Method, program, and device for providing transfer service of emergency patients and monitoring of hospitalized patients on basis of electrocardiograms

Abstract

The invention discloses a method, a program and a device for providing a transfer service of an emergency patient and monitoring of an inpatient on the basis of electrocardiogram. The method comprises the following steps: acquiring electrocardiogram data of the emergency patient at a set time interval; calculating a predicted value corresponding to the possibility of occurrence of each of a plurality of diseases on the basis of the electrocardiogram data using a pre-learned neural network model; calculating a disease severity for grading the first-aid patient on the basis of the predicted value; and selecting a target mechanism or a target facility suitable for diagnosing and treating the first-aid patient according to the calculated severity of the disease.

Description

Technical Field

[0001] This disclosure discloses a transfer service for emergency patients based on electrocardiogram

[0002] A method for monitoring hospitalized patients, in particular, a method using a pre-learned neural network

[0003] The network model predicts the likelihood of heart disease based on electrocardiogram data and

[0004] Symptoms allow emergency patients to be transferred to the hospital most suitable for treatment. Background Art

[0005] The emergency medical service system can be roughly divided into emergency treatment before arriving at the hospital and emergency treatment within the hospital.

[0006] In particular, emergency treatment before arriving at the hospital is carried out in the order of occurrence of emergency patients, call, rescue, on-site treatment and transfer of emergency patients, and includes rapid discharge within a specified time.

[0007] The first step is to mobilize and secure ambulances sufficient for transfer, as well as appropriate emergency treatment in the ambulance. Next, emergency treatment in the hospital includes emergency room treatment, hospitalization treatment, and diagnosis and treatment in emergency medical institutions.

[0009] In the Republic of Korea, the purpose of the emergency medical system before arriving at a hospital is to

[0010] The emergency center first aid team (or emergency medical technicians) provide professional emergency treatment to

[0011] Improve survival rates and further provide patient-centered prevention and management of emergency medical services on the scene

[0012] At this time, the emergency center paramedics need to check the ECG in order to confirm the patient's condition.

[0013] ECG, blood oxygen saturation (Spo2), body temperature and blood pressure.

[0014] The clinical importance of cardiovascular and cerebrovascular disease diagnosis is very great, so it is equipped with

[0015] Related equipment for measuring electrocardiograms include electrocardiogram measuring instruments, electrocardiogram monitors (for monitoring patients), advanced external defibrillators, etc.

[0016] Recently, due to the aging of the population and the sharp increase in cardiovascular diseases, various accidents have increased in South Korea.

[0017] As a result, more and more patients suffer from cardiac arrest before arriving at the hospital.

[0018] The results of this study showed that the survival rate of patients with cardiac arrest before arriving at the hospital was 2% to 17%.

[0019] The rate is lower than that of European and American countries, and has not changed much compared with past records.

[0020] According to a report on emergency medical treatment by the Industrial Development Agency, if the initial emergency treatment is completed well, the recovery rate of emergency patients will increase from about 20% to about 50%.

[0021] Unlike general patients, emergency treatment within 30 minutes from the moment of illness or injury has a significant impact on the patient's life. Therefore, emergency treatment should be started at the scene of the illness or injury and should not be interrupted during the transfer. After arriving at the hospital, medical teams in various fields also need to provide intensive treatment in the shortest possible time.

[0022] In particular, when an emergency situation related to heart disease occurs, it is necessary to quickly transfer the emergency patient to a hospital that can provide treatment through an accurate diagnosis in the emergency treatment stage before arriving at the hospital. Among emergency patients related to heart disease, myocardial infarction patients need to undergo vascular surgery (PCI) within 2 hours, but there is no method to immediately know the location of a hospital that can perform PCI surgery in the emergency treatment stage before arriving at the hospital.

[0023] If an emergency center ambulance transfers a myocardial infarction patient to a hospital that cannot perform PCI surgery, the emergency center ambulance cannot be used for the inter-hospital transfer (transfer) of the emergency patient and a private ambulance must be used, which may consume a lot of time in the transfer process of the emergency patient.

[0024] Furthermore, even if an emergency patient with myocardial infarction takes an ambulance from the emergency center, the emergency center paramedics need to make multiple phone calls to the hospital where the patient can be transferred in order to select a hospital that can perform PCI surgery. This communication process can delay the emergency response time or prevent appropriate treatment.

[0025] More importantly, it is difficult for paramedics at the emergency center to distinguish patients with simple chest pain from patients with myocardial infarction based on the results of electrocardiogram measurements. As a result, they are unable to distinguish patients who must undergo PCI surgery from patients who do not necessarily undergo PCI surgery. If all patients, including patients with simple chest pain, are transferred to hospitals that can perform PCI surgery, not only will the efficiency of emergency response be reduced, but emergency medical resources such as transfer time or PCI surgery preparation work will also be wasted, which will actually cause problems in the appropriate treatment of patients with myocardial infarction. Summary of the invention

[0026] Technical issues

[0027] The present disclosure aims to solve the problems of the aforementioned background technology. The purpose of the present disclosure is to provide a method that uses a pre-learned neural network model to predict the likelihood of heart disease based on electrocardiogram data and to transfer emergency patients to the target institution or facility that is most suitable for diagnosis and treatment according to emergency symptoms.

[0028] However, the technical problems to be solved by the present disclosure are not limited to the aforementioned problems, and other problems not mentioned above can be clearly understood from the following description.

[0029] Technical Solution

[0030] According to an embodiment of the present disclosure for achieving the above-mentioned problem, a method for providing transfer services for emergency patients and monitoring of inpatients based on electrocardiograms is provided. The method may include the following steps: acquiring electrocardiogram data of emergency patients at predetermined time intervals; using a pre-learned neural network model to calculate prediction values ​​corresponding to the likelihood of onset of each of a plurality of diseases based on the electrocardiogram data; calculating the severity of the disease used to classify the emergency patients based on the prediction values; and selecting a target institution or facility suitable for diagnosing and treating the emergency patients using the calculated severity of the disease.

[0031] Alternatively, the step of calculating the severity of the disease for grading emergency patients based on the predicted value may include the following steps: grasping the changing trend of the predicted value and determining the level of the severity of the disease based on the grasped changing trend and the characteristics of the multiple diseases.

[0032] Alternatively, the step of grasping the changing trend of the predicted value and determining the level of severity of the disease based on the grasped changing trend and the characteristics of the multiple diseases may include the following steps: selecting multiple judgment methods for grasping the changing trend of the predicted value based on the characteristics of the multiple diseases; and determining the level of severity of the disease based on the changing trend grasped according to the selected judgment methods.

[0033] Alternatively, the judgment method is one of the following judgment methods: a method for judging whether the predicted value calculated by the neural network model is an upward trend, a method for judging whether the predicted value is a downward trend or repeatedly rises and falls, a method for judging using the slope of the rising curve of the predicted value, a method for judging whether the predicted value deviates from a set cutoff, a method for marking the predicted value on a curve graph and then calculating the area size and judging whether it deviates from the set size.

[0034] Alternatively, the step of selecting a target institution suitable for treating the emergency patient using the calculated disease severity may include the following steps: using the disease severity of the emergency patient measured according to the disease severity grading method used jointly by the emergency personnel and the medical team and the disease severity calculated based on the predicted value, the emergency patient is divided into a first patient who needs a specific operation or a second patient who does not need a specific operation; based on location and traffic information including at least one of the location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to the hospital, a plurality of candidate hospitals for treating the emergency patient are extracted from a hospital group matching the grading; and using accommodation capacity information including at least one of the complexity of the emergency room, emergency facility information, or medical team manpower information of each of the plurality of candidate hospitals, the suitability of the plurality of candidate hospitals is calculated and a transfer plan is formulated according to the hospital priority based on the calculated suitability.

[0035] Alternatively, the first patient may include at least one of a patient who needs to undergo surgery that can only be performed by a specific hospital or a specific medical team, or a patient whose disease severity calculated based on the predicted value is determined to be above a preset benchmark for each disease.

[0036] Alternatively, the step of extracting a plurality of candidate hospitals for treating the emergency patient from a hospital group matching the level based on location and traffic information including at least one of the location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to the hospital may include the following steps: calculating expected transfer time information of a plurality of hospitals included in the hospital group matching the level using the location and traffic information; and extracting a plurality of candidate hospitals for treating the emergency patient from the hospital group matching the level based on the expected transfer time information.

[0037] Alternatively, the step of calculating the suitability of the multiple backup hospitals using the accommodation capacity information including at least one of the complexity of the emergency rooms, emergency facility information or medical team manpower information of the multiple backup hospitals, and formulating a transfer plan based on the hospital priority based on the calculated suitability may also include the following step: providing a communication service to confirm with the N hospitals selected according to the hospital priority whether to accommodate the patient.

[0038] Another embodiment of the present disclosure is a computer program stored in a computer-readable storage medium. When the computer program is executed on one or more processors, it performs multiple actions of providing emergency patient transfer services and inpatient monitoring based on electrocardiograms. The multiple actions may include the following actions: obtaining electrocardiogram data of emergency patients at set time intervals; using a pre-learned neural network model to calculate prediction values ​​corresponding to the likelihood of onset of multiple diseases based on the electrocardiogram data; calculating the severity of the disease used to classify the emergency patients based on the prediction values; and selecting a target institution or facility suitable for diagnosing and treating the emergency patients using the calculated disease severity.

[0039] On the other hand, the present invention discloses an embodiment of a computing device that provides emergency patient transfer services and inpatient monitoring based on cardiac electrocardiograms, comprising: a processor, including at least one core; and a memory, including multiple program codes executable by the processor; as the program codes are executed, the processor obtains the electrocardiogram data of the emergency patient at a set time interval, uses a pre-learned neural network model to calculate predicted values ​​corresponding to the likelihood of onset of multiple diseases based on the electrocardiogram data, calculates the severity of the disease used to classify the emergency patient based on the predicted values, and uses the calculated disease severity to select a target institution or facility suitable for diagnosing and treating the emergency patient.

[0040] Effects of the Invention

[0041] The present invention discloses an embodiment of a method for providing emergency patient transfer services and inpatient monitoring based on electrocardiograms. The method uses a pre-learned neural network model to quickly and accurately predict the likelihood of heart disease based on electrocardiogram data, and grasps the severity of the emergency patient's disease based on the predicted trend of changes in the likelihood of heart disease and the characteristics of multiple diseases. The patient who needs specific surgery is then distinguished based on the grasped severity of the disease. The emergency patient is transferred to the target institution or facility that is most suitable for diagnosis and treatment according to the emergency symptoms of the patient thus distinguished, thereby further improving the appropriateness of emergency treatment for each emergency symptom. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a block diagram of a computing device according to an embodiment of the present disclosure.

[0043] Figure 2 This is a block diagram for explaining the configuration of a system for providing emergency patient transfer services and inpatient monitoring based on electrocardiograms according to an embodiment of the present disclosure.

[0044] Figure 3 It is used to illustrate the process of grasping the change trend by using the neural network model of an embodiment of the present disclosure.

[0045] Figure 4 The flowchart is used to illustrate a method for providing emergency patient transfer services and inpatient monitoring based on electrocardiograms according to an embodiment of the present disclosure.

[0046] Figure 5 The flowchart is used to explain in detail a method of selecting a target institution or a target facility suitable for treating an emergency patient according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0047] The disclosure is described in detail below with reference to the accompanying drawings so that a person of ordinary skill in the art (hereinafter referred to as "a person of ordinary skill in the art") can easily run the embodiments of the disclosure. The embodiments disclosed in the disclosure are used to enable a person of ordinary skill in the art to utilize or implement the contents of the disclosure. Therefore, various variations of the embodiments of the disclosure are obvious to a person of ordinary skill in the art. That is, the disclosure can be implemented in various different forms and is not limited to the following embodiments.

[0048] The same or similar reference numerals throughout the specification of the present disclosure represent the same or similar elements. Moreover, reference numerals of parts not related to the description of the present disclosure may be omitted in the drawings for the purpose of clearly describing the present disclosure.

[0049] The term "or" used in the present disclosure does not mean an exclusive "or" but an inclusive "or". That is, if the present disclosure does not specify otherwise or its meaning is unclear in the context of the sentence, "x utilizes a or b" should be understood to mean one of the natural inclusive substitutions. For example, if the present disclosure does not specify otherwise or its meaning is unclear in the context of the sentence, "x utilizes a or b" can be interpreted as one of the situations where x utilizes a or the situation where x utilizes b or the situation where x utilizes a and b.

[0050] The term "and / or" used in the present disclosure should be understood to refer to or include all possible combinations of more than one of the listed related concepts.

[0051] The terms "include" and / or "comprising" used in this disclosure should be understood to mean the presence of specific features and / or elements. However, the terms "include" and / or "comprising" should be understood to not exclude the presence or addition of more than one other features, other elements and / or their combinations.

[0052] If the disclosure does not specify or it is not clear from the context of the sentence that it indicates a singular form, the singular should generally be interpreted as including "one or more".

[0053] The term "nth (n is a natural number)" used in the present disclosure can be understood as a way of expressing the elements of the present disclosure to be distinguished from each other according to a preset benchmark such as a functional viewpoint, a structural viewpoint, or for convenience of explanation. For example, elements that perform different functions in the present disclosure can be distinguished as first elements or second elements. However, elements that are essentially the same in the technical spirit of the present disclosure but need to be distinguished for the convenience of explanation can also be distinguished as first elements or second elements.

[0054] The term "acquire" used in the present disclosure may be understood to mean not only receiving data through a wired or wireless communication network with an external device or system, but also generating data in an on-device form.

[0055] On the other hand, the term "module" or "unit" used in the present disclosure can be understood as a term referring to an independent functional unit for processing computing resources such as a computer-related entity, firmware, software or a part thereof, hardware or a part thereof, a combination of software and hardware, etc. In this case, a "module" or "unit" can be a unit composed of a single element, or a unit represented by a combination or set of multiple elements. For example, a "module" or "unit" as a protocol concept can refer to a hardware element or a set thereof of a computing device, an application program that executes a specific function of software, a process (procedure) implemented by executing software, or a set of instructions for executing a program, etc. Moreover, a "module" or "unit" as a broad concept can refer to the computing device itself that constitutes the system or an application program executed in the computing device, etc. However, the aforementioned concept is only an example, and the concept of "module" or "unit" can be variously defined within the scope that can be understood by ordinary technicians in the field based on the content of the present disclosure.

[0056] The term "model" used in this disclosure can be understood as a system implemented using mathematical concepts and language to solve a specific problem, a collection of software units used to solve a specific problem, or an abstract model of a process used to solve a specific problem. For example, a neural network "model" can refer to the entire system implemented by a neural network that has the ability to solve problems through learning. In this case, the neural network can optimize the parameters of the connecting nodes (nodes) or neurons (neurons) through learning and thus have the ability to solve problems. A neural network "model" may include a single neural network or a neural network collection composed of multiple neural networks.

[0057] The term "block" used in the present disclosure can be understood as a collection of elements that are distinguished based on various criteria such as type and function. Therefore, the elements classified as a "block" can vary in various ways depending on the criteria. For example, a neural network "block" can be understood as a collection of neural networks that includes at least one neural network. At this time, the neural networks contained in the neural network "block" can be assumed to perform specific operations in the same way. The explanation of the aforementioned terms is to help understand the present disclosure. Therefore, unless the aforementioned terms are clearly recorded as matters that limit the content of the present disclosure, they are not used in the sense of limiting the technical spirit of the content of the present disclosure.

[0058] Figure 1 is a block diagram of a computing device according to an embodiment of the present disclosure.

[0059] The computing device 100 of one embodiment of the present disclosure may be a hardware device or a part of a hardware device that performs comprehensive data processing and computing, or may be a computing environment based on software connected by a communication network. For example, the computing device 100 may be a server that is a main body that performs intensive data processing functions and shares resources, or may be a client that shares resources through interaction with a server. Moreover, the computing device 100 may also be a cloud system that performs comprehensive data processing by means of interaction between multiple servers and multiple clients. The foregoing content is merely an example related to the types of computing devices 100, and the types of computing devices 100 may be constructed in various ways within the scope that can be understood by ordinary technicians in the field based on the content of the present disclosure.

[0060] See also Figure 1 , the computing device 100 of an embodiment of the present disclosure may include a processor 110, a memory 120 and a network unit 130. However, Figure 1This is just an example, and the computing device 100 may include other elements for implementing a computing environment. Moreover, the computing device 100 may also include only a portion of the disclosed multiple elements.

[0061] The processor 110 of one embodiment of the present disclosure may be understood as a component unit including hardware and / or software for performing operations. For example, the processor 110 can read a computer program and then perform data processing for machine learning. The processor 110 can process operations such as processing input data for machine learning, extracting features for machine learning, and calculating errors based on backpropagation. The processor 110 for performing data processing as described above may include a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), a tensor processing unit (TPU), an application specific integrated circuit (ASICc), or a field programmable gate array (FPGA). The aforementioned types of processors 110 are merely examples, and the types of processors 110 can be configured in various ways within the scope that can be understood by ordinary technicians in the field based on the content of the present disclosure.

[0062] The processor 110 can use the pre-learned neural network model to diagnose and predict diseases based on the acquired electrocardiogram data of the emergency patient and transfer the emergency patient to the most suitable hospital in an emergency. At this time, the processor 110 can learn the neural network model as follows, that is, it can extract electrocardiogram features based on the electrocardiogram data and calculate the predicted value corresponding to the possibility of the occurrence of each of multiple heart diseases based on the extracted electrocardiogram features. For example, the processor 110 can learn the neural network model as follows, that is, analyze the electrocardiogram based on the electrocardiogram data and biological information including information such as gender, age, weight, and height, and infer heart disease.

[0063] Specifically, the processor 110 allows the neural network model to learn as follows, that is, inputting the electrocardiogram data and various biological information into the neural network model so that the neural network model can perceive changes in the electrocardiogram caused by arrhythmia or other heart diseases. At this time, the neural network model can learn based on an electrocardiogram data set containing multiple electrocardiogram features extracted from the electrocardiogram data and diagnostic data of arrhythmia and other heart diseases. The processor 110 can perform operations to express at least one neural network block contained in the neural network model during the learning process of the neural network model.

[0064] The processor 110 can use the neural network model generated by the aforementioned learning process to extract electrocardiogram features from the electrocardiogram data obtained from the electrocardiograph and infer electrocardiogram interpretation data based on the extracted electrocardiogram features. The processor 110 can input the electrocardiogram data and biological information including information such as gender, age, weight, and height into the neural network model learned by the aforementioned process and generate inference data, which is the inference result for the probability of heart disease. For example, after the processor 110 inputs the electrocardiogram data into the neural network model that has completed learning, it can provide prediction values ​​such as the presence or absence of arrhythmia or other heart diseases and the degree of progression.

[0065] In addition to the aforementioned examples, the types of medical data and the output of the neural network model can be constructed in a variety of ways based on the contents of this disclosure within the scope understandable to ordinary technicians in this field.

[0066] The memory 120 of an embodiment of the present disclosure may be understood as a hardware and / or software component unit that stores and manages data processed by the computing device 100. That is, the memory 120 can store any form of data generated or determined by the processor 110 and any form of data received by the network unit 130. For example, the memory 120 may include at least one storage medium in the form of a flash memory type, a hard disk type, a multimedia card micro type, a card memory, a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. Moreover, the memory 120 may also include a database system that controls and manages data with a preset system. The aforementioned type of memory 120 is merely an example, and the type of memory 120 can be variously defined within a scope that can be understood by a person of ordinary skill in the art based on the contents of this disclosure.

[0067] The memory 120 can structure and organize the data and data combinations required by the processor 110 when performing operations, and multiple program codes that can be executed by the processor 110. For example, the memory 120 can store the electrocardiogram data received through the network unit 130 described later. The memory 120 can store program codes that allow the neural network model to learn after receiving the input of medical data, program codes that allow the neural network model to infer according to the purpose of use of the computing device 100 after receiving the input of medical data, and processed data generated by executing the program codes.

[0068] The network unit 130 of an embodiment of the present disclosure can be understood as a component unit that transmits and receives data through any form of known wired wireless communication system. For example, the network unit 130 can use a wired wireless communication system such as a local area network (LAN), wideband code division multiple access (WCDMA), long term evolution (LTE), wireless broadband (WIBRO), fifth generation mobile communication (5G), ultra wide-band wireless communication (ultra wide-band), Zigbee, radio frequency (RF), wireless LAN, wireless fidelity, near field communication (NFC) or Bluetooth to transmit and receive data. The aforementioned multiple communication systems are only examples, and various wired wireless communication systems for data transmission and reception of the network unit 130 can also be applied in addition to the aforementioned examples.

[0069] The network unit 130 can receive data required by the processor 110 for operation through wired and wireless communication with any system or any client. In addition, the network unit 130 can send data generated by the operation of the processor 110 through wired and wireless communication with any system or any client. For example, the network unit 130 can receive medical data through communication with the electrocardiograph 10 including wearable devices. The network unit 130 can send output data of the neural network model and intermediate data and processed data derived during the operation of the processor 110 through communication with the aforementioned machines.

[0070] Figure 2 is a block diagram for explaining the configuration of a system for providing emergency patient transfer services and inpatient monitoring based on electrocardiogram according to an embodiment of the present disclosure. Figure 3 It is used to illustrate the process of grasping the change trend by using the neural network model of an embodiment of the present disclosure.

[0071] The system for providing an emergency patient transfer service based on an electrocardiogram includes a local device 10 and a computing device 100, but is not limited thereto.

[0072] The local device 10 is a machine capable of performing electrocardiogram measurement, and can be equipped by emergency center rescue personnel, emergency patients or ambulances. The local device 10 can use various devices capable of measuring electrocardiograms, such as wearable devices worn on the body of emergency patients and measuring and collecting various health indicators such as heart rate, body fat percentage, blood pressure, etc., portable electrocardiographs, and biosignal measuring devices. At this time, the local device 10 can measure the electrocardiogram not only in a single-lead method using a wearable device such as a watch or a small patch, but also in a 12-lead method, a 6-lead method, and other electrode combinations. Preferably, the electrocardiogram measurement time can also be set to increase or decrease according to the signal to be obtained.

[0073] The computing device 100 can use the pre-learned neural network model 200 to obtain electrocardiogram features including P wave, QRS complex wave and T wave based on the electrocardiogram data obtained from the electrocardiograph 10. In this case, the neural network model can be a neural network model learned based on at least one of the electrocardiogram features including the frequency of tachycardia, the length of the QT interval, the deviation direction of the P wave, R wave and T wave, or the QRS duration.

[0074] The computing device 100 includes a first server 110 for interpreting electrocardiograms and a second server 120 for managing emergency patients. The first server 110 and the second server 120 can operate independently or in an integrated manner.

[0075] like Figure 3 As shown, the first server 110 uses the pre-learned neural network model 200 to calculate the predicted value corresponding to the probability of onset of each of the plurality of heart diseases based on the electrocardiogram data, and calculates the severity of the disease used to classify the emergency patient based on the calculated predicted value. The first server 110 may include a classification model that allows the pre-learned neural network model 200 to calculate the predicted value corresponding to the probability of onset of each heart disease. Therefore, the first server 110 can input the electrocardiogram data into the pre-learned plurality of classification models in sequence, and then distinguish the heart diseases with high accuracy, and use each classification model to calculate the predicted value corresponding to the probability of onset of each heart disease.

[0076] For example, the neural network model can establish multiple hierarchical models corresponding to the types of heart diseases that need to be mastered and can predict the likelihood of onset of diseases such as ST-segment elevation myocardial infarction (STEMI), left ventricular systolic dysfunction (LVSD), cardiac arrest within 24 hours, and non-ST-segment elevation myocardial infarction (NSTEMI).

[0077] At this time, the predicted value provided by each grading model can be calculated as a digital value within 0 to 100. After understanding the changing trend of the predicted value of each grading model, the level of disease severity can be determined based on the understood changing trend and the characteristics of multiple diseases.

[0078] Regarding the level of disease severity, the following multiple judgment methods for grasping the changing trend of the predicted value can be selected according to the characteristics of multiple diseases, and the level of disease severity can be determined based on the changing trend grasped by the selected judgment method.

[0079] That is, the second server 120 finally determines the level of severity of the disease after selecting a judgment method from the following judgment methods according to the characteristics of the disease, wherein the judgment method is a method of judging whether the predicted value (or disease score, digital value) calculated by the neural network model is an upward trend, a method of judging whether the predicted value is a downward trend or repeatedly rises and falls, a method of judging by the steepness of the rising curve of the predicted value (such as the slope), a method of judging whether the predicted value deviates from the set cutoff, and a method of marking the predicted value on a curve graph and then calculating the area size and judging whether it deviates from the set size.

[0080] For example, the level of disease severity can be divided into four levels: first level, second level, third level and fourth level. The first level corresponds to the situation where the predicted value shows an upward trend, the second level corresponds to the situation where the predicted value repeatedly rises and falls within the set upper limit range without an upward trend, the third level corresponds to the situation where the predicted value repeatedly rises and falls between the upper limit range (for example, 70) and the set lower limit range (for example, 30), and the fourth level corresponds to the situation where the predicted value repeatedly rises and falls within the lower limit range.

[0081] The first server 110 determines the severity of the disease as the third level based on the STEMI classification model because the change trend of the predicted value repeatedly rises and falls within the upper and lower limits as the number of electrocardiogram measurements increases, and determines the severity of the disease as the first level based on the LVSD classification model because the range of the predicted value deviates from the upper limit range and shows an upward trend as the number of electrocardiogram measurements increases. Furthermore, the first server 110 determines that the change trend of the predicted value based on the classification model of cardiac arrest within 24 hours cannot be distinguished as an upward trend or a downward trend, and determines that it is impossible to grasp because the change trend of the predicted value based on the classification model of NSTEMI repeatedly rises and falls within the lower limit range, and determines that it is the fourth level.

[0082] At this time, the first server 110 can end the prediction value calculation using the neural network model 200 and terminate the electrocardiogram measurement when the number of times the severity level of the disease is determined to be the fourth level is greater than a set number of times.

[0083] The second server 120 selects a target institution or facility suitable for treating the emergency patient using the calculated disease severity and transfers the emergency patient to the selected target institution or facility. The second server 120 can communicate with the emergency call reporting center or the emergency management center and transmit dispatch information to the fire department or the emergency call safety center based on the emergency report, and can formulate a transfer plan for the emergency patient based on the emergency situation or the diagnosis and treatment environment.

[0084] The second server 120 can classify the emergency patient into a first patient who needs a specific surgery or a second patient who does not need a specific surgery according to the disease severity classification method used by the emergency personnel and the medical team, using the disease severity of the emergency patient and the disease severity calculated based on the predicted value. As an example, the disease severity classification method used by the emergency personnel and the medical team can use the Korean pre-hospital disease severity classification method (Pre-KTAS: Prehospital Korean Triage and Acuity Scale).

[0085] Table 1

[0086] Comparison of emergency center emergency teams and KTAS classification for emergency patients

[0087]

[0088] As shown in Table 1, the Korean Triage and Acuity Scale (Pre-KTAS) classifies emergency patients into Level 1 (awakening: very serious), Level 2 (emergency), Level 3 (emergency), Level 4 (quasi-emergency), and Level 5 (non-emergency: very mild) according to their criticality before arriving at the hospital, and the medical treatment time for each level is defined as immediate, within 10 minutes, 30 minutes, 60 minutes, and within 120 minutes. The smaller the level of the Korean Triage and Acuity Scale (Pre-KTAS), the higher the severity of the disease and the higher the priority of diagnosis and treatment.

[0089] Before transferring the emergency patient to the hospital, the second server 120 uses the disease severity of the emergency patient measured according to the disease severity grading method used by the emergency personnel and the medical team and the disease severity calculated based on the predicted value to distinguish the emergency patient into a first patient who needs a specific surgery or a second patient who does not need a specific surgery. For example, the second server 120 can distinguish as the first patient a patient who needs a surgery that can only be performed by a specific hospital or a specific medical team (such as a PCI surgery) or a patient whose disease severity calculated based on the predicted value is determined to be above the preset benchmark according to each disease (for example, a patient whose disease severity level based on the STEMI grading model is above the second level).

[0090] Moreover, the second server 120 can extract multiple backup hospitals for treating emergency patients from a hospital group that matches the patient classification based on location and traffic information including at least one of the location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to the hospital, calculate the suitability of the multiple backup hospitals using at least one of the accommodation capacity information including the complexity of the emergency rooms of the multiple backup hospitals, emergency facility information, or medical team manpower information, and then formulate a transfer plan based on the hospital priority order based on the calculated suitability.

[0091] Moreover, the second server 120 not only provides transfer plans and transfers emergency patients, but also provides monitoring services for hospitalized patients and can continuously judge the severity of the illness of emergency patients transferred from the emergency room. It can also make decisions such as transferring to other hospitals or transferring from general wards to intensive care units based on the judged severity of the illness.

[0092] Figure 4 The flowchart is used to illustrate a method for providing emergency patient transfer services and inpatient monitoring based on electrocardiograms according to an embodiment of the present disclosure.

[0093] See also Figure 4, the computing device 100 obtains the electrocardiogram data of the emergency patient at a set time interval based on the declaration of the emergency situation (step S10). At this time, the second server 120 transmits a link or a two-dimensional barcode that can measure and transmit the electrocardiogram to the emergency patient. If the emergency patient, family members or emergency center paramedics use the link or two-dimensional barcode to access, they can connect to the local device 10 and automatically measure the electrocardiogram of the emergency patient at periodic time intervals (for example, three minutes) and then transmit it. If the emergency patient is in a state of moving or making more movements at the periodic time interval for measuring the electrocardiogram, the second server 120 can put the electrocardiogram measurement operation on standby for a certain period of time and re-measure the electrocardiogram after some time has passed. This is because if the emergency patient is in a state of moving or making more movements, the accuracy of the measured electrocardiogram is reduced and it may be determined that it cannot be grasped when interpreting the electrocardiogram.

[0094] The second server 120 transmits the acquired electrocardiogram data to the first server 110, and the first server 110 uses the pre-learned neural network model to calculate the predicted value of the possibility of occurrence of various heart diseases such as myocardial infarction, cardiac arrest within 24 hours, arrhythmia, etc. based on the electrocardiogram data (step S20).

[0095] The first server 110 transmits the calculated predicted value to the second server 120, and the second server 120 grasps the change trend of the predicted value transmitted at a set time interval, calculates the severity of the disease used to classify the emergency patients based on the grasped change trend and the characteristics of multiple diseases (step S30), and uses the calculated disease severity to select a target institution or target facility suitable for diagnosing and treating the emergency patients (step S40).

[0096] Figure 5 The flowchart is used to explain in detail a method of selecting a target institution or a target facility suitable for treating an emergency patient according to an embodiment of the present disclosure.

[0097] See also Figure 5 The computing device 100 uses the disease severity of the emergency patient measured by the disease severity grading method used by the emergency personnel and the medical team and the disease severity calculated based on the predicted value calculated by the neural network model to classify the emergency patient into a first patient who needs a specific operation or a second patient who does not need a specific operation (step S41).

[0098] At this time, the first patient may include at least one of a patient who needs to undergo surgery that can only be performed by a specific hospital or a specific medical team, or a patient whose disease severity calculated based on the predicted value is determined to be above the preset level for each disease.

[0099] If it is the first patient, the computing device 100 extracts a plurality of candidate hospitals for treating the emergency patient from the hospital group matching the first patient based on the location and traffic information including at least one of the location of the emergency patient, the real-time traffic conditions, or the number of ambulances going to the hospital where a specific operation (e.g., PCI operation) can be performed (steps S42 and S43). At this time, the computing device 100, that is, the second server 120, can collect real-time traffic information through the ITS National Traffic Information Center, and can collect the number of ambulances going to the hospital through the vehicle navigation system operator that guides the route based on the user's real-time location information.

[0100] If it is the second patient, the computing device 100 extracts a plurality of candidate hospitals from the hospital group matching the second patient based on the location and traffic information including at least one of the emergency patient location, real-time traffic conditions, or the number of ambulances heading to the hospital according to the severity of the disease based on pre-KTAS (steps S42, S44). If the severity of the disease based on Pre-KTAS is equivalent to level 1 and level 2, the computing device 100 matches it to the circle / critical emergency center, if the severity of the disease is equivalent to level 2 and level 3, the computing device 100 matches it to the regional emergency medical center, and if the severity of the disease is equivalent to level 4 and level 5, the computing device 100 matches it to the hospital group of the regional emergency medical institution.

[0101] The computing device 100 can calculate expected transfer time information for each of the plurality of hospitals included in the hospital group matching the patient classification using the location and traffic information, and extract a plurality of candidate hospitals based on the expected transfer time information.

[0102] The computing device 100 calculates the suitability of the plurality of candidate hospitals using the accommodation capacity information including at least one of the extracted emergency room complexity, emergency facility information, or medical team manpower information of each of the plurality of candidate hospitals (step S45), and formulates a transfer plan based on the hospital priority order based on the calculated suitability (step S46). The second server 120 periodically summarizes the accommodation capacity information such as the real-time complexity, emergency facility information, and medical team manpower information of each emergency room through the homepage of each hospital or the National Emergency Diagnosis and Treatment Information Network (NEDIS).

[0103] At this time, when the computing device 100 formulates a transfer plan, it can provide communication services such as wired inquiries or voice AI inquiries for emergency medical technicians, so as to confirm whether the N hospitals selected according to the hospital priority order will accept the patient. After the computing device 100 transfers the emergency patient to the appropriate hospital according to the hospital priority order, it can pass the electrocardiogram data and analysis results (predicted values, change trends, etc.) accumulated from the emergency declaration to the final arrival at the hospital to the medical team responsible for diagnosing and treating the emergency patient. Moreover, the computing device 100 can also continuously judge the severity of the emergency patient's disease in a medical environment including the emergency room and continuously determine whether to transfer to another hospital or move from a general ward to an intensive care unit based on the judged severity of the disease, thereby providing emergency patient monitoring services for a certain period of time or until the emergency patient is treated.

[0104] As described above, the present disclosure measures the electrocardiogram of the emergency patient at periodic time intervals and uses the pre-learned neural network model to calculate the predicted value for the possibility of each heart disease, and formulates a transfer plan for the emergency patient based on the change trend of the predicted value for the possibility of the heart disease and the characteristics of multiple diseases. At this time, if the present disclosure infers that the possibility of one or more heart diseases is low based on the change trend of the predicted value, the disease severity level of the emergency patient is set to a level below the set level. If the possibility of one or more heart diseases is high, the disease severity level of the emergency patient is determined to be very high, and a transfer plan is formulated so that the emergency patient is quickly transferred to a hospital that can diagnose, treat or operate on the heart disease of the emergency patient.

[0105] Therefore, the present disclosure can use the pre-learned neural network model to provide emergency treatment and transfer plans such as hospitals and transfer routes that can perform specific operations based on the rapid and accurate prediction value of the possibility of heart disease, thereby benefiting from the rapid transfer of emergency patients without unnecessary time consumption, and can avoid wasting resources and time required for emergency treatment. More importantly, the present disclosure is not classified by emergency medical technicians (or emergency center paramedics) but can use neural network models to classify patients such as simple chest pain patients who are not myocardial infarction and myocardial infarction patients, so the appropriateness of emergency treatment for each emergency symptom can be further improved at the stage before the emergency patient arrives at the hospital.

[0106] The various embodiments of the present disclosure described above can be combined with other different embodiments and can be changed within the scope of understanding of ordinary technicians in the field according to the detailed description above. The embodiments of the present disclosure are illustrative in all aspects and should be interpreted as not restrictive. For example, each element described in a single overall form can be implemented in a dispersed manner, and similarly, each element described in a dispersed form can also be implemented in a combined form. Therefore, the meaning and scope of the invention claimed in the present disclosure and all modifications and deformations derived from its equivalent concepts should be interpreted as belonging to the scope of the present disclosure.

Claims

1. A method, executed by a computing device comprising at least one processor, for providing emergency patient transfer services and inpatient patient monitoring based on electrocardiograms, characterized in that: The following steps are involved: Obtaining electrocardiogram data of emergency patients at set time intervals; Using a pre-learned neural network model, a prediction value corresponding to the likelihood of onset of each of a plurality of diseases is calculated based on the electrocardiogram data; Calculating the severity of the disease for grading the emergency patient based on the predicted value; as well as The calculated severity of the disease is used to select a target institution or facility suitable for treating the emergency patient.

2. The method according to claim 1, characterized in that The step of calculating the severity of the disease used to grade the emergency patient based on the predicted value comprises the following steps: The changing trend of the predicted value is grasped and the severity level of the disease is determined according to the grasped changing trend and the characteristics of the multiple diseases.

3. The method according to claim 2, characterized in that The step of grasping the change trend of the predicted value and determining the severity level of the disease according to the grasped change trend and the characteristics of the multiple diseases comprises the following steps: selecting a plurality of determination methods for grasping the change trend of the predicted value according to the characteristics of the plurality of diseases; as well as The severity level of the disease is determined based on the changing trend determined by the selected judgment method.

4. The method according to claim 3, characterized in that The judgment method is one of the following judgment methods: A method for determining whether the predicted value calculated by the neural network model is an upward trend, a method for determining whether the predicted value is a downward trend or repeatedly rises and falls, a method for determining using the slope of the rising curve of the predicted value, a method for determining whether the predicted value deviates from a set cutoff value, a method for calculating the area size after marking the predicted value on a curve graph and determining whether it deviates from the set size.

5. The method according to claim 1, characterized in that The step of selecting a target institution or a target facility suitable for treating the emergency patient using the calculated severity of the disease comprises the following steps: Using the disease severity of the emergency patient measured according to the disease severity grading method used by the emergency personnel and the medical team and the disease severity calculated based on the predicted value, the emergency patient is classified into a first patient who needs a specific surgery or a second patient who does not need a specific surgery; extracting a plurality of candidate hospitals for treating the emergency patient from a group of hospitals matching the classification based on location and traffic information including at least one of the location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to the hospital; and Using the accommodation capacity information including at least one of the complexity of the emergency rooms, emergency facility information or medical team manpower information of each of the multiple backup hospitals, the suitability of the multiple backup hospitals is calculated and a transfer plan is formulated based on the hospital priority order based on the calculated suitability.

6. The method according to claim 5, characterized in that The first patient includes at least one of a patient who needs to undergo surgery that can only be performed by a specific hospital or a specific medical team, or a patient whose disease severity calculated based on the predicted value is determined to be above a preset benchmark for each disease.

7. The method according to claim 5, characterized in that The step of extracting a plurality of candidate hospitals for treating the emergency patient from a hospital group matching the classification based on the location and traffic information including at least one of the location of the emergency patient, the real-time traffic conditions, or the number of ambulances heading to the hospital comprises the following steps: Calculating expected transfer time information of a plurality of hospitals included in the hospital group matching the classification using the location and traffic information; and A plurality of candidate hospitals for treating the emergency patient are extracted from the hospital group matching the classification based on the expected transfer time information.

8. The method according to claim 5, characterized in that The step of calculating the suitability of the plurality of candidate hospitals using the accommodation capacity information including at least one of the complexity of the emergency rooms, the emergency facility information, or the medical team manpower information of the plurality of candidate hospitals, and formulating a transfer plan according to the hospital priority based on the calculated suitability further includes the following steps: A communication service is provided to confirm with the N hospitals selected according to the hospital priority whether to admit the patient.

9. A computer program stored in a computer-readable storage medium, characterized in that The computer program, when executed on one or more processors, performs a plurality of actions of providing emergency patient transfer services and inpatient patient monitoring based on electrocardiograms, The multiple actions include the following actions: Obtaining electrocardiogram data of emergency patients at set time intervals; Using a pre-learned neural network model, a prediction value corresponding to the likelihood of onset of each of a plurality of diseases is calculated based on the electrocardiogram data; Calculating the severity of the disease for grading the emergency patient based on the predicted value; as well as The calculated severity of the disease is used to select a target institution or facility suitable for treating the emergency patient.

10. A computing device for providing emergency patient transfer services and inpatient patient monitoring based on electrocardiogram, characterized in that: include: a processor comprising at least one core; and a memory including a plurality of program codes executable by the processor, As the program code executes, the processor, Obtain ECG data of emergency patients at set time intervals. Using a pre-learned neural network model, a prediction value corresponding to the likelihood of onset of each of a plurality of diseases is calculated based on the electrocardiogram data. calculating the severity of the disease used to grade the emergency patient based on the predicted value, The calculated severity of the disease is used to select a target institution or facility suitable for treating the emergency patient.

Images