Methods, programs, and apparatus for providing emergency patient transport services and hospital patient monitoring based on electrocardiograms.

Abstract

The present disclosure relates to a method, program, and apparatus for providing emergency patient transport services and inpatient monitoring based on electrocardiograms, including the steps of acquiring electrocardiogram data of emergency patients at predetermined time intervals, calculating a predicted value corresponding to the likelihood of occurrence of each of a plurality of diseases based on the electrocardiogram data using a pre-trained neural network model, calculating a severity level for classifying the emergency patient based on the predicted value, and using the calculated severity level to select a target institution or facility suitable for treating the emergency patient.

Description

[[TECHNICAL FIELD]]

[0001] The content of the present disclosure relates to a method for providing emergency patient transfer service and inpatient monitoring based on electrocardiograms, and specifically to a method of using a pre-trained neural network model to predict the probability of heart disease occurrence based on electrocardiogram data, and transferring an emergency patient to an optimal hospital for emergency symptom-specific medical treatment. [[BACKGROUND ART]]

[0002] The emergency medical system can be broadly divided into pre-hospital emergency treatment and in-hospital emergency treatment. In particular, pre-hospital emergency treatment proceeds through the stages of occurrence of an acute patient, notification, rescue, on-site treatment, and transfer of the acute patient, and includes securing ambulances that can be dispatched quickly within a fixed time for adequate transfer, and appropriate emergency treatment on ambulances, etc. Next, in-hospital emergency treatment includes emergency room treatment, hospitalization treatment and medical care in emergency medical institutions.

[0003] In the case of the present country, the fire department 119 pre-hospital emergency medical system is intended to increase the survival rate by providing professional emergency treatment performed by 119 paramedics (or emergency rescuers), and furthermore to provide patient-centered preventive and management emergency medical services on site. Here, 119 paramedics grasp electrocardiogram (ECG), oxygen saturation (Spo2), body temperature, blood pressure, etc., to confirm the patient's condition. Among them, electrocardiography has very great clinical importance for the diagnosis of cardiovascular diseases, so 119 ambulances are equipped with electrocardiogram-related equipment such as electrocardiographs, electrocardiogram monitors (for patient monitoring), and advanced cardiac defibrillators.

[0004] In recent years, in the present country, the occurrence of pre-hospital cardiac arrest patients has been increasing due to the aging of the population, the rapid increase in cardiovascular diseases, and the increase in various accidents. According to many domestic research results, the survival rate of pre-hospital cardiac arrest patients is 2 to 17%, which is lower than that in Western Europe, and there has been no significant change compared to the past. According to an emergency medical-related report from the Korea Health Industry Development Institute, it has been shown that when proper initial emergency treatment is performed, the resuscitation rate of acutely ill patients improves from the 20% range to the 50% range.

[0005] Unlike general patients, emergency treatment for critically ill patients is crucial for their survival, and treatment within 30 minutes of the onset of illness or injury can have a significant impact on their life. Therefore, emergency treatment must begin at the scene of the illness or injury and must not be interrupted during transport. Upon arrival at the hospital, intensive care by a diverse medical team must be provided within a short timeframe.

[0006] In particular, when a cardiac emergency occurs, it is necessary to quickly transfer the patient to a hospital capable of treatment based on an accurate diagnosis at the pre-hospital emergency care stage. However, among cardiac emergency patients, those with myocardial infarction must undergo percutaneous coronary intervention (PCI) within two hours, but there is no way to determine which hospitals are capable of performing PCI at the pre-hospital emergency care stage.

[0007] If a 119 ambulance transports a myocardial infarction patient to a hospital that cannot perform PCI procedures, the 119 ambulance cannot be used for the inter-hospital transfer of the emergency patient, and a private ambulance must be used instead. This can cause significant delays in the transfer process for emergency patients.

[0008] Furthermore, even if a patient suffering a myocardial infarction boards a 119 ambulance, the paramedics must make several phone calls to hospitals capable of performing PCI procedures. This communication process can delay emergency treatment or prevent appropriate treatment from being provided.

[0009] Most importantly, because 119 paramedics have difficulty distinguishing between patients with simple chest pain and those with myocardial infarction based on electrocardiogram results, and therefore cannot differentiate between patients who necessarily require PCI and those who do not, transporting all patients, including those with simple chest pain, to hospitals capable of performing PCI not only reduces the efficiency of emergency treatment but also leads to a waste of emergency medical resources such as transport time and PCI preparation, which can actually cause problems in providing appropriate treatment to patients with myocardial infarction. [Overview of the project] [Problems that the invention aims to solve]

[0010] This disclosure was devised in response to the aforementioned background technology and aims to provide a method for predicting the likelihood of cardiac disease occurring based on electrocardiogram data using a pre-trained neural network model, and for transporting emergency patients to the most suitable institution or facility for emergency treatment based on their symptoms.

[0011] However, the issues that this disclosure aims to address are not limited to those mentioned above, and other issues not mentioned can be clearly understood from the description below. [Means for solving the problem]

[0012] In order to address the aforementioned challenges, one embodiment of the present disclosure provides a method for providing emergency patient transport services and hospital patient monitoring based on electrocardiograms. The method includes the steps of: acquiring electrocardiogram data of an emergency patient at predetermined time intervals; calculating predicted values ​​corresponding to the likelihood of occurrence of each of several diseases based on the electrocardiogram data using a pre-trained neural network model; calculating a severity level for classifying the emergency patient based on the predicted values; and selecting a suitable medical institution or facility for treating the emergency patient using the calculated severity level.

[0013] As an alternative, the step of calculating the severity of the emergency patient based on the aforementioned predicted values ​​is:

[0014] The procedure may include a step of understanding the changes in the predicted values ​​and determining the severity level based on the understood changes and the characteristics of the multiple diseases.

[0015] Alternatively, the step of understanding the trend of changes in the predicted value and determining the severity level based on the understood trend of changes and the characteristics of the multiple diseases may include the step of selecting a judgment method for understanding the trend of changes in the predicted value based on the characteristics of the multiple diseases, and the step of determining the severity level based on the trend of changes understood by the selected judgment method.

[0016] As an alternative, the judgment method may be any one of the following: a method for determining whether the predicted value calculated by the neural network model is on an upward trend; a method for determining whether the predicted value is on a downward trend or alternates between downward and upward trends; a method for determining whether the predicted value is on an upward trend relative to the predicted value; a method for determining whether the predicted value is outside a previously set cutoff; and a method for determining whether the area under the graph, after displaying the predicted value, is outside a previously set size.

[0017] As an alternative, the step of selecting a suitable institution or facility for treating the emergency patient using the calculated severity may include: classifying the emergency patient into either a first patient requiring specific treatment or a second patient not requiring specific treatment, using the severity of the emergency patient measured by a severity classification commonly used by emergency personnel and medical staff, and the severity calculated based on the predicted value; extracting 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 emergency patient's location, real-time traffic conditions, or the number of ambulances heading to the hospital; and calculating the suitability of the candidate hospitals using capacity information including at least one of the emergency room congestion level, emergency facility information, or medical staff manpower information for each candidate hospital, and establishing a transfer plan based on the hospital priority order determined by the calculated suitability.

[0018] Alternatively, the first patient may include at least one of the following: a patient who requires a procedure that can only be performed through a specific hospital or medical team; or a patient whose severity, calculated based on the predicted values, is determined to be above a dictionary-defined standard for each disease.

[0019] As an alternative, the step of extracting candidate hospitals for treating the emergency patient from a group of hospitals that match 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, may include the steps of: calculating estimated transport time information for hospitals included in the group of hospitals that match the classification using the location and traffic information; and extracting candidate hospitals for treating the emergency patient from the group of hospitals that match the classification, based on the estimated transport time information.

[0020] Alternatively, the step of calculating the suitability of the candidate hospitals using capacity information that includes at least one of the following: emergency room congestion level, emergency facility information, or medical staff manpower information, and establishing a transfer plan based on the hospital priority ranking determined by the calculated suitability, may include a step of providing communication services so that the patient's availability can be confirmed for the N hospitals selected according to the hospital priority ranking.

[0021] A computer program stored on a computer-readable storage medium according to another embodiment of the present disclosure, which, when executed on one or more processors, performs operations for providing emergency patient transport services and hospital patient monitoring based on electrocardiograms, the operations including: acquiring electrocardiogram data of emergency patients at predetermined time intervals; calculating predicted values ​​corresponding to the likelihood of occurrence of each of several diseases based on the electrocardiogram data using a pre-trained neural network model; calculating a severity level for classifying the emergency patients based on the predicted values; and using the calculated severity level to select a suitable institution or facility for treating the emergency patients.

[0022] On the other hand, a computing device for providing emergency patient transfer service and inpatient monitoring based on electrocardiograms according to an embodiment of the present disclosure includes: a processor including at least one core; and a memory storing program codes executable by the processor, wherein the processor, through execution of the program codes, acquires electrocardiogram data of an emergency patient at preset time intervals, uses a pre-trained neural network model to calculate prediction values corresponding to the probability of occurrence of each of a plurality of diseases based on the electrocardiogram data, calculates a severity level for classifying the emergency patient based on the prediction values, and uses the calculated severity level to select a target institution or target facility suitable for medical treatment of the emergency patient. [Advantages of the Invention]

[0023] A method for providing emergency patient transfer service and inpatient monitoring based on electrocardiograms according to an embodiment of the present disclosure can quickly and accurately predict the probability of occurrence of heart diseases based on electrocardiogram data by using a pre-trained neural network model. After grasping the severity of an acutely ill patient based on the transition trend of changes in the predicted probability of heart disease occurrence and the characteristics of a plurality of diseases, the method can classify patients requiring specific treatment based on the grasped severity. By transferring the emergency patient to a target institution or target facility that is optimal for medical treatment corresponding to the emergency symptom of the classified patient, the present disclosure has the effect of further improving the appropriateness of emergency treatment for different emergency symptoms. [Brief Description of Drawings]

[0024] [Figure 1] It is a block diagram of a computing device according to an embodiment of the present disclosure. [Figure 2] It is a block diagram illustrating the configuration of a system that provides emergency patient transfer service and inpatient monitoring based on electrocardiograms, according to an embodiment of the present disclosure. [Figure 3]It is a diagram for explaining a process of grasping changes using a neural network model according to an embodiment of the present disclosure. [Figure 4] It is a flowchart for explaining a method of providing emergency patient transfer service and inpatient monitoring based on an electrocardiogram according to an embodiment of the present disclosure. [Figure 5] It is a flowchart for explaining in detail a method of selecting a target institution or a target facility suitable for medical treatment of an emergency patient according to an embodiment of the present disclosure. Mode for Carrying Out the Invention

[0025] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that a person having ordinary knowledge in the technical field of the present disclosure (hereinafter referred to as a person skilled in the art) can easily carry out the present disclosure. The embodiments presented in the present disclosure are provided to allow a person skilled in the art to use or practice the content of the present disclosure. Therefore, various modifications to the embodiments of the present disclosure will be apparent to a person skilled in the art. That is, the present disclosure can be embodied in various different forms, and is not limited to the following embodiments.

[0026] Throughout the specification of the present disclosure, the same or similar reference numerals in the drawings refer to the same or similar components. In addition, in order to clearly describe the present disclosure, reference numerals of parts irrelevant to the description of the present disclosure may be omitted from the drawings.

[0027] The term "or" used in the present disclosure is not intended to mean exclusive "or", but is intended to mean inclusive "or". That is, in the present disclosure, unless otherwise specified or the meaning is not clear from the context, "X uses A or B" should be understood to mean one of natural inclusive substitutions. For example, in the present disclosure, unless otherwise specified or the meaning is not clear from the context, "X uses A or B" can be interpreted as any one of the cases where X uses A, X uses B, or X uses both A and B.

[0028] The terms "and / or" as used in this disclosure should be understood to include all possible combinations of one or more of the related concepts listed.

[0029] The terms “contains” and / or “contains” as used in this disclosure should be understood to mean the presence of certain features and / or components. However, the terms “contains” and / or “contains” should be understood not to exclude the presence or addition of one or more other features, other components and / or combinations thereof.

[0030] Wherever the context does not clearly indicate otherwise or singular form in this disclosure, singular should generally be interpreted as including "one or more."

[0031] The term “nth (where n is a natural number)” as used in this disclosure can be understood as an expression used to distinguish components of this disclosure from one another based on predetermined criteria such as functional, structural, or ease of explanation. For example, components in this disclosure that perform different functional roles may be distinguished as either a first component or a second component. However, components that are substantially identical within the technical concept of this disclosure but must be distinguished for ease of explanation may also be distinguished as either a first component or a second component.

[0032] The term "acquisition" as used in this disclosure can be understood to mean not only receiving data from an external device or system via a wired or wireless network, but also generating data in an on-device form.

[0033] On the other hand, the terms "module" or "unit" as used in this disclosure can be understood as referring to an independent functional unit that processes computing resources, such as a computer-related entity, firmware, software or a part thereof, hardware or a part thereof, or a combination of software and hardware. Here, a "module" or "unit" may be a unit composed of a single element, or it may be a unit expressed as a combination or set of multiple elements. For example, as a concept, a "module" or "unit" may refer to a hardware element or set thereof of a computing device, an application program that performs a specific function of software, a processing procedure embodied by the execution of software, or a set of instructions for executing a program. Furthermore, as a broader concept, a "module" or "unit" may refer to the computing device itself that constitutes a system, or an application executed on a computing device. However, the above concepts are merely examples, and the concepts of "module" or "unit" can be defined in various ways to the extent that a person skilled in the art can understand them based on the content of this disclosure.

[0034] As used in this disclosure, the term "model" can be understood as a system embodied using mathematical concepts and language to solve a particular problem, a set of software units to solve a particular problem, or an abstract model of a processing step to solve a particular problem. For example, a neural network "model" can refer to any system embodied as a neural network that has problem-solving capabilities through learning. Here, the neural network can have problem-solving capabilities by optimizing the parameters connecting nodes or neurons through learning. A neural network "model" may include a single neural network or a set of neural networks that are combinations of multiple neural networks.

[0035] As used in this disclosure, the term "block" can be understood as a set of configurations categorized based on various criteria such as type and function. Therefore, the configurations classified as a single "block" can vary considerably depending on the criteria. For example, a neural network "block" can be understood as a set of neural networks containing at least one neural network. Here, it can be assumed that the neural networks included in the neural network "block" perform specific operations equally. The above explanations of terminology are intended to aid in understanding this disclosure. Therefore, unless the above terms are explicitly stated as limiting the content of this disclosure, it should be noted that they are not used to limit the technical ideas of this disclosure.

[0036] Figure 1 is a block diagram of a computing device according to one embodiment of the present disclosure.

[0037] A computing device 100 according to one embodiment of this disclosure may be a hardware device or part of a hardware device that performs comprehensive data processing and calculations, or it may be a software-based computing environment connected via a communication network. For example, the computing device 100 may be a server that performs intensive data processing functions and is the entity that shares resources, or it may be a client that shares resources through interaction with a server. Furthermore, the computing device 100 may be a cloud system in which multiple servers and clients interact with each other to process data comprehensively. The above description is merely an example related to the type of computing device 100, and the type of computing device 100 can be configured in a variety of ways within the scope that can be understood by a person skilled in the art based on the content of this disclosure.

[0038] Referring to Figure 1, a computing device 100 according to one embodiment of the present disclosure may include a processor 110, memory 120, and a network unit 130. However, since Figure 1 is merely an example, the computing device 100 may include other configurations to embody a computer environment. Furthermore, the computing device 100 may include only a portion of the disclosed configurations.

[0039] A processor 110 according to one embodiment of the present disclosure can be understood as a component unit including hardware and / or software for performing computing operations. For example, the processor 110 can read a computer program and perform data processing for machine learning. The processor 110 can handle computational processes such as processing input data for machine learning, feature extraction for machine learning, and error calculation based on backpropagation. A processor 110 for performing such data processing may include a central processing unit (CPU), a general-purpose graphics processing unit (GPGPU), a tensor processing unit (TPU), an application-specific integrated circuit (ASIC), or a field-programmable gate array (FPGA). The types of processors 110 described above are merely examples, and the types of processors 110 can be configured in a variety of ways within the scope understandable to those skilled in the art based on the content of the present disclosure.

[0040] The processor 110 uses a pre-trained neural network model to diagnose and predict diseases based on acquired electrocardiogram data of critically ill patients, enabling the patient to be transported to the most suitable hospital in the event of an emergency. Here, the processor 110 can be trained to extract electrocardiogram features based on the electrocardiogram data and to calculate predicted values ​​corresponding to the probability of occurrence of each of several cardiac diseases based on the extracted electrocardiogram features. For example, the processor 110 can be trained to analyze the electrocardiogram data along with biological information including information such as gender, age, weight, and height to estimate cardiac diseases.

[0041] Specifically, the processor 110 inputs electrocardiogram data and various biological information into a neural network model, allowing the neural network model to learn to sense changes in the electrocardiogram due to arrhythmias and other heart diseases. Here, the neural network model can perform learning based on an electrocardiogram dataset that includes electrocardiogram features extracted from the electrocardiogram data, and diagnostic data for arrhythmias and other heart diseases. The processor 110 can perform operations that represent at least one neural network block included in the neural network model during the learning process of the neural network model.

[0042] The processor 110 can extract electrocardiogram features from electrocardiogram data acquired from an electrocardiogram measuring device using the neural network model generated by the learning process described above, and estimate electrocardiogram interpretation data based on the extracted electrocardiogram features. The processor 110 can input electrocardiogram data and biological information including information such as gender, age, weight, and height into the neural network model learned by the process described above, and generate inference data showing the result of estimating the probability of heart disease. For example, the processor 110 can input electrocardiogram data into the learned neural network model and provide predicted values ​​such as the presence or progression of arrhythmias and other heart diseases.

[0043] In addition to the examples given above, the types of medical data and the outputs of the neural network model can be configured in a variety of ways, to the extent that a person skilled in the art can understand from the content of this disclosure.

[0044] A memory 120 according to one embodiment of the present disclosure can be understood as a component unit including hardware and / or software for storing and managing 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 type of storage medium from among flash memory type, hard disk type, multimedia card micro type, card type memory, RAM (random access memory), SRAM (static random access memory), ROM (read-only memory), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. The memory 120 may also include a database system for controlling and managing data in a predetermined manner. The types of memory 120 described above are merely examples, and the types of memory 120 can be configured in a variety of ways within the scope understandable to those skilled in the art based on the content of the present disclosure.

[0045] Memory 120 can structure and organize data, data combinations, and program code executable by processor 110 that are necessary for processor 110 to perform calculations. For example, memory 120 can store electrocardiogram data received via network unit 130, which will be described later. Memory 120 can store program code that causes a neural network model to receive medical data and perform learning, program code that causes the neural network model to receive medical data and perform inference according to the intended use of computing device 100, and processed data generated by the execution of the program code.

[0046] A network unit 130 according to one embodiment of this disclosure can be understood as a component that transmits and receives data via any known wired wireless communication system. For example, the network unit 130 can transmit and receive data using a wired wireless communication system such as a local area network (LAN), wideband code division multiple access (WCDMA), LTE (long term evolution), WiBro (wireless broadband internet), 5th generation mobile communication (5G), ultrawide-band wireless communication (ultrawide-band), ZigBee, radio frequency (RF) communication, wireless LAN (wireless LAN), Wi-Fi (wireless fidelity), near field communication (NFC), or Bluetooth®. The above-mentioned communication systems are merely examples, and a wide variety of wired wireless communication systems for data transmission and reception of the network unit 130 are applicable beyond the examples given above.

[0047] The network unit 130 can receive data necessary for the processor 110 to perform calculations via wired or wireless communication with any system or client. The network unit 130 can also transmit data generated by the processor 110's calculations via wired or wireless communication with any system or client. For example, the network unit 130 can receive medical data via communication with an electrocardiogram measuring device 10, including wearable devices. The network unit 130 can also transmit output data of a neural network model, as well as intermediate and processed data derived during the processor 110's calculation process, via communication with the aforementioned devices.

[0048] Figure 2 is a block diagram illustrating the configuration of a system that provides emergency patient transport services and hospitalized patient monitoring based on electrocardiograms, according to one embodiment of the present disclosure, and Figure 3 is a diagram illustrating the process of understanding changes using a neural network model, according to one embodiment of the present disclosure.

[0049] A system that provides emergency patient transport services based on an electrocardiogram includes, but is not limited to, a local device 10 and a computing device 100.

[0050] The local device 10 is a device capable of measuring electrocardiograms and may be provided to 119 emergency medical personnel, emergency patients, or ambulances. Such a local device 10 can be a variety of electrocardiogram measuring devices, including wearable devices worn on the emergency patient's body to measure and collect various health indicators such as heart rate, body fat percentage, and blood pressure; portable electrocardiogram measuring devices; and biosignal measuring equipment. Here, the local device 10 can measure electrocardiograms using not only single-lead methods with wearable devices such as wristwatches or patches, but also various electrode combinations such as 12-lead and 6-lead methods. It is also preferable to adjust the electrocardiogram measurement time according to the signal to be obtained.

[0051] The computing device 100 can use a pre-trained neural network model 200 to extract electrocardiogram features, including P waves, QRS complexes, and T waves, based on electrocardiogram data acquired from the electrocardiogram measuring device 10. Here, the neural network model may have been trained based on electrocardiogram features including at least one of the following: tachycardia frequency, QT interval length, P wave, R wave, and T wave deviation direction, or QRS duration.

[0052] Such a computing device 100 includes a first server 110 for electrocardiogram interpretation and a second server 120 for emergency patient management. The first server 110 and the second server 120 can be operated independently or in an integrated manner.

[0053] As shown in Figure 3, the first server 110 uses a pre-trained neural network model 200 to calculate predicted values ​​corresponding to the probability of occurrence of multiple cardiac diseases based on electrocardiogram data, and calculates the severity for classifying emergency patients based on the calculated predicted values. The first server 110 may include classification models in which the pre-trained neural network model 200 can calculate predicted values ​​corresponding to the probability of occurrence for each cardiac disease. Therefore, the first server 110 can input electrocardiogram data stepwise into multiple pre-trained classification models to classify into cardiac diseases with high accuracy, and use each classification model to calculate predicted values ​​corresponding to the probability of occurrence for each cardiac disease.

[0054] For example, neural network models can construct multiple classification models corresponding to the types of cardiac diseases they are trying to understand, and can predict the likelihood of each disease occurring, such as ST-elevation myocardial infarction (STEMI), left ventricular systolic dysfunction (LVSD), cardiac arrest within 24 hours, and non-ST segment elevation myocardial infarction (NSTEMI).

[0055] Here, the predicted values ​​provided by each classification model can be calculated as numerical values ​​between 0 and 100. After understanding the changes in the predicted values ​​of each classification model, the severity level can be determined based on the observed changes and the characteristics of multiple diseases.

[0056] The severity level can be determined by selecting one of the following judgment methods for understanding the changes in predicted values, based on the characteristics of multiple diseases, and then determining the severity level based on the changes observed using the selected judgment method.

[0057] In other words, the second server 120 selects a judgment method from among the following, depending on the characteristics of the disease, to finally determine the severity level: a method to determine whether the predicted value (or disease score, numerical value) calculated by the neural network model is on an upward trend; a method to determine whether the predicted value is on a downward trend or alternates between downward and upward trends; a method to determine using the degree of slope (e.g., gradient) of the upward curve relative to the predicted value; a method to determine whether the predicted value falls outside a previously determined cutoff; and a method to display the predicted value on a graph, calculate the size of the area, and determine whether it falls outside a previously set size.

[0058] For example, the severity levels can be divided into four levels: Level 1, which corresponds to a predicted value trending upward; Level 2, which corresponds to a predicted value repeatedly rising and falling within a pre-set upper limit without an upward trend; Level 3, which corresponds to a predicted value repeatedly rising and falling within an upper limit (e.g., 70) and a pre-set lower limit (e.g., 30); and Level 4, which corresponds to a predicted value repeatedly rising and falling within a lower limit.

[0059] Server 110, based on the STEMI classification model, sets the severity level to Level 3 because the predicted value changes repeatedly within the upper and lower limits as the number of ECG measurements increases. Based on the LVSD classification model, the predicted value range moves outside the upper limit as the number of ECG measurements increases, so the severity level is set to Level 1. Furthermore, Server 110 cannot classify the predicted value changes based on the 24-hour cardiac arrest classification model into an upward or downward trend, so it is determined to be undetectable. Based on the NSTEMI classification model, the predicted value changes repeatedly within the lower limit, so it is set to Level 4.

[0060] Here, the first server 110 can terminate the calculation of the predicted value using the neural network model 200 and stop the electrocardiogram measurement if the severity level is determined to be level 4 for a number of previously set times or more.

[0061] The second server 120 uses the calculated severity to select a suitable institution or facility for treating the emergency patient and transports the emergency patient to the selected institution or facility. Such a second server 120 is connected to a 119 reporting center or emergency situation management center and can transmit dispatch information to the fire station or 119 safety center based on the emergency situation report, and can establish a transport plan for the emergency patient based on the emergency situation or treatment environment.

[0062] The second server 120 can classify emergency patients into either a first patient requiring specific treatment or a second patient not requiring specific treatment, using the severity of the emergency patient calculated based on the severity classification used in common by emergency personnel and medical staff, and the predicted value. For example, the Pre-KTAS (Prehospital Korean Triage and Acuity Scale) method can be used as the severity classification used in common by emergency personnel and medical staff.

[0063] [Table 1] JPEG0007923890000002.jpg32169

[0064] As shown in Table 1, the Pre-KTAS (Prehospital Korean Triage and Acuity Scale) classifies emergency patients into five grades based on the severity of their condition at the prehospital stage: Grade 1 (Resuscitation: Very Severe), Grade 2 (Emergency), Grade 3 (Emergency), Grade 4 (Semi-Emergency), and Grade 5 (Non-Emergency: Very Mild). The medical treatment time for each grade is defined as immediate, 10 minutes, 30 minutes, 60 minutes, and within 120 minutes, respectively. A lower Pre-KTAS grade indicates a higher severity and higher priority for medical treatment.

[0065] Before transporting emergency patients to a hospital, the second server 120 classifies emergency patients into either a first-class patient requiring specific treatment or a second-class patient not requiring specific treatment, using the patient's severity measured by a severity classification system commonly used by emergency personnel and medical staff, and a severity calculated based on predicted values. For example, the second server 120 can classify patients as first-class patients if they require treatment that can be performed by a specific hospital or medical team (e.g., PCI procedure), or if their severity, calculated based on predicted values, is determined to be above a pre-set standard for their disease (e.g., patients with a severity level of 2 or higher based on the STEMI classification model).

[0066] Furthermore, the second server 120 can extract candidate hospitals for treating emergency patients from a group of hospitals that match the patient classification, based on location and traffic information including at least one of the following: the location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to the hospital. After calculating the suitability of the candidate hospitals using capacity information including at least one of the following: the congestion level of the emergency room, emergency facility information, or medical staff manpower information for each candidate hospital, it can then establish a transfer plan based on the hospital priority order calculated from the suitability.

[0067] Furthermore, the second server 120 not only plans and transports emergency patients, but also provides monitoring services for hospitalized patients. This allows for continuous assessment of the severity of emergency patients transported from the emergency room, and based on the assessed severity, it determines whether to transfer them to another hospital or move them from a general ward to a ward for critically ill patients.

[0068] Figure 4 is a flowchart illustrating a method for providing emergency patient transport services and hospitalized patient monitoring based on an electrocardiogram, according to one embodiment of the present disclosure.

[0069] Referring to Figure 4, the computing device 100 acquires electrocardiogram data of the emergency patient at pre-set time intervals based on the emergency situation report (S10). Here, the second server 120 can transmit a link or QR code (registered trademark) that allows for the measurement and transmission of the electrocardiogram to the emergency patient. Once the emergency patient, guardian, or 119 emergency medical personnel have completed the connection using the link or QR code (registered trademark), the server connects with the local device 10 and can automatically measure and transmit the emergency patient's electrocardiogram at periodic time intervals (e.g., 3 minutes). If the periodic time interval for electrocardiogram measurement has arrived, but the emergency patient is moving or moving around a lot, the second server 120 may wait for a certain period of time before measuring the electrocardiogram again. This is because the accuracy of the electrocardiogram measured when the emergency patient is moving or moving around a lot decreases, and it may be determined to be unreadable during electrocardiogram interpretation.

[0070] The second server 120 transmits the acquired electrocardiogram data to the first server 110, and the first server 110 uses a pre-trained neural network model to calculate predicted values ​​corresponding to the probability of occurrence of multiple cardiac diseases such as myocardial infarction, cardiac arrest within 24 hours, and arrhythmia, based on the electrocardiogram data (S20).

[0071] The first server 110 transmits the calculated predicted values ​​to the second server 120, the second server 120 grasps the changes in the predicted values ​​transmitted at pre-set time intervals, calculates the severity level for classifying emergency patients based on the grasped changes and the characteristics of multiple diseases (S30), and uses the calculated severity level to select a target institution or facility suitable for treating emergency patients (S40).

[0072] Figure 5 is a flowchart illustrating in detail a method for selecting a target institution or facility suitable for treating emergency patients, according to one embodiment of the present disclosure.

[0073] Referring to Figure 5, the computing device 100 classifies emergency patients into either a first-class patient requiring specific treatment or a second-class patient not requiring specific treatment, using the severity of the emergency patient measured by a severity classification commonly used by emergency personnel and medical staff, and the severity calculated based on a predicted value calculated by a neural network model (S41).

[0074] Here, the first patient may include at least one of the following: a patient who requires treatment that can only be performed by a specific hospital or medical team, or a patient whose severity, calculated based on predicted values, is determined to be at or above a level set for each disease.

[0075] In the case of the first patient, the computing device 100 extracts candidate hospitals for treating the emergency patient from a group of hospitals that match the first patient, based on location and traffic information including at least one of the following: the location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to hospitals capable of performing a specific procedure (e.g., PCI) (S42, S43). Here, the computing device 100, i.e., the second server 120, can collect real-time traffic information via the ITS National Traffic Information Center and can collect the number of ambulances heading to hospitals via navigation operators that provide route guidance based on the user's real-time location information.

[0076] In the case of the second patient, the computing device 100 extracts candidate hospitals from a group of hospitals that match the second patient based on the severity level determined by pre-KTAS, using location and traffic information that includes at least one of the following: the location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to the hospital (S42, S44). For example, if the severity level determined by Pre-KTAS corresponds to level 1 or 2, the computing device 100 matches the patient with a regional / severe emergency center; if the severity level corresponds to level 2 or 3, it matches the patient with a regional emergency medical center; and if the severity level corresponds to level 4 or 5, it matches the patient with a group of regional emergency medical institutions.

[0077] The computing device 100 can use location and traffic information to calculate estimated transport time information for each hospital included in the group of hospitals that match the patient classification, and extract candidate hospitals based on the estimated transport time information.

[0078] The computing device 100 calculates the suitability of the candidate hospitals using capacity information that includes at least one of the following: the congestion level of each emergency room, emergency facility information, or medical staff manpower information of the extracted candidate hospitals (S45), and establishes a transfer plan based on the hospital priority order calculated based on the suitability (S46). The second server 120 can periodically collect capacity information such as the real-time congestion level of each emergency room, emergency facility information, and medical staff manpower information from each hospital's homepage or the National Emergency Medical Information Network (NEDIS), etc.

[0079] Here, the computing device 100 can provide communication services such as wired inquiries or voice AI inquiries to emergency medical personnel so that they can confirm the availability of patient admission to N hospitals selected according to hospital priority when establishing a transfer plan. After transferring the emergency patient to the appropriate hospital according to hospital priority, the computing device 100 can transmit the accumulated electrocardiogram data and analysis results (predicted values, changes, etc.) from the emergency situation report to the final arrival at the hospital to the medical staff in charge of treating the emergency patient. Furthermore, the computing device 100 can continuously assess the severity of the emergency patient's condition even in a medical environment including the emergency room, and continuously perform tasks such as deciding whether to transfer the patient to another hospital or move them from a general ward to a critical care ward based on the assessed severity, and can provide emergency patient monitoring services for a certain period of time or until the treatment of the emergency patient is completed.

[0080] Thus, in this disclosure, an electrocardiogram of a critically ill patient is measured at periodic time intervals, and a pre-trained neural network model is used to calculate a predicted value for the probability of each cardiac disease occurring. Based on the changes in the predicted value for the probability of cardiac disease occurring and the characteristics of multiple diseases, a transport plan for the critically ill patient is established. In this disclosure, if the changes in the predicted value indicate that the probability of one or more cardiac diseases occurring is low, the severity level of the critically ill patient is set to a previously set level or lower. If the probability of one or more cardiac diseases occurring is estimated to be high, the severity level of the critically ill patient is determined to be very high, and a transport plan is established to quickly transport the critically ill patient to a hospital capable of treating or treating their cardiac disease.

[0081] Therefore, this disclosure can provide a transport plan, including hospitals and transport routes where emergency treatment and specific procedures can be performed, based on early and accurate predictions of the likelihood of cardiac disease occurring using a pre-trained neural network model, thereby preventing unnecessary time from being wasted in the rapid transport of critically ill patients and avoiding the waste of resources and time necessary for emergency treatment. Above all, this disclosure can classify patients, such as those with simple chest pain who do not have a myocardial infarction and those with a myocardial infarction, using a neural network model rather than emergency medical personnel (or 119 paramedics), thereby improving the appropriateness of emergency treatment for critically ill patients at the pre-hospital stage based on their symptoms.

[0082] The various embodiments of this disclosure described above can be combined with additional embodiments and modified to the extent that a person skilled in the art can understand from the detailed description above. The embodiments of this disclosure should be understood in all respects to be illustrative and not limiting. For example, each component described as a single type can be implemented in a distributed manner, and similarly, components described as distributed can be implemented in a combined form. Therefore, all forms of modification or variation derived from the meaning, scope and equivalent concepts of the claims of this disclosure should be interpreted as being included within the scope of this disclosure.

Claims

1. A method for providing emergency patient transport and monitoring services based on an electrocardiogram, which is performed by a computing device including at least one processor, The stage of acquiring electrocardiogram data of emergency patients at pre-set time intervals, A step of using a pre-trained neural network model to calculate multiple predictive values ​​corresponding to the probability of each of several cardiac diseases occurring based on the electrocardiogram data, A step of calculating the severity of each of the multiple heart diseases based on the multiple predicted values, The steps include classifying the emergency patients using the calculated severity level and selecting a suitable medical institution or facility for treating the emergency patients based on the results of the classification, Methods that include...

2. The step of calculating the severity corresponding to each of the multiple heart diseases based on the multiple predicted values ​​is: A step of understanding the trend of changes in the predicted value, and determining the level of severity based on the understood trend of changes and the characteristics of the multiple heart diseases, The method according to claim 1, including the method described in claim 1.

3. The step of understanding the trend of changes in the predicted value and determining the level of severity based on the understood trend of changes and the characteristics of the multiple heart diseases is: A step of selecting a judgment method for understanding the trend of changes in the predicted value according to the characteristics of the multiple heart diseases, A step of determining the severity level based on the change progression observed by the selected judgment method, The method according to claim 2, including the method described in claim 2.

4. The method according to claim 3, wherein the determination method is one of the following methods: determining whether the predicted value calculated by the neural network model is on an upward trend; determining whether the predicted value is on a downward trend or alternates between downward and upward trends; determining whether the determination is made using the slope of the upward curve relative to the predicted value; determining whether the predicted value falls outside a previously set cutoff; and determining whether the area of ​​the graph where the predicted value is displayed is calculated and whether it falls outside a previously set size.

5. The step of classifying the emergency patients using the calculated severity level and selecting a suitable medical institution or facility for treating the emergency patients according to the results of the classification is as follows: A step of classifying the emergency patient into either a first patient requiring specific treatment or a second patient not requiring specific treatment, using the severity of the emergency patient measured by a severity classification commonly used by emergency personnel and medical staff, and the severity calculated based on the predicted value, Based on location and traffic information including at least one of the following: the location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to the hospital, a step is to extract candidate hospitals for treating the emergency patient from a group of hospitals that match the classification. The steps include: calculating the suitability of each candidate hospital using capacity information that includes at least one of the following: emergency room congestion level, emergency facility information, or medical staff manpower information; and establishing a transfer plan based on the hospital priority order determined by the calculated suitability; The method according to claim 1, including the method described in claim 1.

6. The method according to claim 5, wherein the first patient includes at least one of the following: a patient who requires a procedure that can only be performed through a specific hospital or medical team, or a patient whose severity, calculated based on the predicted value, is determined to be above a dictionary-defined standard for each heart disease.

7. The step of extracting candidate hospitals for treating the emergency patient from a group of hospitals that match the classification, based on location and traffic information including at least one of the following: the location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to the hospital, is as follows: Using the aforementioned location and traffic information, the step of calculating the estimated transport time information for hospitals included in the group of hospitals that match the classification, Based on the predicted transport time information, the step of extracting candidate hospitals for treating the emergency patient from a group of hospitals that match the classification, The method according to claim 5, including the method described in claim 5.

8. The step of calculating the suitability of the candidate hospitals using capacity information that includes at least one of the following: emergency room congestion level, emergency facility information, or medical staff manpower information, and establishing a transfer plan based on the hospital priority ranking calculated, is as follows: A step in which a communication service is provided so that it is possible to confirm the patient admission status of N hospitals selected according to the aforementioned hospital priority order, The method according to claim 5, including the method described in claim 5.

9. A computer program stored on a computer-readable storage medium, The computer program is configured to cause the computer to perform actions to provide emergency patient transport services and monitoring based on an electrocardiogram. The aforementioned operation is, The operation involves acquiring electrocardiogram data of emergency patients at pre-set time intervals, The process involves using a pre-trained neural network model to calculate multiple predicted values ​​corresponding to the likelihood of each of several cardiac diseases occurring based on the electrocardiogram data, An operation to calculate the severity of each of the multiple heart diseases based on the multiple predicted values, The process involves classifying the emergency patients using the calculated severity level, and selecting a suitable medical institution or facility for treating the emergency patients based on the results of the classification. A computer program that includes [this].

10. A computing device for providing emergency patient transport services and monitoring based on electrocardiograms, A processor containing at least one core, Memory containing program code executable by the aforementioned processor, Includes, The processor, upon execution of the program code, ECG data of emergency patients is acquired at pre-set time intervals. Using a pre-trained neural network model, multiple predicted values ​​corresponding to the probability of occurrence of each of several cardiac diseases are calculated based on the electrocardiogram data. Based on the aforementioned multiple predicted values, the severity level corresponding to each of the aforementioned multiple heart diseases is calculated. The emergency patients are classified using the calculated severity level, and a suitable medical institution or facility is selected for the treatment of the emergency patients based on the classification results. Device.

Images