Method, program and apparatus for providing electrocardiogram-based emergency patient transport services and inpatient monitoring

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 present disclosure relates to a method for providing emergency patient transport services and inpatient monitoring based on electrocardiograms, and more particularly to a method for predicting the likelihood of cardiac disease based on electrocardiogram data using a pre-trained neural network model and transporting emergency patients to a hospital that is best suited for emergency symptom-specific treatment. [Background technology]

[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 involves the stages of reporting, rescue, on-site treatment, and transporting the emergency patient from the time of the emergence of an emergency patient, as well as securing an ambulance that can quickly dispatch within a set time frame and provide adequate emergency treatment in the ambulance. Next, in-hospital emergency treatment includes emergency room treatment, hospitalization, and medical treatment at an emergency medical institution.

[0003] In Japan, the Fire Department 119 pre-hospital emergency medical system aims to increase survival rates through professional first aid provided by 119 emergency personnel (or first responders), and ultimately to provide patient-centered, preventive, and management emergency medical services on the scene. To check the patient's condition, 119 emergency personnel take electrocardiograms (ECGs), oxygen saturation (Spo2), body temperature, blood pressure, etc. As ECGs are of great clinical importance in diagnosing cardiovascular diseases, emergency medical centers are equipped with ECG-related equipment, such as ECG machines, ECG monitors (for patient monitoring), and high-end cardiac shock machines.

[0004] In recent years, the number of patients suffering from pre-hospital cardiac arrest has been increasing in Korea due to the aging of the population, the rapid rise in cardiovascular disease, and an increase in various accidents, but according to the results of many domestic studies, the survival rate of patients suffering from pre-hospital cardiac arrest is 2-17%, which is lower than in Western Europe and has not changed significantly compared to the past. According to a report on emergency medical care by the Korea Health Industry Development Institute, if initial first aid is performed properly, the resuscitation rate of patients suffering from sudden illness can increase from the 20% to 50% range.

[0005] Unlike general patients, emergency treatment within 30 minutes of the onset of illness or injury can have a significant impact on the patient's life. Therefore, emergency treatment must begin at the scene of illness or injury, and treatment must not be interrupted during transport. After arriving at the hospital, intensive care must be provided within a short time by a multidisciplinary medical team.

[0006] In particular, when a cardiac emergency occurs, it is necessary to quickly transfer the patient to a hospital that can provide treatment based on an accurate diagnosis at the pre-hospital emergency treatment stage. However, among cardiac emergency patients, those with myocardial infarction must undergo PCI (Percutaneous Cardiac Intervention) within two hours, but there is no way to know which hospitals can perform PCI at the pre-hospital emergency treatment 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 to transport emergency patients between hospitals (transfers), and a private ambulance must be used, which can result in significant delays in the process of transferring emergency patients.

[0008] In addition, even if a patient with myocardial infarction is called by 119 ambulance, the 119 ambulance crew must make several phone calls to hospitals that can perform PCI to select a hospital that can transport the patient. This communication process can delay emergency treatment or prevent appropriate treatment from being provided.

[0009] Above all, it is difficult for 119 emergency personnel to distinguish between patients with simple chest pain and those with myocardial infarction based on electrocardiogram results, and therefore they are unable to distinguish between patients who absolutely require PCI treatment and those who do not. Therefore, if all patients, including those with simple chest pain, are transported to hospitals that can perform PCI treatment, not only will the efficiency of emergency treatment decrease, but emergency medical resources such as transport time and preparation for PCI treatment may be wasted, which may actually cause problems in the appropriate treatment of patients with myocardial infarction. Summary of the Invention [Problem to be solved by the invention]

[0010] The present disclosure has been devised in response to the background art described above, and aims to provide a method for predicting the likelihood of cardiac disease based on electrocardiogram data using a pre-trained neural network model, and transporting a patient to a target institution or facility that is best suited for emergency symptom-specific treatment.

[0011] However, the problems to be solved by this disclosure are not limited to those mentioned above, and other problems not mentioned will be clearly understood from the description below. [Means for solving the problem]

[0012] To achieve the above object, one embodiment of the present disclosure provides a method for providing emergency patient transport services and inpatient monitoring based on electrocardiograms, including: acquiring electrocardiogram data of an emergency patient at a predetermined time interval; 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 selecting a target institution or facility suitable for treating the emergency patient using the calculated severity level.

[0013] Alternatively, the step of calculating a severity level for classifying an emergency patient based on the predicted value comprises:

[0014] The method may include determining a change trend of the predicted value and determining the severity level based on the determined change trend and characteristics of the plurality of diseases.

[0015] Alternatively, the step of grasping the change trend of the predicted value and determining the severity level based on the grasped change trend and characteristics of the plurality of diseases may include the steps of selecting a judgment method for grasping the change trend of the predicted value based on characteristics of the plurality of diseases, and determining the severity level based on the change trend grasped by the selected judgment method.

[0016] Alternatively, the determination method may be any one of a method of determining whether the predicted value calculated by the neural network model is on an upward trend, a method of determining whether the predicted value is on a downward trend or alternates between downward and upward trends, a method of determining using the gradient of an upward curve for the predicted value, a method of determining whether the predicted value is outside a preset cutoff, and a method of displaying the predicted value on a graph and then calculating the size of the area to determine whether the predicted value is outside a preset size.

[0017] Alternatively, the step of selecting a target institution or facility suitable for treating the emergency patient using the calculated severity may include the steps 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 according to 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 location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to the hospital; and calculating suitability of the candidate hospitals using capacity information including at least one of emergency room congestion, emergency facility information, or medical staff manpower information of each of the candidate hospitals, and establishing a transportation plan according to hospital priorities based on the calculated suitability.

[0018] Alternatively, the first patient may include at least one of a patient who requires treatment that can only be performed at a specific hospital or by a specific medical team, or a patient whose severity calculated based on the predicted value is determined to be equal to or greater than a dictionary-defined standard for each disease.

[0019] Alternatively, the step of extracting candidate hospitals for treating the emergency patient from the 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 may include the steps of: calculating expected transport time information of hospitals included in the group of hospitals matching the classification using the location and traffic information; and extracting candidate hospitals for treating the emergency patient from the group of hospitals matching the classification based on the expected transport time information.

[0020] Alternatively, the step of 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 of the candidate hospitals, and establishing a transfer plan according to the hospital priority order based on the calculated suitability may include the step of providing a communication service to check whether the N hospitals selected according to the hospital priority order can accommodate patients.

[0021] According to another embodiment of the present disclosure, there is provided a computer program stored on a computer-readable storage medium, the computer program, when executed by one or more processors, performing operations for providing emergency patient transport services and monitoring of hospitalized patients based on electrocardiograms, the operations including: 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 selecting a target institution or facility suitable for treating the emergency patient using the calculated severity level.

[0022] Meanwhile, a computing device for providing emergency patient transport services and inpatient monitoring based on electrocardiograms according to one embodiment of the present disclosure includes a processor including at least one core and a memory including program code executable by the processor, wherein the processor acquires electrocardiogram data of emergency patients at predetermined time intervals by executing the program code, calculates 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, calculates a severity level for classifying the emergency patient based on the predicted value, and uses the calculated severity level to select a target institution or facility suitable for treating the emergency patient. [Effects of the Invention]

[0023] A method for providing an emergency patient transport service and monitoring of hospitalized patients based on an electrocardiogram according to an embodiment of the present disclosure can quickly and accurately predict the likelihood of developing a heart disease based on electrocardiogram data using a pre-trained neural network model, and can grasp the severity of the patient's emergency condition based on the predicted change in the likelihood of developing a heart disease and the characteristics of multiple diseases.The method can then classify patients who require specific treatment based on the grasped severity, and transport the emergency patient to a target institution or facility that is best suited to provide emergency treatment based on the patient's emergency condition, thereby improving the appropriateness of emergency treatment based on the patient's emergency condition. [Brief explanation of the drawings]

[0024] [Figure 1] FIG. 1 is a block diagram of a computing device according to one embodiment of the present disclosure. [Figure 2] FIG. 1 is a block diagram illustrating the configuration of a system for providing emergency patient transport services and inpatient monitoring based on electrocardiograms, according to one embodiment of the present disclosure. [Figure 3]FIG. 10 is a diagram illustrating a process of grasping a change transition using a neural network model according to an embodiment of the present disclosure. [Figure 4] 1 is a flowchart illustrating a method for providing emergency patient transport services and inpatient monitoring based on electrocardiograms, according to one embodiment of the present disclosure. [Figure 5] 1 is a flowchart detailing a method for selecting target institutions or facilities suitable for treating emergency patients, according to one embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0025] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement the present disclosure. The embodiments presented in this disclosure are provided to enable those skilled in the art to use or practice the contents of the present disclosure. Therefore, various modifications to the embodiments of the present disclosure will be apparent to those skilled in the art. That is, the present disclosure may 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 refer to the same or similar components. In addition, in order to clearly explain the present disclosure, reference numerals of parts that are not relevant to the explanation of the present disclosure may be omitted from the drawings.

[0027] The term "or" as used in this disclosure is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or otherwise clear from the context in this disclosure, "X uses A or B" should be understood to mean one of the natural inclusive permutations. For example, unless otherwise specified or otherwise clear from the context in this disclosure, "X uses A or B" can be interpreted as either X uses A, X uses B, or X uses both A and B.

[0028] The term "and / or" as used in this disclosure must be understood to indicate and include all possible combinations of one or more of the associated listed concepts.

[0029] The terms "comprises" and / or "comprising" as used in this disclosure should be understood to mean that the specified features and / or components are present. However, the terms "comprises" and / or "comprising" should not be understood to exclude the presence or addition of one or more other features, other components and / or combinations thereof.

[0030] In this disclosure, unless otherwise specified or clear from the context as referring to the singular form, the singular should generally be construed as including "one or more."

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

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

[0033] Meanwhile, the terms "module" or "unit" used in this disclosure may be understood to refer to an independent functional unit that processes computing resources, such as a computer-related entity, firmware, software or a portion thereof, hardware or a portion thereof, or a combination of software and hardware. Here, a "module" or "unit" may refer to a unit composed of a single element or a unit expressed as a combination or collection of multiple elements. For example, as a concept of connotation, a "module" or "unit" may refer to a hardware element or a collection of hardware elements of a computing device, an application program that performs a specific software function, a processing procedure implemented by executing software, or a collection of instructions for executing a program. Furthermore, as a broad concept, a "module" or "unit" may refer to a 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" and "unit" may be defined in various ways within the scope of understanding of those skilled in the art based on the contents of this disclosure.

[0034] The term "model" as used in this disclosure may be understood as a system implemented using mathematical concepts and language to solve a specific problem, a set of software units for solving a specific problem, or an abstract model of a processing process for solving a specific problem. For example, a neural network "model" may refer to a system implemented as a neural network that has problem-solving capabilities through learning. Here, a neural network may have problem-solving capabilities by optimizing parameters connecting nodes or neurons through learning. A neural network "model" may include a single neural network or a neural network ensemble that combines multiple neural networks.

[0035] The term "block" used in this disclosure may be understood as a collection of components classified based on various criteria, such as type, function, etc. Therefore, the components classified into one "block" may vary depending on the criteria. For example, a neural network "block" may be understood as a collection of neural networks including at least one neural network. Here, neural networks included in a neural network "block" may be assumed to perform a specific operation equally. The explanations of the above terms are intended to facilitate understanding of the present disclosure. Therefore, unless the above terms are explicitly described as limitations on the content of the present disclosure, care should be taken not to use them to limit the technical ideas of the content of the present disclosure.

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

[0037] The computing device 100 according to an embodiment of the present disclosure may be a hardware device or part of a hardware device that performs comprehensive data processing and calculations, or 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 shares resources, or a client that shares resources by interacting with the server. The computing device 100 may also be a cloud system in which multiple servers and clients interact with each other to comprehensively process data. The above description is merely an example of a type of computing device 100, and various types of computing device 100 may be configured within the scope of what one skilled in the art would understand based on the contents of this disclosure.

[0038] 1, a computing device 100 according to an embodiment of the present disclosure may include a processor 110, a memory 120, and a network unit 130. However, since FIG. 1 is merely an example, the computing device 100 may include other components for implementing a computer environment. Also, the computing device 100 may include only some of the disclosed components.

[0039] The processor 110 according to an embodiment of the present disclosure may be understood as a component including hardware and / or software for performing computing operations. For example, the processor 110 may read a computer program to perform data processing for machine learning. The processor 110 may process operations such as input data processing for machine learning, feature extraction for machine learning, and error calculation based on backpropagation. The 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), a field programmable gate array (FPGA), etc. The types of processor 110 described above are merely examples, and various types of processor 110 may be configured within the scope of what one skilled in the art would understand based on the present disclosure.

[0040] The processor 110 uses a pre-trained neural network model to diagnose and predict diseases based on the acquired electrocardiogram data of a patient who is suddenly ill, thereby enabling the patient to be transported to the most appropriate hospital in the event of an emergency. Here, the processor 110 can train a neural network model that extracts electrocardiogram features based on the electrocardiogram data and calculates a predicted value corresponding to the likelihood of each of a plurality of cardiac diseases based on the extracted electrocardiogram features. For example, the processor 110 can train the neural network model to analyze an electrocardiogram and predict cardiac diseases based on biological information including information such as gender, age, weight, and height in addition to the electrocardiogram data.

[0041] Specifically, the processor 110 inputs electrocardiogram data and various biological information into the neural network model, and trains the neural network model to detect electrocardiogram changes due to arrhythmia and other cardiac diseases. Here, the neural network model may perform training based on an electrocardiogram dataset including electrocardiogram features extracted from the electrocardiogram data and diagnostic data for arrhythmia and other cardiac diseases. The processor 110 may perform an operation to represent at least one neural network block included in the neural network model during the training process of the neural network model.

[0042] The processor 110 can extract electrocardiogram features from electrocardiogram data acquired from an electrocardiogram monitor using the neural network model generated by the above-described learning process, and estimate electrocardiogram interpretation data based on the extracted electrocardiogram features. The processor 110 can input biological information, including electrocardiogram data, gender, age, weight, height, etc., to the neural network model trained by the above-described process, and generate inference data indicating the results of estimating the probability of heart disease. For example, the processor 110 can input electrocardiogram data to the neural network model that has completed training, and provide predicted values ​​for the presence or absence of arrhythmia or other heart diseases, and the degree of progression.

[0043] In addition to the examples given above, the types of medical data and the output of the neural network model can be configured in a variety of ways within the scope that would be understandable to one skilled in the art from the contents of this disclosure.

[0044] The memory 120 according to an embodiment of the present disclosure may be understood as a component including hardware and / or software for storing and managing data processed by the computing device 100. That is, the memory 120 may store any type of data generated or determined by the processor 110 and any type of data received by the network unit 130. For example, the memory 120 may include at least one type of storage medium selected from the group consisting of flash memory, hard disk, multimedia card micro, card-type memory, random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, and optical disk. The memory 120 may also include a database system that manages data in a predetermined manner. The types of memory 120 described above are merely examples, and various configurations of the memory 120 are possible within the scope of what would be understood by one skilled in the art based on the present disclosure.

[0045] The memory 120 may structure and organize and manage data, data combinations, and program code executable by the processor 110 required for the processor 110 to perform calculations. For example, the memory 120 may store electrocardiogram data received via the network unit 130 (described later). The memory 120 may store program code for operating a neural network model to receive medical data and perform learning, program code for operating a neural network model to receive medical data and perform inference according to the intended use of the computing device 100, and processed data generated by executing the program code.

[0046] The network unit 130 according to an embodiment of the present disclosure may be understood as a component that transmits and receives data via any type of known wired or wireless communication system. For example, the network unit 130 may transmit and receive data using a wired or wireless communication system such as a local area network (LAN), wideband code division multiple access (WCDMA), long term evolution (LTE), wireless broadband internet (WiBro), 5th generation mobile communication (5G), ultra wide-band, ZigBee, radio frequency (RF) communication, wireless LAN, wireless fidelity (WiFi), near field communication (NFC), or Bluetooth. The above-described communication systems are merely examples, and various wired or wireless communication systems for transmitting and receiving data by the network unit 130 may be applied in addition to the above examples.

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

[0048] FIG. 2 is a block diagram illustrating the configuration of a system for providing emergency patient transport services and monitoring of hospitalized patients based on electrocardiograms according to one embodiment of the present disclosure, and FIG. 3 is a diagram illustrating the process of grasping change trends using a neural network model according to one embodiment of the present disclosure.

[0049] The system for providing emergency patient transport services based on 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 an electrocardiogram and may be provided to a 119 emergency responder, a patient receiving emergency medical treatment, or an ambulance. The local device 10 may be a wearable device worn on the body of a patient receiving emergency medical treatment and capable of measuring and collecting various health indicators such as heart rate, body fat percentage, and blood pressure, a portable electrocardiogram monitor, or a biosignal measurement device. Here, the local device 10 may measure an electrocardiogram using a wearable device such as a wristwatch or a patch, as well as various electrode combinations such as a 12-lead system and a 6-lead system. The electrocardiogram measurement time may also be adjusted depending on the signal to be obtained.

[0051] The computing device 100 can use the 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 machine 10. Here, the neural network model can be trained based on electrocardiogram features, including at least one of the frequency of tachycardia, the length of the QT interval, the deflection direction of P waves, R waves, and T waves, or the QRS duration.

[0052] The computing device 100 includes a first server 110 for ECG 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] 3, the first server 110 uses a pre-trained neural network model 200 to calculate a predicted value corresponding to the likelihood of occurrence of each of a plurality of cardiac diseases based on electrocardiogram data, and calculates a severity level for classifying emergency patients based on the calculated predicted value. The first server 110 may include a classification model that enables the pre-trained neural network model 200 to calculate a predicted value corresponding to the likelihood of occurrence of each cardiac disease. Thus, the first server 110 can input electrocardiogram data into a plurality of pre-trained classification models in a stepwise manner to classify cardiac diseases with high accuracy, and calculate a predicted value corresponding to the likelihood of occurrence of each cardiac disease using each classification model.

[0054] For example, neural network models can build multiple classification models corresponding to the type of cardiac disease being identified, and can predict the likelihood of each disease, 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 value provided by each classification model can be calculated as a numerical value from 0 to 100, and after grasping the change trend of the predicted value of each classification model, the severity level can be determined based on the grasped change trend and the characteristics of multiple diseases.

[0056] The severity level can be determined by selecting one of the following judgment methods for grasping the change in the predicted value over time based on the characteristics of multiple diseases, and determining the severity level based on the change in the predicted value over time grasped by the selected judgment method.

[0057] That is, the second server 120 selects a judgment method according to the characteristics of the disease from among a method of determining whether the predicted value (or disease score, numerical value) calculated by the neural network model is on an upward trend, a method of determining whether the predicted value is on a downward trend or repeatedly increases and decreases, a method of judging using the inclination (e.g., gradient) of the upward curve for the predicted value, a method of determining whether the predicted value deviates from a pre-determined cutoff, and a method of displaying the predicted value on a graph and then calculating the size of the area to determine whether it deviates from a pre-determined size, and finally determines the severity level.

[0058] For example, the severity levels can be classified into a first level corresponding to a case where the predicted value is on an upward trend, a second level corresponding to a case where the predicted value repeatedly rises and falls within a preset upper limit range without an upward trend, a third level corresponding to a case where the predicted value repeatedly rises and falls within an upper limit range (e.g., 70) and a preset lower limit range (e.g., 30), and a fourth level corresponding to a case where the predicted value repeatedly rises and falls within a lower limit range.

[0059] The first server 110 sets the severity level to Level 3 because the change trend of the predicted value repeatedly rises and falls within the upper and lower limit ranges as the number of electrocardiogram measurements increases based on the STEMI classification model, and sets the severity level to Level 1 because the change trend of the predicted value range exceeds the upper limit range as the number of electrocardiogram measurements increases based on the LVSD classification model.Furthermore, the first server 110 determines that the change trend of the predicted value based on the classification model for within 24 hours cardiac arrest cannot be classified as an upward or downward trend and therefore cannot be grasped, and sets the change trend of the predicted value based on the classification model for NSTEMI repeatedly rises and falls within the lower limit range as Level 4.

[0060] Here, if the severity level is determined to be the fourth level more than the preset number of times, the first server 110 can terminate the calculation of the predicted value using the neural network model 200 and stop the electrocardiogram measurement.

[0061] The second server 120 selects an appropriate institution or facility for treating the emergency patient using the calculated severity, and transfers the emergency patient to the selected institution or facility. The second server 120 is connected to a 119 reporting center or an emergency situation management center, and can transmit dispatch information to a fire department or a 119 safety center by reporting an emergency situation, and can establish a transfer plan for the emergency patient depending on the emergency situation or the treatment environment.

[0062] The second server 120 may classify the emergency patient into either a first patient who requires a specific treatment or a second patient who does not require a specific treatment, using the severity calculated based on the severity of the emergency patient and the predicted value according to a severity classification commonly used by emergency personnel and medical staff. For example, the severity classification commonly used by emergency personnel and medical staff may use the Pre-KTAS (Prehospital Korean Triage and Acuity Scale) method.

[0063] [Table 1] JPEG2025528683000003.jpg32169

[0064] As shown in Table 1, the Pre-KTAS (Prehospital Korean Triage and Acuity Scale) classifies patients in the pre-hospital stage according to their level of emergency into Grade 1 (resuscitation: very serious), Grade 2 (urgent), Grade 3 (emergency), Grade 4 (semi-emergency), and Grade 5 (non-emergency: very mild), and defines the medical treatment time for each grade as immediate, 10 minutes, 30 minutes, 60 minutes, or within 120 minutes. The lower the classification grade, the higher the severity and the higher the priority of treatment.

[0065] Before transporting the emergency patient to the hospital, the second server 120 classifies the emergency patient into either a first patient who requires a specific treatment or a second patient who does not require a specific treatment, using the severity of the emergency patient measured according to a severity classification commonly used by emergency personnel and medical staff and the severity calculated based on the predicted value. For example, the second server 120 can classify as a first patient a patient who requires a treatment (e.g., PCI treatment) that can be performed by a specific hospital or specific medical staff, or whose severity calculated based on the predicted value is determined to be above a predetermined standard for each disease (e.g., a patient whose severity level based on the STEMI classification model is above the second level).

[0066] In addition, 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 location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to the hospital, calculate 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 of each candidate hospital, and then establish a transportation plan according to hospital priorities based on the calculated suitability.

[0067] In addition, the second server 120 provides not only a transportation plan and transportation for emergency patients but also a monitoring service for hospitalized patients, thereby continuously determining the severity of the emergency patients transferred from the emergency room and deciding whether to transfer them to another hospital or move them from a general ward to a ward for serious patients based on the determined severity.

[0068] FIG. 4 is a flow chart illustrating a method for providing emergency patient transport services and inpatient monitoring based on electrocardiograms, according to one embodiment of the present disclosure.

[0069] Referring to FIG. 4, the computing device 100 acquires electrocardiogram data of the patient receiving emergency care at preset time intervals in response to an emergency situation report (S10). The second server 120 may transmit a link or QR code (registered trademark) that allows the patient to measure and transmit an electrocardiogram. When the patient, their guardian, or a 119 emergency responder completes connection using the link or QR code, the second server 120 connects to the local device 10 and automatically measures and transmits the patient's electrocardiogram at periodic time intervals (e.g., every 3 minutes). Even if the periodic time interval for electrocardiogram measurement has arrived, if the patient is moving or moving around a lot, the second server 120 may wait a certain period of time before measuring the electrocardiogram and then measure the electrocardiogram again after a certain time has passed. This is because the accuracy of the electrocardiogram measured when the patient is moving or moving around a lot may decrease, resulting in the electrocardiogram being determined to be indeterminable.

[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 likelihood of occurrence of each 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 value to the second server 120, and the second server 120 grasps the change trend of the predicted value transmitted at a predetermined time interval, calculates the severity for classifying emergency patients according to the grasped change trend and the characteristics of multiple diseases (S30), and selects the target institution or facility suitable for treating the emergency patient using the calculated severity (S40).

[0072] FIG. 5 is a flowchart detailing a method for selecting target institutions or facilities suitable for treating emergency patients according to one embodiment of the present disclosure.

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

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

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

[0076] For the second patient, the computing device 100 extracts candidate hospitals from the group of hospitals that match with the second patient based on the severity level according to the pre-KTAS and location and traffic information including at least one of the patient's location, real-time traffic conditions, and the number of ambulances heading to the hospital (S42, S44). If the severity level according to the pre-KTAS corresponds to the first and second levels, the computing device 100 matches the second patient with a regional / critical care center, if the severity level corresponds to the second and third levels, the computing device 100 matches the second patient with a regional critical care center, and if the severity level corresponds to the fourth and fifth levels, the computing device 100 matches the second patient with a regional critical care center.

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

[0078] The computing device 100 calculates the suitability of the candidate hospitals using capacity information including at least one of 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 according to the hospital priority based on the calculated 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 via the homepage of each hospital or the National Emergency Medical Information Network (NEDIS), etc.

[0079] Here, the computing device 100 may provide communication services such as wired inquiries or voice AI inquiries for emergency responders so that N hospitals selected according to hospital priority can confirm whether they can accommodate a patient when establishing a transportation plan. After transporting an emergency patient to an appropriate hospital according to hospital priority, the computing device 100 may transmit accumulated electrocardiogram data and analysis results (predicted values, changes, etc.) accumulated from the emergency situation report to the final arrival at the hospital to medical staff in charge of treating the emergency patient. Furthermore, the computing device 100 may continuously determine the severity of an emergency patient even in a medical environment including an emergency room, and continuously perform an operation of determining whether to transfer the patient to another hospital or move the patient from a general ward to an intensive care room based on the determined severity, and may provide a monitoring service for the emergency patient for a certain period of time or until the treatment of the emergency patient is completed.

[0080] In this manner, the present disclosure measures the electrocardiogram of an emergency patient at periodic time intervals, calculates a predicted value for the likelihood of each cardiac disease using a pre-trained neural network model, and establishes a transport plan for the emergency patient based on the change over time of the predicted value for the likelihood of the cardiac disease and the characteristics of multiple diseases. Here, in the present disclosure, if the change over time of the predicted value indicates that the likelihood of one or more cardiac diseases is low, the severity level of the emergency patient is set to a predetermined level or lower, and if the likelihood of one or more cardiac diseases is estimated to be high, the severity level of the emergency patient is determined to be very high, and establishes a transport plan so that the emergency patient can be quickly transported to a hospital that can provide medical treatment or surgery for the cardiac disease.

[0081] Therefore, the present disclosure can provide a transportation plan, such as a hospital where emergency treatment and specific treatment can be performed and a transportation route, based on a fast and accurate prediction value of the likelihood of a heart disease using a pre-trained neural network model, thereby preventing unnecessary time from being wasted in quickly transporting a patient with an emergency condition and avoiding the waste of resources and time needed for emergency treatment.More importantly, the present disclosure can use a neural network model, rather than a first responder (or 119 ambulance personnel), to classify patients into patients with simple chest pain that is not a myocardial infarction and patients with a myocardial infarction, thereby further improving the appropriateness of emergency treatment according to the symptoms of the patient at the pre-hospital stage.

[0082] The various embodiments of the present disclosure described above can be combined with additional embodiments and can be modified within the scope that can be understood by those skilled in the art from the above detailed description. The embodiments of the present disclosure are illustrative in all respects and should not be construed as limiting. For example, each component described as a single type can also be implemented in a distributed form, and similarly, components described as distributed can also be implemented in a combined form. Therefore, all modifications and variations derived from the meaning, scope, and equivalent concepts of the claims of the present disclosure should be construed as being within the scope of the present disclosure.

Claims

1. 1. A method for providing electrocardiogram-based emergency patient transport services and inpatient monitoring, executed by a computing device including at least one processor, comprising: acquiring electrocardiogram data of the emergency patient 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; using the calculated severity to select a target institution or facility suitable for treating the emergency patient; A method comprising:

2. The step of calculating a severity level for classifying an emergency patient based on the predicted value includes: determining a change in the predicted value over time and determining the severity level based on the change in the predicted value and characteristics of the plurality of diseases; The method of claim 1 , comprising:

3. The step of determining the severity level based on the change in the predicted value and the characteristics of the plurality of diseases includes: selecting a judgment method for grasping the change in the predicted value according to the characteristics of the plurality of diseases; determining the severity level based on the change progression grasped by the selected judgment method; The method of claim 2 , comprising:

4. 4. The method of claim 3, wherein the determination method is one of a method of determining whether the predicted value calculated by the neural network model is on an upward trend, a method of determining whether the predicted value is on a downward trend or alternates between downward and upward trends, a method of determining using a gradient of an upward curve for the predicted value, a method of determining whether the predicted value is outside a preset cutoff, and a method of displaying the predicted value on a graph and then calculating the size of an area to determine whether the predicted value is outside a preset size.

5. The step of selecting a target institution or facility suitable for treating the emergency patient using the calculated severity includes: classifying the emergency patient into either a first patient who requires a specific treatment or a second patient who does not require a specific treatment, using the severity of the emergency patient measured according to 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 location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to the hospital; calculating suitability of the candidate hospitals using capacity information including at least one of emergency room congestion, emergency facility information, and medical staff manpower information of each of the candidate hospitals, and establishing a transfer plan according to hospital priorities based on the calculated suitability; The method of claim 1 , comprising:

6. The method of claim 5, wherein the first patient includes at least one of a patient who requires treatment that can only be performed at a specific hospital or by a specific medical team, or a patient whose severity calculated based on the predicted value is determined to be equal to or greater than a dictionary-defined standard for each disease.

7. 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 location of the emergency patient, real-time traffic conditions, or the number of ambulances heading to the hospital, calculating estimated transportation time information for hospitals included in a group of hospitals that matches the classification using the location and traffic information; extracting candidate hospitals for treating the emergency patient from a group of hospitals matching the classification based on the expected transport time information; The method of claim 5 , comprising:

8. calculating suitability of the candidate hospitals using capacity information including at least one of emergency room congestion, emergency facility information, and medical staff manpower information of the candidate hospitals, and establishing a transfer plan according to hospital priorities based on the calculated suitability; providing a communication service to check whether the N hospitals selected according to the hospital priority order can accommodate patients; The method of claim 5 , comprising:

9. A computer program stored on a computer-readable storage medium, comprising: the computer program is configured to cause a computer to perform operations to provide emergency patient transport services and inpatient monitoring based on electrocardiograms; The operation is acquiring electrocardiogram data of the emergency patient at a predetermined time interval; 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; selecting a target institution or facility suitable for treating the emergency patient using the calculated severity; a computer program comprising:

10. 1. A computing device for providing emergency patient transport services and inpatient monitoring based on electrocardiograms, comprising: a processor including at least one core; a memory containing program code executable by the processor; Including, The processor, by executing the program code, Acquire electrocardiogram data of the emergency patient at a preset time interval; Using a pre-trained neural network model, calculate a predicted value corresponding to the likelihood of occurrence of each of a plurality of diseases based on the electrocardiogram data; calculating a severity level for classifying the emergency patient based on the predicted value; Using the calculated severity, select a target institution or facility suitable for treating the emergency patient; Device.

Images