Infusion system and storage medium

Abstract

The application discloses an infusion system and a storage medium. The infusion system comprises an information acquisition module, which is configured to acquire first information, second information and infusion pump parameter data of a corresponding patient when an information acquisition instruction is received; a data processing module, which is configured to input the first information, the second information and the infusion pump parameter data into a trained neural network model to obtain a target infusion speed; determine a current infusion strategy based on the target infusion speed and a current infusion speed, and send the current infusion strategy to a corresponding infusion pump; and an infusion pump, which is configured to perform an infusion operation corresponding to the current infusion strategy. The purpose of automatically and accurately adjusting the infusion speed of the infusion pump is achieved, and the safety of patient infusion is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the medical technical field, and in particular to an infusion system and a storage medium. BACKGROUND

[0002] In the process of patient infusion, if the infusion speed is too fast, it may cause adverse reactions such as pulsating headache, facial flushing, blood pressure drop, heart rate acceleration and syncope, and if the speed is too slow, it is also unable to timely input sufficient drugs for the patient, therefore, in the process of patient infusion, medical staff need to timely adjust the infusion speed according to the patient condition, but in the case of serious imbalance between doctors and patients, the response speed of medical staff will lag, therefore, it is necessary to provide an infusion system capable of automatically adjusting the infusion speed of an infusion pump. SUMMARY

[0003] The present application provides an infusion system and a storage medium to solve the problem that medical staff may be unable to timely adjust the infusion speed.

[0004] According to an aspect of the present application, an infusion system is provided, which comprises:

[0005] An information acquisition module is configured to acquire first information, second information and infusion pump parameter data of a corresponding patient in the case of receiving an infusion instruction, wherein the first information comprises age, past medical history and diagnosis information read from a patient information system, the second information comprises vital sign data acquired from a clinical monitoring device, and the infusion pump parameter data comprises a current infusion speed;

[0006] A data processing module is configured to input the first information, the second information and the infusion pump parameter data into a trained neural network model to obtain a target infusion speed, determine a current infusion strategy based on the target infusion speed and the current infusion speed, and send the current infusion strategy to a corresponding infusion pump;

[0007] An infusion pump is configured to perform an infusion operation corresponding to the current infusion strategy.

[0008] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the following infusion control method when executed:

[0009] In the case of receiving an infusion instruction, first information, second information and infusion pump parameter data of a corresponding patient are acquired, wherein the first information comprises age, past medical history and diagnosis information read from a patient information system, the second information comprises vital sign data acquired from a clinical monitoring device, and the infusion pump parameter data comprises a current infusion speed;

[0010] input the first information, the second information and the infusion pump parameter data into the trained neural network model to obtain a target infusion speed; determine a current infusion strategy based on the target infusion speed and a current infusion speed, and send the current infusion strategy to the corresponding infusion pump.

[0011] The technical scheme of the infusion system provided by the embodiment of the present application realizes the purposes of monitoring and adjusting the infusion speed of the patient in real time and accurately by analyzing the first information, the second information and the infusion pump parameter data of the patient in real time through the trained neural network model to obtain the target infusion speed, since the target infusion speed is the infusion speed determined based on the multi-aspect information of the patient, and the accuracy of the current infusion strategy determined based on the target infusion speed and the current infusion speed in the infusion pump parameter is higher.

[0012] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0014] Figure 1 is a structural block diagram of an infusion system according to an embodiment of the present application;

[0015] Figure 2 is a structural block diagram of another infusion system according to an embodiment of the present application. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the present application scheme, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0017] It should be noted that the terms "first", "second", and "third" and the like in the description and in the claims of the present application and above-described accompanying drawings are used only to distinguish similar objects, and are not necessarily used to describe a particular chronological or sequential order. It should be understood that the data thus used can be interchanged, where appropriate, so that the embodiments of the present application described herein can be carried out in sequences other than those illustrated or described herein. Furthermore, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, processes, methods, systems, products, or devices that include a series of steps or units are not necessarily limited to those clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0018] Figure 1 is a structural diagram of an infusion system according to an embodiment of the present application. The present embodiment can be applied to the scenario of automatically adjusting the infusion speed of a patient, as shown in the figure, the infusion system comprises an information acquisition module 101, a data processing module 102 and an infusion pump 103. The information acquisition module 101 is configured to acquire first information, second information and infusion pump parameter data of a corresponding patient in the case of receiving an information acquisition instruction, wherein the first information comprises age, medical history and diagnosis information read from a patient information system, the second information comprises vital sign data acquired from a clinical monitoring device, and the infusion pump parameter data comprises a current infusion speed; the data processing module 102 is configured to input the first information, the second information and the infusion pump parameter data into a trained neural network model to obtain a target infusion speed; determine a current infusion strategy based on the target infusion speed and the current infusion speed, and send the current infusion strategy to the corresponding infusion pump 103; the infusion pump 103 is configured to perform an infusion operation corresponding to the current infusion strategy. Figure 1

[0019] Wherein, the patient information system can be associated with a hospital information system (HIS) or a laboratory information system (LIS), and is used for information collection, storage, transmission, statistics, analysis, comprehensive query, report output and information sharing, and timely provision of comprehensive and accurate data.

[0020] In one embodiment, in addition to age, medical history and diagnosis information, the first information also includes one or more of gender, height, weight and clinical examination results.

[0021] The diagnosis information refers to the latest clinical diagnosis information of the patient, including one or more of operation identification, drug identification, disease identification and allergy history.

[0022] ​The clinical monitoring device includes, but is not limited to, one or more of a thermometer, a blood oxygen monitoring device, an electrocardio monitoring device, a sphygmomanometer and a breathing machine. The thermometer is used to acquire the body temperature of the patient in real time, the blood oxygen monitoring device is used to acquire the blood oxygen saturation of the patient in real time, the electrocardio monitoring device is used to acquire the heart rate of the patient in real time, and the sphygmomanometer is used to acquire the blood pressure of the patient in real time.

[0023] In an embodiment, the infusion pump parameter data includes a current infusion speed and an infusion pump identifier. Different infusion pumps correspond to different control modes, for example, the infusion speed corresponding to the infusion gear a1 of the infusion pump A can be greater than the infusion speed corresponding to the infusion gear b1 of the infusion pump B. Therefore, a corresponding relationship between the infusion gears and the infusion speeds of each infusion pump identifier is established in advance, so that when the target infusion speed is different from the current infusion speed and the target infusion speed is less than a set threshold, the data processing module 102 can determine the infusion gear corresponding to the target infusion speed according to the target infusion speed and the corresponding relationship between the infusion gears and the infusion speeds of the corresponding infusion pump identifier, and take the infusion gear as the current infusion strategy; the infusion pump 103 adjusts the infusion gear to the infusion gear corresponding to the current infusion strategy. The technical effect of controlling different types of infusion pumps 103 to perform accurate infusion operations is achieved.

[0024] The embodiment of the present application realizes the purpose of accurately changing the infusion speed in real time according to the individual differences, disease differences and life sign change trends of patients, and can meet the infusion needs of various patients, for example, for severe patients, the patient can be quickly and effectively recovered, and the workload of medical staff can be reduced.

[0025] In an embodiment, the infusion contents used in the clinic are divided into several types in advance, and a neural network model is trained for each type of infusion content to improve the accuracy of the target infusion speed determination. During infusion, the information acquisition module 101 also needs to acquire the liquid identifier; the data processing module 102 determines the liquid type corresponding to the liquid identifier according to the pre-created corresponding relationship between the liquid identifier and the liquid type; determines the trained neural network model corresponding to the liquid type, and inputs the first information, the second information and the infusion pump parameter data into the trained neural network model to obtain the target infusion speed. In this embodiment, the liquid identifier is used to distinguish different liquids, such as liquids containing C medicine, liquids containing D medicine and plasma. In this embodiment, the liquid identifier can be input by the medical staff through the input device of the infusion pump 103 or the mobile terminal 104 (for reference Figure 2 ). When the medical staff inputs the liquid identifier through the mobile terminal 104, identity verification is required first, after the identity verification is passed, the information acquisition module 101 receives the input liquid identifier, and then sends the liquid identifier to the data processing module 102.

[0026] In one embodiment, the infusion system includes at least two infusion pumps 103, each corresponding to a different patient, and the at least two infusion pumps 103 can operate simultaneously.

[0027] In one embodiment, the data processing module 102 is specifically used to determine the score of vital sign data and the threshold range identifier corresponding to the score; if the threshold range identifier is a first identifier, then the first information, the second information, and the infusion pump parameter data are input into a trained neural network model to obtain the target infusion rate. In this embodiment, if the identifier of the threshold range to which the score of the vital sign data belongs is the first identifier, it indicates that the vital sign data is normal.

[0028] In one embodiment, if the threshold range is identified by a second identifier, a first alert indicating abnormal vital sign data is output, and the first information, the second information, and infusion pump parameter data are input into a trained neural network model to obtain a target infusion rate. The current infusion strategy is then determined based on the target infusion rate and the current infusion rate. If the threshold range is identified by a third identifier, a second alert indicating abnormal vital sign data is output. The infusion pump 103 is used to output the first alert and execute the current infusion strategy when the first alert is detected; and to output the second alert and terminate the current infusion operation when the second alert is detected. In this embodiment, if the identifier of the threshold range corresponding to the vital sign data score is the second identifier, it indicates that the vital sign data is abnormal, but the abnormality will not endanger the patient's life. If the identifier of the threshold range corresponding to the vital sign data score is the third identifier, it indicates that the vital sign data is abnormal, and the abnormality will endanger the patient's life. This embodiment configures corresponding processing strategies for vital sign data under different conditions, achieving the purpose of timely identification of risk factors and timely output of early warning information.

[0029] In this process, after detecting vital sign data acquired by information acquisition module 101, data processing module 102 compares the vital sign data with reference vital sign data in a preset medical database and determines a score for the vital sign data based on the comparison result. Specifically, for each vital sign data, the reference vital sign data in the preset medical database is subtracted from the vital sign data, and the ratio of this difference to the reference vital sign data is determined. Based on this ratio and a pre-established correspondence between ratios and scores, the score corresponding to this ratio is determined. The average of all vital sign data is used as the score for the corresponding patient's vital sign data, or if the score of any vital sign data is lower than a set threshold, the lowest value of all vital sign data is used as the score for the corresponding patient's vital sign data. The evaluation criteria for each vital sign data are unified through scoring.

[0030] In one embodiment, the data processing module 102 is further configured to, upon receiving infusion pump parameter data, determine whether the infusion pump parameter data exceeds a set parameter threshold; if so, output a third prompt message to the infusion pump 103 indicating that the infusion pump parameter data has exceeded the limit; the infusion pump 103 is further configured to, upon detecting the third prompt message, perform a pause infusion operation. The set parameter threshold is a safe infusion parameter threshold for the infusion pump 103. Once the data processing module 102 detects that the infusion pump parameter data exceeds this set parameter threshold, it indicates that the infusion pump 103 has malfunctioned, and therefore outputs the third prompt message indicating that the infusion pump parameter data has exceeded the limit; upon receiving the third prompt message, the infusion pump 103 stops the infusion operation. The infusion pump parameters can be infusion rate or infusion pressure. This embodiment is used to ensure that during infusion, the infusion pump 103 will not experience an excessively fast infusion rate due to malfunction of the infusion pump 103.

[0031] In one embodiment, the information acquisition module 101 is further configured to acquire an infusion rate change threshold; the infusion rate acquired upon receiving the initial signal is used as the initial infusion rate; the data processing module 102 is further configured to output a prompt message indicating that the infusion rate change exceeds the limit when the difference between the current infusion rate and the initial infusion rate is greater than the infusion rate change threshold. Since the infusion rate is adjusted in real time according to the patient's physical condition, when the difference between the current infusion rate and the initial infusion rate is greater than the infusion rate change threshold, it indicates a significant change in the patient's physical condition. Therefore, a prompt message indicating that the infusion rate change exceeds the limit is output to encourage doctors to pay close attention to the patient's condition. In this embodiment, the data processing module 102 pushes this prompt message to a designated terminal, such as a medical staff account that has subscribed to the patient's information or a client application of a nursing center in the attending physician's jurisdiction.

[0032] In one embodiment, the information acquisition module 101 is further configured to receive infusion rate limiting information; the data processing module 102 is further configured to use the infusion rate corresponding to the infusion rate limiting information as the target infusion rate when the infusion rate corresponding to the infusion rate limiting information is less than the target infusion rate. The infusion rate limiting information can be input by the user through the input device of the infusion pump or by the user through the mobile terminal 104.

[0033] In one embodiment, the infusion pump 103 is configured to send an information acquisition instruction to the information acquisition module 101 upon detecting an infusion command. This information acquisition instruction includes an infusion pump identifier. The information acquisition module 101 determines the patient identifier corresponding to the infusion pump identifier based on the infusion pump identifier and a pre-stored correspondence between patient identifiers and infusion pump identifiers. Then, it retrieves the patient's first information, second information, and infusion pump parameter data from the patient information system. Specifically, in this embodiment, the infusion pump 103 is configured to generate an infusion command upon detecting that a user presses (or touches) the infusion start button.

[0034] In one embodiment, Figure 2 This is a structural block diagram of another infusion system provided according to an embodiment of the present invention. Figure 2 As shown, the infusion system also includes a mobile terminal 104, which receives an infusion pump identifier and an infusion command for controlling the infusion pump corresponding to the infusion pump identifier. The mobile terminal 104 then sends an information acquisition command to the information acquisition module 101 based on the infusion command. This information acquisition command includes the infusion pump identifier. The information acquisition module 101 determines the patient identifier corresponding to the infusion pump identifier based on the infusion pump identifier and a pre-stored correspondence between patient identifiers and infusion pump identifiers. Then, it retrieves the patient's first information, second information, and infusion pump parameter data from the patient information system. In this embodiment, medical personnel can use the mobile terminal 104 to query the infusion pump parameter data of all patients within their access permissions.

[0035] The infusion system provided in this invention uses a trained neural network model to analyze the patient's first information, second information, and infusion pump parameters in real time to obtain a target infusion rate. Since the target infusion rate is determined based on the patient's multi-dimensional information, the accuracy of the current infusion strategy determined based on the target infusion rate and the current infusion rate in the infusion pump parameters is high, thus achieving the goal of real-time and accurate monitoring and adjustment of the patient's infusion rate.

[0036] The various embodiments of the infusion system described above can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0037] Computer programs for implementing the infusion control method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine or partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0038] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0039] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0040] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0041] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0042] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An infusion system, characterized in that, include: The mobile terminal is used to receive an infusion pump identifier and an infusion command for controlling the infusion pump corresponding to the infusion pump identifier, and to send an information acquisition command to the information acquisition module according to the infusion command. The information acquisition module is used to acquire first information, second information and infusion pump parameter data of the corresponding patient upon receiving an information acquisition instruction. The first information includes age, past medical history and diagnosis information read from the patient information system. The second information includes vital sign data acquired from clinical monitoring equipment. The infusion pump parameter data includes the current infusion rate and infusion pump identifier. The data processing module is used to input the first information, the second information, and the infusion pump parameter data into a trained neural network model to obtain the target infusion rate; determine the current infusion strategy based on the target infusion rate and the current infusion rate, and send the current infusion strategy to the corresponding infusion pump; The data processing module is further configured to: based on a pre-established correspondence between the infusion level and the infusion speed corresponding to each infusion pump identifier, when the target infusion speed is different from the current infusion speed and the target infusion speed is less than a set threshold, determine the infusion level corresponding to the target infusion speed according to the target infusion speed and the correspondence between the infusion level and the infusion speed of the corresponding infusion pump identifier, and use the infusion level as the current infusion strategy; An infusion pump is used to perform the infusion operation corresponding to the current infusion strategy. The information acquisition module is also used to acquire liquid labels; The data processing module is specifically used to determine the liquid type corresponding to the liquid identifier based on the liquid identifier and the pre-created correspondence between liquid identifiers and liquid types; determine the trained neural network model corresponding to the liquid type; and input the first information, the second information, and the infusion pump parameter data into the trained neural network model to obtain the target infusion rate. The information acquisition module is also used to receive infusion rate limiting information; The data processing module is also specifically used to take the infusion rate corresponding to the infusion rate limit information as the target infusion rate when the infusion rate corresponding to the infusion rate limit information is less than the target infusion rate.

2. The infusion system according to claim 1, characterized in that, The data processing module is specifically used for: Determine the score of the vital signs data and the threshold range identifier corresponding to the score; If the threshold range is identified as the first identifier, then the first information, the second information, and the infusion pump parameter data are input into the trained neural network model to obtain the target infusion rate.

3. The infusion system according to claim 2, characterized in that, The data processing module is also specifically used for: If the threshold range is identified as the second identifier, a first prompt message indicating abnormal vital sign data is output, and the first message, the second message, and the infusion pump parameter data are input into a trained neural network model to obtain the target infusion rate. If the threshold range is identified as a third identifier, a second prompt message indicating abnormal vital sign data is output. The infusion pump is also used to output the first prompt information when the first prompt information is detected; and to output the second prompt information and stop the current infusion operation when the second prompt information is detected.

4. The infusion system according to claim 2, characterized in that, The determination of the score for the vital signs data includes: The vital signs data are compared with reference vital signs data in a preset medical database, and the score of the vital signs data is determined based on the comparison results.

5. The infusion system according to claim 1, characterized in that, The data processing module is also used to determine whether the infusion pump parameter data is greater than a set parameter threshold when the infusion pump parameter data is received; if so, it outputs a third prompt message to the infusion pump to indicate that the infusion pump parameter data has exceeded the limit. The infusion pump is also used to pause the infusion operation upon detecting the third prompt information.

6. The infusion system according to claim 1, characterized in that, The information acquisition module is also used to acquire the infusion rate change threshold; and to take the infusion rate acquired when the initial signal is received as the initial infusion rate; The data processing module is also used to output a prompt message indicating that the infusion rate change exceeds the limit when the difference between the current infusion rate and the initial infusion rate is greater than the infusion rate change threshold.

7. The infusion system according to claim 1, characterized in that, The infusion pump is configured to send an information acquisition command to the information acquisition module upon detecting an infusion command.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the following infusion control method: Receive an infusion pump identifier and an infusion command for controlling the infusion pump corresponding to the infusion pump identifier, and send an information acquisition command according to the infusion command; Upon receiving an information acquisition instruction, the system acquires the first information, the second information, and the infusion pump parameter data for the corresponding patient. The first information includes the patient's age, past medical history, and diagnostic information read from the patient information system. The second information includes vital sign data acquired from the clinical monitoring equipment. The infusion pump parameter data includes the current infusion rate and the infusion pump identifier. The first information, the second information, and the infusion pump parameter data are input into a trained neural network model to obtain the target infusion rate; the current infusion strategy is determined based on the target infusion rate and the current infusion rate, and the current infusion strategy is sent to the corresponding infusion pump; The method further includes: Based on the pre-established correspondence between the infusion level and the infusion rate corresponding to each infusion pump identifier, when the target infusion rate is different from the current infusion rate and the target infusion rate is less than a set threshold, the infusion level corresponding to the target infusion rate is determined according to the target infusion rate and the correspondence between the infusion level and the infusion rate of the corresponding infusion pump identifier, and the infusion level is used as the current infusion strategy. The method further includes: Obtain a liquid identifier; determine the liquid type corresponding to the liquid identifier based on the liquid identifier and the pre-created correspondence between liquid identifiers and liquid types; determine the trained neural network model corresponding to the liquid type, and input the first information, the second information, and the infusion pump parameter data into the trained neural network model to obtain the target infusion rate; The method further includes: Receive infusion rate limit information; if the infusion rate corresponding to the infusion rate limit information is less than the target infusion rate, take the infusion rate corresponding to the infusion rate limit information as the target infusion rate.

Images