Artificial intelligence-based hemodialysis data processing method and system

Abstract

The present disclosure relates to an artificial intelligence-based hemodialysis data processing method, device, and system. The method of the present disclosure includes a step of extracting identification information already stored for a target patient, a step of acquiring health condition information measured for the target patient, a step of mapping the extracted identification information and the acquired health condition information, a step of acquiring recommended hemodialysis demand amount information for the day calculated for the target patient based on the mapped identification information and health condition information, and a step of outputting the acquired recommended hemodialysis demand amount information for the day.

Description

[Technical field]

[0001] The present disclosure relates to hemodialysis data processing, and more particularly to an artificial intelligence-based hemodialysis data processing method, device, and system. [Background technology]

[0002] Hemodialysis is a treatment for patients with end-stage chronic renal failure that takes more than four hours per session and must be continued three times a week for the rest of their lives.

[0003] It is necessary to continuously monitor and record the patient's vital signs and the hemodialysis machine's sensor data during hemodialysis.

[0004] However, hemodialysis machines transmit data in a standard file format for exchanging medical data (i.e., HL7 format), but the file format of the data sent in this way differs from that of the electronic medical record system used by medical staff, making it difficult for humans to read and interpret.

[0005] In addition, the nursing and treatment records of patients undergoing hemodialysis must be continuously recorded, but this is usually done using hemodialysis nursing records written by hand on paper, or medical staff must directly input the records into the nursing record screen of the computer's electronic medical record software.

[0006] However, during this process, there is a possibility that patient data may be stored differently than it actually was due to errors or omissions. This could lead to serious accidents during subsequent treatment, so measures to prevent this are required. Summary of the Invention [Problem to be solved by the invention]

[0007] The present disclosure has been made in consideration of the above circumstances, and its purpose is to provide a hemodialysis data processing method and system that can provide customized hemodialysis information based on artificial intelligence and monitor the hemodialysis process based on artificial intelligence.

[0008] The problems to be solved by the present disclosure are not limited to those mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0009] To achieve the above-mentioned technical objectives, the artificial intelligence-based hemodialysis data processing method according to the present disclosure includes a step of extracting identification information already stored for a target patient, a step of acquiring health condition information measured for the target patient, a step of mapping the extracted identification information and the acquired health condition information, a step of acquiring recommended hemodialysis requirement information for the day calculated for the target patient based on the mapped identification information and health condition information, and a step of outputting the acquired recommended hemodialysis requirement information for the day.

[0010] In this case, the step of acquiring information on the recommended hemodialysis requirement for that day includes a step of predicting dry weight data based on data on changes in weight and blood pressure of the target patient during a preset period using an artificial intelligence model, a step of correcting the predicted dry weight data by reflecting the learning result of labeling a standard dry weight based on the type, dose, and duration of medication taken by the target patient, and a step of calculating a recommended hemodialysis requirement for that day based on the corrected dry weight data. In the step of calculating the recommended hemodialysis requirement for that day, if an event occurs during a previous hemodialysis process of the target patient that changes the health condition of the target patient and the hemodialysis requirement of the target patient is adjusted due to the event, the step of calculating the recommended hemodialysis requirement for that day can be finally calculated by correcting the recommended hemodialysis requirement for that day based on the learning result of the adjusted hemodialysis requirement data.

[0011] In addition, the method disclosed herein further includes a step of monitoring the hemodialysis process of the target patient based on the recommended hemodialysis requirement information for that day, and a step of acquiring vital signs data during the monitoring process while the hemodialysis of the target patient is progressing, and the vital signs data may include sequential data generated when the blood flow of the target patient passes through a dialyzer.

[0012] Additionally, the method of the present disclosure may further include labeling and learning clinical events for each of the sequential data using the artificial intelligence model.

[0013] In addition, the method according to the present disclosure may further include a step of acquiring data predicting vital signs due to hemodialysis of the target patient based on the acquired vital signs data, a step of generating clinical event data due to hemodialysis of the target patient based on the predicted data, and a step of outputting the generated clinical event data.

[0014] Furthermore, the method disclosed herein may further include a step of determining whether or not the target patient has a health abnormality due to hemodialysis based on the acquired vital sign data, clinical event data, and unique characteristic information related to hemodialysis, and a step of controlling so that the determination result of the presence or absence of the health abnormality is output.

[0015] In addition, the method disclosed herein further includes a step of labeling and learning sequential data at the time when the health abnormality occurred and the diagnosis and response content of a medical institution for resolving the health abnormality using the artificial intelligence model, and the judgment result of the presence or absence of the health abnormality may include the diagnosis and response content of the medical institution based on the learning result of the artificial intelligence model.

[0016] Furthermore, the artificial intelligence-based hemodialysis data processing system of the present disclosure for achieving the above-mentioned technical objectives includes at least one terminal and a server including a processor that performs data communication with the terminal, and the processor can be controlled to extract identification information already stored for a target patient, acquire health condition information measured for the target patient, map the extracted identification information and the acquired health condition information, acquire recommended hemodialysis requirement information for the day calculated for the target patient based on the mapped identification information and health condition information, and output the acquired recommended hemodialysis requirement information for the day.

[0017] In this case, when obtaining the recommended hemodialysis requirement information for that day, the processor uses an artificial intelligence model to predict dry weight data based on the change data of the weight and blood pressure of the target patient during a preset period, corrects the predicted dry weight data to reflect the learning result of labeling a standard dry weight based on the type, dose, and duration of medication taken by the target patient, and calculates the recommended hemodialysis requirement for that day based on the corrected dry weight data. If an event occurs during the target patient's previous hemodialysis process that changes the target patient's health condition and the hemodialysis requirement of the target patient is adjusted due to the event, the processor can correct and finally calculate the recommended hemodialysis requirement for that day based on the learning result of the adjusted hemodialysis requirement data.

[0018] In addition, the processor may monitor the hemodialysis process of the target patient based on the recommended hemodialysis demand information for the day, and during the monitoring process, obtain vital signs data during the progress of the hemodialysis of the target patient, and the vital signs data may include each sequential data generated as the blood flow of the target patient passes through the dialyzer.

[0019] Additionally, the processor can use the artificial intelligence model to label and learn clinical events for each of the sequential data.

[0020] Further, the processor can acquire data predicting vital signs due to hemodialysis of the target patient based on the acquired vital signs data, generate clinical event data due to hemodialysis of the target patient based on the predicted data, and control the generated clinical event data to be output.

[0021] The processor can also be controlled to determine whether or not the target patient has a health abnormality due to hemodialysis based on the acquired vital sign data, clinical event data, and unique characteristic information related to hemodialysis, and to output the determination result of the presence or absence of the health abnormality.

[0022] Furthermore, the processor uses the artificial intelligence model to label and learn sequential data at the time the health abnormality occurred and the diagnosis and response content of a medical institution to resolve the health abnormality, and the judgment result of the presence or absence of the health abnormality may include the diagnosis and response content of the medical institution based on the learning result of the artificial intelligence model.

[0023] In addition, a computer program stored on a computer-readable recording medium for execution to realize the present disclosure may further be provided.

[0024] In addition, a computer-readable recording medium having a computer program for executing the method for implementing the present disclosure can be further provided. Effect of the Invention

[0025] According to the present disclosure, it is possible to provide customized hemodialysis information based on artificial intelligence.

[0026] According to the present disclosure, the hemodialysis process can be monitored based on artificial intelligence to detect or predict events such as abnormalities in the patient's health condition, thereby preventing accidents or responding quickly and accurately to any accidents that do occur.

[0027] The effects of the present disclosure are not limited to those mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the following description. [Brief description of the drawings]

[0028] [Figure 1] FIG. 1 is a diagram illustrating an artificial intelligence-based hemodialysis data processing system according to one embodiment of the present disclosure. [Diagram 2] FIG. 2 is a configuration block diagram of the server in FIG. [Diagram 3] FIG. 3 is a configuration block diagram of the processor in FIG. 2. [Figure 4] FIG. 2 is a diagram illustrating a processing process within an artificial intelligence-based hemodialysis data processing system according to one embodiment of the present disclosure. [Diagram 5] 1 is a flow chart illustrating an artificial intelligence-based hemodialysis data processing method according to an embodiment of the present disclosure. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0029] The advantages and features of the present disclosure, and the methods for achieving them, will become clear from the following detailed description of the embodiments in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments shown below, and can be realized in various different forms. However, the embodiments are provided to complete the disclosure of the present disclosure and to allow those skilled in the art to which the present disclosure pertains to fully understand the scope of the present disclosure, and the present disclosure is only defined by the scope of the claims.

[0030] The terms used in this specification are for the purpose of describing the embodiments and are not intended to limit the present disclosure. In this specification, the singular includes the plural unless otherwise specified. The terms "comprises" and / or "comprising" used in the specification do not exclude the presence or addition of one or more other components other than the components mentioned. The same reference numerals throughout the specification refer to the same components, and "and / or" includes each and every combination of one or more of the components mentioned. Even if "first", "second", etc. are used to describe various components, it is natural that these components are not limited by these terms. These terms are used simply to distinguish one component from another component. Therefore, it goes without saying that the first component mentioned below can also be the second component within the technical spirit of the present disclosure.

[0031] Unless otherwise defined, all terms (including technical and scientific terms) used herein are used as meanings commonly understood by ordinary skilled artisans in the technical field to which this disclosure belongs. Furthermore, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless clearly and specifically defined.

[0032] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

[0033] In this specification, the AI-based hemodialysis data processing device according to the present disclosure includes various devices that can perform arithmetic processing and provide a result to a user. For example, the data processing device according to the present disclosure may include at least one computer or computing device, a server device, a terminal, etc., or may be any one of them.

[0034] Here, the computer may include, for example, a notebook computer, a desktop computer, a laptop computer, a tablet PC, a slate PC, etc. equipped with a web browser.

[0035] The server device is a server that communicates with external devices and processes information, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, a web server, etc.

[0036] The portable terminal may be, for example, a wireless communication device that ensures portability and mobility, and may include any kind of handheld-based wireless communication device such as a personal communication system (PCS), a global system for mobile communications (GSM), a personal digital cellular (PDC), a personal handyphone system (PHS), a personal digital assistant (PDA), an international mobile telecommunication (IMT)-2000, a code division multiple access (CDMA)-2000, a W-code division multiple access (W-CDMA), a wireless broadband internet (WiBro) terminal, a smartphone, etc., and a wearable device such as a watch, a ring, a bracelet, an anklet, a necklace, glasses, a contact lens, or a head-mounted device (HMD).

[0037] In this specification, an information provision control model may be defined or a related platform may be constructed in relation to the artificial intelligence-based hemodialysis data processing device according to the present disclosure, which may be generated and provided by a computer based on big data and artificial intelligence technology, and may be realized by using or referring to ICT (Information and Communication Technology) technologies such as extended reality, which collectively refers to virtual reality, augmented reality, and mixed reality, and block-chain technology for security of personal information of users using the information provision device. However, it is to be made clear in advance that the detailed description of such ICT technologies in this specification refers to known technologies, and a separate description thereof will be omitted.

[0038] FIG. 1 is a diagram illustrating an artificial intelligence-based hemodialysis data processing system 1 according to an embodiment of the present disclosure.

[0039] FIG. 2 is a block diagram of the configuration of the server shown in FIG.

[0040] FIG. 3 is a configuration block diagram of the processor of FIG.

[0041] A system for providing an AI-based custom-made health functional food curation service according to an embodiment of the present disclosure may include a patient information measurement device 10, a medical institution terminal 20, a hemodialysis device 30, and a server 40. In this case, the AI-based hemodialysis data processing system 1 may also include a DB 50 that communicates with the server 40 and stores data.

[0042] Depending on the embodiment, the artificial intelligence-based hemodialysis data processing system 1 may be configured with one or more additional components in addition to the components shown in FIG. 1 in connection with performing operations related to the present disclosure.

[0043] The AI-based hemodialysis data processing process according to the present disclosure can use information provided in the form of an application provided by the server 40 or a web service via the web.

[0044] In the above, the application is provided by, for example, the server 40, and when it is executed after being downloaded and installed on the medical institution terminal 20 or the hemodialysis device 30, it can provide a related service user interface (UI) to input information on the target patient or provide various service information related to the hemodialysis service related to the present invention. At this time, the medical institution terminal 20 or the hemodialysis device 30 can output the target patient or the hemodialysis-related information of the target patient via the server 40 through the application execution screen via a display (or an augmented reality method).

[0045] In relation to this, the server 40 can provide algorithms and logic for the artificial intelligence-based hemodialysis data processing according to the present disclosure and / or related APIs (Application Programming Interfaces) and plug-ins, etc. to the patient information measuring device 10, the medical institution terminal 20, and the hemodialysis device 30.

[0046] Meanwhile, the server 40 constructs and provides a service platform for providing an artificial intelligence-based hemodialysis data processing service, and can provide a service to read patient information measured from the patient information measuring device 10 through the service platform, or to receive or output information from the medical institution terminal 20 or the hemodialysis device 30.

[0047] The patient information measurement device 10 can measure patient information such as the patient's weight, blood pressure, etc. on the day of dialysis. Such a patient information measurement device 10 can include various sensor devices such as a weight scale and a camera.

[0048] The patient information measuring device 10 can directly transmit the patient information measured on the target patient to the medical institution terminal 20.

[0049] Alternatively, the patient information measuring device 10 can transmit the patient information measured on the target patient to the server 40, and the server 40 can transmit it to the corresponding medical institution terminal 20.

[0050] In the above process, at least one of the patient information measuring device 10 and the server 40 can map the measured patient information and the target patient, and transmit the mapped information.

[0051] The medical institution terminal 20 can calculate the dry weight of the target patient and the recommended hemodialysis requirement for that day based on the patient information of the target patient measured by the patient information measurement device 10.

[0052] The medical institution terminal 20 can output the thus calculated dry weight of the subject patient and the recommended hemodialysis requirement information for that day via a screen, and can also transmit the information to the server 40.

[0053] In the above, the dry weight may refer to the appropriate weight of a patient at which blood pressure is normally maintained without edema. That is, the dry weight may refer to the normal target weight of a patient as a reference by removing water from the body through hemodialysis on the day. However, the dry weight value on the day may be individually set according to the opinion of a doctor who diagnoses the condition of the subject patient.

[0054] The medical institution terminal 20 may be a fixed terminal such as a PC, a monitor, or a digital signage, or a mobile terminal such as a smartphone, a tablet PC, or a laptop. Alternatively, the medical institution terminal 20 may be in the form of a wearable device such as a smart watch or a head-mounted display (HMD). Alternatively, the medical institution terminal 20 may be a dedicated device for medical use or for the artificial intelligence-based hemodialysis data processing service according to the present disclosure, or a device equipped with such software.

[0055] The hemodialysis device 30 stores the recommended hemodialysis requirement information for the day of the target patient sent from the server 40 in the DB, and can output the stored information via a display.

[0056] The hemodialysis machine 30 includes various sensors and can transmit to the server 40 various data collected about the subject patient during the hemodialysis process.

[0057] Each component constituting the artificial intelligence-based hemodialysis data processing system 1 of Fig. 1 may include a communication module for data communication with other components. Such a communication module may include, for example, at least one of a wired communication module, a wireless communication module, a short-range communication module, a location information module, and the like.

[0058] In the above, the wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as a Universal Serial Bus (USB), a High Definition Multimedia Interface (HDMI), a Digital Visual Interface (DVI), recommended standard-232 (RS-232), power line communication, or a plain old telephone service (POTS).

[0059] The wireless communication module may include a Wi-fi (registered trademark) module, a Wibro (wireless broadband) module, as well as wireless communication modules supporting various wireless communication methods such as GSM (Global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), and 4G (Generation), 5G, and 6G.

[0060] The short-range communication module is for short-range communication and can support short-range communication using at least one of Bluetooth (registered trademark), RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee (registered trademark), NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity) (registered trademark), Wi-Fi Direct, and Wireless Universal Serial Bus (Wireless USB) technologies.

[0061] The location information module is, for example, a module for acquiring the location (or current location) of the medical institution terminal 20, and representative examples thereof include a GPS (Global Positioning System) module or a Wi-Fi (registered trademark) module. For example, by utilizing a GPS module, the location of the medical institution terminal 20 can be acquired using a signal sent from a GPS satellite. As another example, by utilizing a Wi-Fi (registered trademark) module, the location of the medical institution terminal 20 can be acquired based on information of the Wi-Fi (registered trademark) module and a wireless AP (Wireless Access Point) that transmits or receives a wireless signal. If necessary, the location information module can perform any function of the other modules of the communication module to obtain data regarding the location of the medical institution terminal 20 instead or in addition. The location information module is a module used to acquire the location (or current location) of the medical institution terminal 20, and is not limited to a module that directly calculates or acquires the location of the medical institution terminal 20. Such a location information module can be built into the medical institution terminal 20 and provide the location information of the medical institution terminal 20 to the server 40.

[0062] The server 40 will be described with reference to FIG.

[0063] The server 40 may include a memory 210 and at least one processor 220 in communication with the memory 210 .

[0064] At this time, the memory 210 of Fig. 2 may be the DB 50 of Fig. 1 or a separate storage medium in the form of a cloud. Meanwhile, the memory 210 does not necessarily have to be one.

[0065] The processor 220 can perform data communication and control operations with the components of the artificial intelligence-based hemodialysis data processing system 1 according to the present invention shown in FIG.

[0066] The processor 220 can perform or control various operations, processes, data configuration and provision on the service platform that interacts with other components. The processor 220 can store data for various algorithms or programs that reproduce algorithms that can be used in the process in the memory 210, and can perform various operations for providing the AI-based hemodialysis data processing service according to the present disclosure using the data stored in the memory 210.

[0067] The processor 220 generates and learns at least one learning model related to an AI-based hemodialysis data processing service, and can use the model to provide the AI-based hemodialysis data processing service according to the present disclosure using user information as an input. Big data and AI technology can be used in the learning process. Furthermore, the processor 220 can process sensitive personal information, disease information, and the like, among the information of the target patient, using blockchain technology, if necessary. In addition, the relevant information according to the present disclosure can be provided to be used through various ICT technologies such as the Internet of Things (IoT), eXtended Reality (XR), and the like.

[0068] The operation of the processor 220 will now be described with reference to FIG.

[0069] Referring to FIG. 3, the processor 220 may include a parser module 310, an encryption module 320, a user management module 330, a service module 340, an administrator authentication module 350, an artificial kidney room management module 360, and the like.

[0070] However, the present invention is not limited thereto, and some of the modules shown in FIG. 3 may be combined into one module, or may be separated.

[0071] The parser module 310 can include an HL7 parser and an xlsx parser.

[0072] The HL7 parser can read from memory the HL7 format file generated by the hemodialysis machine 30. The HL7 parser can check whether the file thus read complies with the HL7 Version 2 file standard (check whether a specific string exists in the first line of the file) and extract data and attributes from the file thus read from memory. The HL7 parser can then encrypt the data using the encryption module and transmit the encrypted data to the patient information management module of the service module 340.

[0073] The xlsx parser can read an Excel file downloaded from the website of an external testing institution from the memory, and can check whether the Excel file thus read complies with the format of the blood test result sheet. The xlsx parser can extract data and attributes from the file read from the memory, encrypt the data using the encryption module, and transmit the encrypted data to the patient information management module of the service module 340.

[0074] The encryption module 320 can select an encryption method, which can include encryption methods such as SHA256, SHA512, SEED, etc. The encryption module 320 can generate / store / read / delete an encryption key according to the selected encryption method, and can encrypt and decrypt data according to the selected encryption method.

[0075] The user management module 330 can change the user's login password and store the user's connection records (connection time, logout time, IP address, MAC address, etc.).

[0076] The service module 340 may include at least one of a patient information management module, a dialysis schedule management module, a blood test management module, a drug management module, a consumables management module, a handover items management module, an evaluation materials management module, and the like.

[0077] First, the patient information management module can encrypt / decrypt the personal information of the target patient using the encryption module. The patient information management module can manage the personal information of the target patient and can inquire about infectious diseases / diseases imported from overseas by communicating with public institution servers (e.g., the National Health Insurance Service).

[0078] The dialysis schedule management module has the function of connecting hemodialysis patients with beds, and the function of reserving / changing / deleting dialysis schedules and times for hemodialysis patients.

[0079] The blood test management module can automatically generate scheduled test dates for blood tests for target patients according to the test cycle (e.g., 1 month, 3 months, 6 months, 12 months, etc.), and automatically judge test results (e.g., if they fall outside the pre-set normal range) and recommend follow-up tests to medical staff (e.g., retest in 2 days, 2 weeks, 1 month, etc.). The blood test management module can classify stored blood test results into normal and abnormal results and generate reports.

[0080] The drug management module can perform the function of accumulating and managing the drug prescribed to the patient according to the dosage and period, visualizing the drug and dosage by component based on the standard code of the drug ingredient (e.g., dosage by drug along the time axis), and visualizing the severity of symptoms or test results preset by the user at the same time.

[0081] The consumables management module can register / change / delete the consumables list, manage the purchase / use / damage / alteration of consumables related to hemodialysis, set the minimum stock of consumables, and report the purchase list when the stock of consumables falls below the minimum.

[0082] The handover management module allows users to create / modify / delete the creator, recipient, target patient, and handover details, and to confirm and record that the recipient has accepted the handover.

[0083] In addition, the evaluation material management module can manage evaluation materials.

[0084] The administrator identification module 350 can register / modify / delete users, set the scope of program use for each user, output a user connection record report, and initialize a user's login password.

[0085] The artificial kidney room management module 360 ​​can register / change / delete information on the hemodialysis machine of the artificial kidney room, and can register / change / delete the operating hours and medical treatment schedule of the artificial kidney room.

[0086] 4 and 5 are diagrams for explaining an artificial intelligence-based hemodialysis data processing process according to an embodiment of the present disclosure.

[0087] FIG. 4 illustrates the overall process in the artificial intelligence-based hemodialysis data processing system 1.

[0088] According to the AI-based hemodialysis data processing system 1 of the present invention, basic information of a subject patient, disease information of the subject patient, bed reservation information, etc. can be integrated and managed. At this time, methods such as login, face recognition, fingerprint recognition, QR code recognition, NFC, etc. can be used. Meanwhile, the AI-based hemodialysis data processing system 1 of the present invention can monitor vital signs of a subject during the hemodialysis process, detect abnormal symptoms based on an AI model, and quickly respond to them.

[0089] Referring to FIG. 4, first, the patient information measuring device 10 and the hemodialysis device 30 can be linked together.

[0090] As described above, the patient information measuring device 10 identifies information of a target patient through face recognition or QR code (registered trademark) recognition of the patient, and reads the identified information of the target patient from the DB 50 via the server 40, and can manage the information in an integrated manner during examination / bed movement. Here, the bed is one of the components of the hemodialysis device 30, and refers to the part used for hemodialysis of the patient.

[0091] In the present disclosure, the target patient is not simply recognized, but only the target patient who visited on a pre-specified date can be targeted for recognition such as facial recognition by referring to the schedule information of the target patient. In other words, there may be a procedure for verifying whether the visitor (patient) is assigned to the current visitor session before facial recognition.

[0092] The patient information measurement device 10 can measure the patient's health condition information such as the patient's weight and blood pressure on the day of dialysis and map it with the identified patient information. The information mapped in this way can be transmitted to the medical institution terminal 20 (or via the server 40).

[0093] Therefore, the medical institution terminal 20 can calculate the recommended dialysis requirement for the target patient on that day based on the dry weight based on the transmitted information, and the recommended dialysis requirement for the day based on the dry weight calculated in this manner can be sent to the server 40 and transmitted to the hemodialysis device 30.

[0094] The hemodialysis device 30 is a display module, i.e., a display arranged near the hemodialysis device 10 / bed, which can display the dialysis demand and patient data of the patient of the bed. The patient's bed can be automatically designated as a rule base by the server 40 that receives the patient data from the patient information measuring device 10, taking into consideration the presence or absence of illness of the target patient visiting the ward, the bed preparation time (by disinfection, cleaning, etc.), the dialysis demand, the dialysis schedule, the dialysis time for each visiting patient, the urgency (priority) for each patient, etc., and automatic matching between the target patient and the bed can be performed by identifying the target patient.

[0095] According to one embodiment of the present disclosure, the patient information measurement device 10 can include an artificial intelligence model separately, and can use the artificial intelligence model to calculate and compute the hemodialysis requirement for the target patient on that day.

[0096] That is, the patient information measurement device 10 is equipped with an artificial intelligence model, and can receive input of target patient information, calculate the recommended dialysis requirement for the patient on that day, and transmit the calculated amount of dialysis requirement for the patient to the server 40 and the hemodialysis device 30. At this time, the patient information measurement device 10 can transmit the calculated recommended dialysis requirement for the day together with the target patient's identification information and measured health condition information to the medical institution terminal 20 and receive confirmation from the medical institution.

[0097] In relation to the artificial intelligence learning in the present disclosure, the server 40 can learn the health condition data of the target patient, such as weight change data and blood pressure change data, during any preset period, and predict the dry weight of the patient through this. In this case, the server 40 can learn by labeling the ideal dry weight using input data such as the type of medication being taken, the dosage, and the duration of medication as learning factors.

[0098] According to another embodiment, the predicted dry weight of the target patient through the AI ​​learning can be used to correct the recommended dialysis requirement calculated on the day of hemodialysis. For example, the recommended dialysis requirement calculated on the day is based on health information, i.e., dry weight, measured on the day, and therefore the dry weight measured on the day can be compared with the predicted dry weight of the target patient based on AI, and the predicted dry weight of the target patient based on AI can be used as a weighting value for the dry weight measured on the day to correct the dry weight measured on the day. The corrected dry weight of the target patient can be used as a reference for correcting the recommended dialysis requirement calculated for the target patient on the day.

[0099] On the other hand, the server 40 can make adjustments such as recalculating and reducing the dialysis demand that has already been calculated based on health condition events that occur from each patient's previous dialysis records (e.g., a drop in blood pressure during hemodialysis, headaches, dizziness, etc.).

[0100] The server 40 can recalculate and adjust the previously calculated dialysis demand based on the dry weight correction and the health status events.

[0101] In relation to the artificial intelligence learning, the present disclosure may utilize common models such as LSTM of the RNN method, Transformer, etc., but is not limited to these.

[0102] The server 40 can monitor the vital signs (blood pressure, pulse, temperature) data measurement results of the patient during hemodialysis, and can perform anomaly detection or prediction during the progress of hemodialysis using an artificial intelligence model.

[0103] The hemodialysis machine 30 may be equipped with at least one sensor device, which allows for measuring / collecting real-time patient data, such as vital signs, blood pressure, blood flow rate, pulse, vascular access status, etc., of the subject patient.

[0104] Specifically, the hemodialysis machine 30 can transmit and store the measured and collected data in a machine management DB.

[0105] The server 40 is equipped with the above-mentioned artificial intelligence models (anomaly detection model and event prediction model) and can detect abnormal symptoms of the patient during hemodialysis by reflecting the patient's vital signs and individual characteristics collected in real time from the device management DB of the hemodialysis device 30, and can control the medical institution terminal 20 and the hemodialysis device 30 to output related information to the display.

[0106] The anomaly detection model and event prediction model described above may be included as a component of the processor 220.

[0107] The AI ​​model according to the present disclosure can predict the near future vital signs of a hemodialysis patient, such as in 10 minutes or 20 minutes, and can detect abnormalities when they occur and recommend and provide corresponding actions. Such recommended actions can also be provided as a service by labeling and learning the corresponding measures in advance through the AI ​​model. In the above process, the model can measure the blood pressure, blood flow rate, pulse, body temperature, etc. of the vascular access (the pressure of the blood where the needle is inserted), predict the degree of stenosis / closure of the vascular access, and predict the above items in 10 minutes / 20 minutes / 30 minutes.

[0108] In conjunction with the learning of the artificial intelligence model in the server 40, sequential patient data (see Table 1) collected from sensors in the hemodialysis machine 30 can be received in real time as the hemodialysis progresses.

[0109] [Table 1] JPEG2025504792000003.jpg230170JPEG2025504792000004.jpg95170

[0110] As shown in Table 1, the hemodialysis device 30 can collect sequential data (e.g., about 27 types of data from 160 sensors in the dialyzer, such as blood flow, blood velocity, and pressure changes) that are generated when the blood flow of the target patient passes through the dialyzer, and transmit the collected data to the server 40. However, the data is not limited to the contents shown in Table 1. The server 40 can label each piece of sequential data in Table 1 with a clinical event and use the data as learning data. Here, a clinical event can mean an abnormal symptom that appears in the patient when a specific piece of sequential data occurs, such as a drop in blood pressure, chest pain, or headache.

[0111] The server 40 can generate predictive events such as those listed below, and can provide services to display them as acute (prediction of the possibility of stroke / cerebral hemorrhage when blood pressure rises suddenly during hemodialysis), chronic (based on data measured during hemodialysis, prediction of the possibility of future complications when the status quo is maintained), etc.

[0112] That is, the server 40 can label and learn sequential data at the time when an abnormal symptom occurs and a diagnosis that a medical team should make to resolve the abnormal symptom.

[0113] The operation of the artificial intelligence model according to the present disclosure can include an anomaly presence / absence prediction model and an anomaly judgment model.

[0114] The anomaly judgment model can be a model called gradient boosting that applies multiple models simultaneously, but is not limited to this. For example, an RNN-based model or a transformer can also be used.

[0115] On the other hand, when multiple models are used, the output value can be calculated using an average calculation method or a voting method (a method in which the output is determined by a majority vote of the results between multiple models), but is not limited to these.

[0116] Encryption can be performed using a RESTful API when transmitting and receiving signals between the components that make up the artificial intelligence-based hemodialysis data processing system 1 according to the present disclosure.

[0117] For example, when a hemodialysis machine or bed is installed in a home, it is necessary to remotely monitor whether the hemodialysis machine is operating or not. For this purpose, a Rest API is used for encrypted communication between the hemodialysis machine in the home and a monitoring terminal (for example, at least one of the medical institution terminal 20 and the server 40), and when encrypted data is transmitted, it can be decrypted and output on the receiving side. In addition, data can be transmitted and received between the terminal and the server (server, nurse terminal, and hemodialysis machine) using the RESTful API. However, the encryption method is not limited to the above-mentioned examples, and a web-based SSL (Secure Sockets Layer) method can also be used.

[0118] Data can be transmitted in an encrypted state from the hemodialysis device 30 to the device management DB, the device management DB can decrypt the data and store it as a file in its own DB directory, and the device management DB can transmit the data to the server 40 again in an encrypted state.

[0119] A separate device for detecting changes in the condition of a dialysis patient on the bed can be used to detect whether there is an abnormality in the target patient. That is, the change in the health condition of a dialysis patient using an auxiliary device can be detected during hemodialysis to detect abnormalities.

[0120] In the above, as an example of the assisting device, a camera is used to recognize the face of a patient, and then changes in facial expression are input as data to predict a drop / rise in blood pressure from the amount of change, and if the blood pressure drops / rises below a threshold, it can be determined that there is an abnormality. Also, even if the blood pressure does not drop / rise below / above the threshold, if the amount of change in blood pressure fluctuates rapidly to a value greater than a predetermined value, it can be determined that there is an abnormality.

[0121] As another example of an assistive device, a wearable device (e.g., wrist ring, 3-axis gyro sensor, etc.) can be used to detect abnormalities by collecting pulse / movement data from the patient. For example, the presence or absence of abnormalities in cardiac function or cardiovascular system (stroke, angina, myocardial infarction) can be determined based on pulse, oxygen saturation, muscle spasms, and other movement data collected from the wearable device.

[0122] In addition, when an audio input device such as a microphone in the bed or a wearable device is used, audio data of the patient can be collected, and the collected audio data can be processed using STT (Speech to Text) and NLP (Natural Language Processing) to be used to detect abnormalities in the patient. In the above, the NLP-processed audio data can be directly transmitted to the medical institution terminal 20 and used as a reference for monitoring the patient's condition.

[0123] In addition, the wearable device can detect abnormalities in the patient's motion data, such as the patient falling off the bed. Detection of abnormalities in the patient's motion data can be performed by comparing the patient's motion with a threshold value set based on the average value of a large number of patient movements during the hemodialysis process, and if the patient's motion exceeds the threshold value, an abnormality can be detected or determined.

[0124] Meanwhile, the above-mentioned abnormality detection or determination methods can be appropriately combined.

[0125] In this manner, when the auxiliary device is utilized, the abnormality detection results determined from the above-mentioned artificial intelligence model and the abnormality detection results determined from the auxiliary device are collected, and the presence or absence of an abnormality is finally determined using a multiple result mixing method such as an average value or majority voting method, and this can be controlled to be output via the display of the medical institution terminal 20 and the hemodialysis device 30.

[0126] In FIG. 5, the artificial intelligence based hemodialysis data processing method according to an embodiment of the present disclosure is described based on the processor 220 for the convenience of the applicant's description, but is not limited thereto.

[0127] In step S101, the processor 220 can extract previously stored identifying information for the subject patient.

[0128] In step S103, the processor 220 can obtain measured health condition information for the subject patient.

[0129] At step S105, the processor 220 can map the extracted identification information and the acquired health condition information for the target patient.

[0130] In step S107, the processor 220 can obtain the recommended hemodialysis requirement information for the day calculated for the target patient based on the mapped information.

[0131] In step S109, the processor 220 can be controlled to output the mapped information and the obtained recommended hemodialysis requirement information for the day for the target patient.

[0132] In step S107, when acquiring the recommended hemodialysis requirement information for the day, the processor 220 predicts dry weight data based on the change data of the weight and blood pressure of the target patient during a preset period using an artificial intelligence model, corrects the predicted dry weight data by reflecting the learning result of labeling a standard dry weight based on the type, dose and duration of the medicine taken by the target patient, and calculates the recommended hemodialysis requirement for the day based on the corrected dry weight data. In this case, when an event occurs during a previous hemodialysis process of the target patient that changes the health condition of the target patient and the hemodialysis requirement of the target patient is adjusted due to the event, the processor 220 can correct the recommended hemodialysis requirement for the day based on the learning result of the adjusted hemodialysis requirement data and finally calculate it.

[0133] In the above, the processor 220 can monitor the hemodialysis process of the target patient according to the finally calculated recommended hemodialysis demand for the day, and can obtain vital signs data during the monitoring process while the hemodialysis of the target patient is in progress.

[0134] In the above, vital signs data can include sequential data generated as the subject patient's blood flow passes through a dialyzer.

[0135] In the above, the processor 220 can use an artificial intelligence model to learn by labeling each of the sequential data with a clinical event.

[0136] In the above, the processor 220 can control to acquire vital sign prediction data due to hemodialysis of the target patient based on the acquired vital sign data, generate clinical event data due to hemodialysis of the target patient based on the generated vital sign prediction data, and output the generated clinical event data.

[0137] In the above, the processor 220 can be controlled to determine whether or not the target patient has a health abnormality due to hemodialysis based on at least one of the target patient's vital sign data, clinical event data, and unique characteristic information related to hemodialysis, and to output the determination result of whether or not the target patient has a health abnormality due to hemodialysis.

[0138] In the above, the processor 220 can use the artificial intelligence model to label and learn in advance sequential data at the time when the health abnormality occurs and the diagnosis and response content of a medical institution to resolve the health abnormality, and the judgment result of the presence or absence of the health abnormality can include the diagnosis and response content of the medical institution based on the learning result of the artificial intelligence model.

[0139] In the above, the processor 220 can encrypt the information and data obtained for the target patient using a Restful API.

[0140] According to at least one of the various embodiments of the present disclosure described above, files generated by a hemodialysis device can be automatically analyzed and linked to or stored in an electronic medical record system, and the patient's condition can be grasped in real time, thereby improving the efficiency of medical treatment, the target patient can be monitored to determine whether it is normal or abnormal and respond immediately, a nursing record can be created at the time of nursing interview with a medical staff at the patient's side undergoing hemodialysis using a mobile device, and the amount of dialysis required on the day that reflects the patient's condition on that day can be calculated using an artificial intelligence model in a patient information measuring device without a uniform judgment or a doctor's diagnosis. In addition, the artificial intelligence model in a server can be used to predict or detect abnormalities of a patient during dialysis and provide related recommended response information to respond immediately when an event occurs, and an auxiliary device can be additionally used to increase the reliability of the prediction result of the artificial intelligence model's abnormality detection / anticipated event.

[0141] The steps of the method or algorithm described in connection with the embodiments of the present disclosure may be implemented directly in hardware, in software modules executed by hardware, or in a combination thereof. The software modules may also be present in a Random Access Memory (RAM), a Read Only Memory (ROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), a Flash Memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer readable storage medium known in the art to which the present disclosure pertains.

[0142] Although the embodiments of the present disclosure have been described above with reference to the accompanying drawings, those skilled in the art to which the present disclosure pertains can understand that the present disclosure can be embodied in other specific forms without changing the technical spirit or essential features thereof. Therefore, the above-described embodiments should be understood as illustrative in all respects and not restrictive.

Claims

1. A method for processing hemodialysis data based on artificial intelligence, which is performed by an electronic device, comprising: Retrieving previously stored identifying information for a patient of interest; obtaining measured health status information for the subject patient; mapping the extracted identity information and the obtained health status information; obtaining a calculated recommended hemodialysis requirement for the target patient based on the mapped identification information and health status information; outputting the obtained recommended hemodialysis requirement information for the day; The present invention relates to an artificial intelligence-based hemodialysis data processing method.

2. The step of obtaining the recommended hemodialysis requirement information for the day includes: Using an artificial intelligence model, predicting dry weight data based on the weight and blood pressure change data of the subject patient during a preset period of time; A step of correcting the predicted dry weight data by reflecting the learning result of labeling the standard dry weight based on the type, dose and duration of the medicine taken by the subject patient; calculating a recommended hemodialysis requirement for that day based on the corrected dry weight data; Including, The artificial intelligence-based hemodialysis data processing method of claim 1, wherein the step of calculating the recommended hemodialysis demand for the day comprises, when an event occurs during a previous hemodialysis process of the target patient that changes the health condition of the target patient and the hemodialysis demand of the target patient is adjusted due to the event, correcting the recommended hemodialysis demand for the day based on the result of learning the adjusted hemodialysis demand data, and finally calculating the recommended hemodialysis demand for the day.

3. monitoring the hemodialysis process of the subject patient according to the recommended hemodialysis requirement information for that day; acquiring vital signs data during the course of hemodialysis of the subject patient; Further comprising:

2. The method of claim 1, wherein the vital sign data includes sequential data generated when the blood flow of the subject patient passes through a dialysis machine.

4. 4. The method of claim 3, further comprising labeling each of the sequential data with a clinical event using an artificial intelligence model to learn the sequential data.

5. obtaining data predicting hemodialysis vital signs of the subject patient based on the obtained vital signs data; generating hemodialysis clinical event data for the subject patient based on the predicted data; outputting the generated clinical event data; The method of claim 3, further comprising:

6. determining whether the subject has a health abnormality due to hemodialysis based on the acquired vital sign data, clinical event data, and unique characteristic information related to hemodialysis; a step of controlling the output of the determination result of the presence or absence of the health abnormality; The method of claim 3, further comprising:

7. The method further includes labeling and learning sequential data at the time when the health abnormality occurs and a diagnosis and response content of a medical institution for resolving the health abnormality using an artificial intelligence model; The artificial intelligence-based hemodialysis data processing method according to claim 6, wherein the judgment result of the presence or absence of a health abnormality includes the diagnosis and response contents of the medical institution based on the learning result of the artificial intelligence model.

8. A computer-readable recording medium storing a program for causing a computer, which is hardware, to execute the artificial intelligence-based hemodialysis data processing method according to any one of claims 1 to 7.

9. At least one terminal; a server including a processor for data communication with the terminal; Including, The processor, Extracting previously stored identifying information for the subject patient; Obtaining health condition information measured for the subject patient; Mapping the extracted identity information and the obtained health status information; Obtaining recommended hemodialysis requirement information for the target patient for the day calculated based on the mapped identification information and health condition information; Controlling to output the acquired recommended hemodialysis requirement information for the day; Artificial intelligence-based hemodialysis data processing system.

10. The processor, When obtaining the recommended hemodialysis requirement information for the day, Using an artificial intelligence model, predicting dry weight data based on the weight and blood pressure change data of the subject patient during a preset period of time; The predicted dry weight data is corrected to reflect the results of labeling the standard dry weight based on the type, dose, and duration of the medication taken by the subject patient, and Based on the corrected dry weight data, the recommended hemodialysis requirement for the day is calculated. The artificial intelligence-based hemodialysis data processing system of claim 9, characterized in that when an event occurs during a previous hemodialysis process of the target patient that changes the health condition of the target patient and the hemodialysis volume of the target patient is adjusted due to the occurred event, the recommended hemodialysis requirement volume for that day is corrected based on the results of learning the adjusted hemodialysis volume data, and finally calculated.

11. the processor monitors the hemodialysis process of the subject patient according to the recommended hemodialysis requirement information for the day, and acquires vital signs data during the monitoring process while the hemodialysis of the subject patient is in progress; 10. The AI-based hemodialysis data processing system of claim 9, wherein the vital sign data includes sequential data generated when the blood flow of the subject patient passes through a dialyzer.

12. The processor, The AI-based hemodialysis data processing system according to claim 11, further comprising: labeling each of the sequential data with a clinical event using an AI model for learning.

13. The processor, obtaining data predicting hemodialysis vital signs for the subject patient based on the obtained vital signs data; generating hemodialysis clinical event data for the subject patient based on the predicted data; The artificial intelligence-based hemodialysis data processing system according to claim 11, further comprising a control for outputting the generated clinical event data.

14. The processor, determining whether the subject has a health abnormality due to hemodialysis based on the acquired vital sign data, clinical event data, and unique characteristic information related to hemodialysis; The AI-based hemodialysis data processing system according to claim 11, further comprising a control unit for outputting the determination result of the presence or absence of the health abnormality.

15. The processor, Using an artificial intelligence model, label and learn sequential data at the time when the health abnormality occurred and the diagnosis and response content of the medical institution for resolving the health abnormality; The artificial intelligence-based hemodialysis data processing system of claim 14, wherein the judgment result of the presence or absence of a health abnormality includes the diagnosis and response contents of the medical institution based on the learning result of the artificial intelligence model.

Images