic characteristic data, and blood oxygen; The pump speed calculation module is used for the smart terminal to retrieve the database according to the recommended medication code to obtain the required drug dosage data, obtain the syringe milliliter data and the drug dosage data, and then calculate the pump speed data through the pump speed algorithm according to the body weight, the required drug dosage data, the syringe milliliter data and the drug dosage data. The smart terminal generates an adaptive signal according to the pump speed data to control the injection pump to inject the drug at the pump speed; The comparison module is used for the intelligent terminal to compare the lean body weight, the heart rate, and the basic characteristic data with a preset threshold value to obtain a comparison result, and to generate an adaptive signal according to the comparison result to control an infusion pump to inject medicine; the intelligent terminal compares the blood oxygen with a preset blood oxygen threshold to obtain a blood oxygen comparison result, generates an adaptive signal according to the blood oxygen comparison result to issue an oxygen supply machine control instruction, and generates an alarm signal according to the comparison result and the blood oxygen comparison result.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, a clinical monitoring management method as described in any one of claims 1-7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute a clinical monitoring management method as described in any one of claims 1-7 when executed by a computer processor.

Citation Information

Patent Citations

  • Critical illness monitoring, infusion controlling, diagnosis and treatment integrated system and control method thereof

    CN101496923A

  • Intravenous infusion pump control system, intravenous infusion pump control method and storage medium

    CN115282401A

  • Drug recommendation method based on attention mechanism and global retrieval

    CN116153528A

  • Systems and methods for precision or personal pharmaceutical dosing

    US11367519B1

  • Method for injecting drug into patient using infusion pump, server and computer-readable recording medium

    WO2018070771A1