KR20240009884A - Method, program and apparatus for providing medical emergency patient transport service based on electrocardiogram interpreting - Google Patents

Abstract

The present disclosure relates to a method, program, and device for providing transport services for emergency patients and monitoring of hospitalized patients based on electrocardiograms, comprising: acquiring electrocardiogram data of emergency patients at preset time intervals; Using a pre-trained neural network model, calculating a predicted value corresponding to the probability 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; and using the calculated severity to select a target institution or facility suitable for treatment of the emergency patient.

Description

Method, program and device for providing transport services for emergency patients and monitoring for hospitalized patients based on electrocardiogram {METHOD, PROGRAM AND APPARATUS FOR PROVIDING MEDICAL EMERGENCY PATIENT TRANSPORT SERVICE BASED ON ELECTROCARDIOGRAM INTERPRETING}

The present disclosure relates to a method of providing transport services for emergency patients and monitoring of hospitalized patients based on electrocardiograms. Specifically, prediction of the possibility of occurrence of heart disease and emergency symptoms based on electrocardiogram data using a pre-trained neural network model. It is about how to ensure that emergency patients are transferred to the hospital best suited for special treatment.

The emergency medical system can be broadly divided into pre-hospital emergency treatment and in-hospital emergency treatment. In particular, pre-hospital emergency treatment progresses from the occurrence of an emergency patient to reporting, rescue, on-site treatment, and emergency patient transport, and includes securing an ambulance capable of quickly dispatching and sufficiently transporting the patient within a set time, and providing appropriate first aid in the ambulance. do. Next, emergency treatment in hospitals includes emergency room treatment, hospitalization treatment, and treatment at emergency medical institutions.

In Korea, the firefighting 119 pre-hospital emergency medical system is intended to improve survival rates by providing professional first aid by 119 paramedics (or emergency medical technicians) and further provide emergency medical services of patient-centered prevention and management in the field. . At this time, 119 paramedics check the electrocardiogram (ECG), oxygen saturation (Spo2), body temperature, and blood pressure to check the patient's condition. Among them, since the electrocardiogram has great clinical importance in diagnosing cardiovascular diseases, we are equipped with equipment related to electrocardiogram measurement, such as electrocardiogram meters, electrocardiogram monitors (for patient monitoring), and high-end defibrillators.

Recently, in Korea, the number of patients with out-of-hospital cardiac arrest has been increasing due to the aging population, rapid increase in cardiovascular disease, and increase in various accidents. However, according to the results of several domestic studies, the survival rate of patients with out-of-hospital cardiac arrest is 2- At 17%, it is lower than in the West and there is no significant change compared to the past. According to a report on emergency medicine by the Korea Health Industry Development Institute, when initial first aid is performed well, the emergency patient resuscitation rate improves from the 20% range to the 50% range.

For emergency patients, unlike general patients, emergency treatment within 30 minutes from the moment the disease or injury occurs has a significant impact on the patient's life. Therefore, emergency treatment must begin at the scene where disease or damage occurs, and treatment must not be stopped even during transport. Even after arriving at the hospital, intensive treatment by a multidisciplinary medical team must be provided as quickly as possible.

In particular, when an emergency related to heart disease occurs, it is necessary to quickly transfer the emergency patient to a hospital where treatment is possible through accurate diagnosis in the pre-hospital emergency treatment stage. However, among emergency patients related to heart disease, patients with myocardial infarction must undergo vascular intervention (PCI) within 2 hours, but there is no way to immediately know which hospitals can perform PCI during the pre-hospital emergency treatment stage.

If the 119 ambulance transports a myocardial infarction patient to a hospital where PCI is not possible, the 119 ambulance cannot be used to transfer (transfer) the emergency patient between hospitals, so a private ambulance must be used, so a lot of time is spent in the transfer process of the emergency patient. There may be a delay.

In addition, even if an emergency patient diagnosed with myocardial infarction boards a 119 ambulance, the 119 paramedic must make several calls to hospitals that can be transferred to select a hospital that can perform PCI, so the emergency treatment time is delayed or delayed during this communication process. There is a problem that appropriate treatment cannot be performed.

Above all, it is difficult for 119 paramedics to distinguish between patients with simple chest pain and patients with myocardial infarction based on electrocardiogram measurement results, and as a result, they cannot distinguish between patients who absolutely require PCI surgery and those who do not, so all patients, including patients with simple chest pain, are treated. If the patient is transferred to a hospital capable of PCI, not only does the efficiency of emergency treatment decrease, but emergency medical resources such as transport time and PCI procedure preparation may be wasted, which may actually cause problems in the proper treatment of patients with myocardial infarction.

Republic of Korea Patent No. 10-2265069 (2021.06.09)

This disclosure was made in response to the above-mentioned background technology, and uses a pre-trained neural network model to predict the possibility of heart disease based on electrocardiogram data and transport emergency patients to the target institution or facility optimal for treatment according to emergency symptoms. The purpose is to provide a method to make it possible.

However, the problems to be solved by this disclosure are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood based on the description below.

According to an embodiment of the present disclosure for realizing the above-mentioned problem, an object is to provide a method of providing transport services for emergency patients and monitoring of hospitalized patients based on electrocardiograms. The method includes acquiring electrocardiogram data of an emergency patient at preset time intervals; Using a pre-trained neural network model, calculating a predicted value corresponding to the probability 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; and selecting a target institution or facility suitable for treatment of the emergency patient using the calculated severity.

Alternatively, the step of calculating the severity for classifying an emergency patient based on the predicted value includes identifying a change trend in the predicted value, and determining the level of severity according to the identified change trend and characteristics of the plurality of diseases. It may include a decision step.

Alternatively, the step of determining the change trend in the predicted value and determining the level of severity according to the identified change trend and characteristics of the plurality of diseases includes the above judgment methods for determining the change trend in the predicted value. Selecting a plurality of diseases according to their characteristics; and determining the level of severity based on the change trend identified according to the selected judgment method.

Alternatively, the determination method may include a method of determining whether the predicted value calculated by the neural network model is in an upward trend, a method of determining whether the predicted value is a downward trend or repeats decline and rise, and a method of determining whether the predicted value is in a downward trend or repeats decline and rise. A method of judging using the slope, a method of determining whether the predicted value deviates from a preset cutoff, or a method of displaying the predicted value on a graph and then calculating the size of the area to determine whether it deviates from the preset size. It is the method of.

Alternatively, the step of selecting a target institution suitable for treatment of the emergency patient using the calculated severity may include the severity of the emergency patient measured by a severity classification commonly used by emergency personnel and medical staff and the predicted value. Using the severity calculated based on , classifying the emergency patient as either a first patient requiring a specific procedure or a second patient not requiring a specific procedure; Extracting candidate hospitals for treatment of 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. step; and calculating the suitability of the candidate hospitals using capacity information including at least one of emergency room congestion, emergency facility information, or medical staff personnel information for each of the candidate hospitals, according to hospital priority based on the calculated suitability. It may include the step of establishing a transfer plan.

Alternatively, the first patient may include at least one of a patient in need of a procedure that can only be performed at a specific hospital or through a specific medical staff, or a patient whose severity calculated based on the predicted value is determined to be higher than a preset standard for each disease. You can.

Alternatively, a candidate for treatment of the emergency patient at 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 number of ambulances heading to the hospital. The step of extracting hospitals includes using the location and traffic information to calculate expected transfer time information for hospitals included in the hospital group matching the classification; and extracting candidate hospitals for treatment of the emergency patient from a group of hospitals matching the classification, based on the expected transfer time information.

Alternatively, the suitability of the candidate hospitals is calculated using capacity information including at least one of emergency room congestion, emergency facility information, or medical staff personnel information, and hospital priorities are based on the calculated suitability. The step of establishing a transfer plan may include providing a communication service to check whether or not the patient is accepted at N hospitals selected according to the hospital priority.

A computer program stored in a computer-readable storage medium according to another embodiment of the present disclosure, wherein the computer program, when executed on one or more processors, provides transport services for emergency patients and monitoring of inpatients based on electrocardiograms. To perform operations to provide, the operations including: acquiring electrocardiogram data of an emergency patient at preset time intervals; Using a pre-trained neural network model, calculating a predicted value corresponding to the probability 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; and an operation of selecting a target institution or facility suitable for treatment of the emergency patient using the calculated severity.

Meanwhile, according to an embodiment of the present disclosure, there is provided a computing device for providing transport services for emergency patients and monitoring of hospitalized patients based on electrocardiograms, comprising: a processor including at least one core; and a memory including program codes executable by the processor, wherein the processor acquires electrocardiogram data of an emergency patient at preset time intervals according to execution of the program code, and performs dictionary learning. Using the neural network model, a predicted value corresponding to the probability of occurrence of each of a plurality of diseases is calculated based on the electrocardiogram data, a severity for classifying the emergency patient is calculated based on the predicted value, and the calculated severity is calculated. Using , you can select a target institution or facility suitable for treatment of the emergency patient.

A method of providing emergency patient transport services and monitoring of hospitalized patients based on electrocardiograms according to an embodiment of the present disclosure can quickly and accurately predict the likelihood of cardiac disease based on electrocardiogram data using a pre-trained neural network model. After identifying the severity of emergency patients based on the predicted change in the likelihood of developing heart disease and the characteristics of multiple diseases, it is possible to classify patients who require specific procedures based on the identified severity. It has the effect of further increasing the appropriateness of emergency treatment for each emergency symptom by ensuring that emergency patients are transferred to the target institution or facility that is optimal for treatment for each emergency symptom.

1 is a block diagram of a computing device according to an embodiment of the present disclosure.
FIG. 2 is a block diagram illustrating the configuration of a system that provides transport services for emergency patients and monitoring of hospitalized patients based on electrocardiograms according to an embodiment of the present disclosure.
Figure 3 is a diagram illustrating a process for identifying change trends using a neural network model according to an embodiment of the present disclosure.
FIG. 4 is a flowchart illustrating a method of providing transport services for emergency patients and monitoring of hospitalized patients based on electrocardiograms according to an embodiment of the present disclosure.
Figure 5 is a flowchart illustrating in detail a method of selecting a target institution or target facility suitable for treating emergency patients according to an embodiment of the present disclosure.

Below, with reference to the attached drawings, embodiments of the present disclosure are described in detail so that those skilled in the art (hereinafter referred to as skilled in the art) can easily implement the present disclosure. The embodiments presented in this disclosure are provided to enable any person skilled in the art to use or practice the subject matter of this disclosure. Accordingly, various modifications to the embodiments of the present disclosure will be apparent to those skilled in the art. That is, the present disclosure can be implemented in various different forms and is not limited to the following embodiments.

The same or similar reference numerals refer to the same or similar elements throughout the specification of this disclosure. Additionally, in order to clearly describe the present disclosure, reference numerals in the drawings may be omitted for parts that are not related to the description of the present disclosure.

As used in this disclosure, the term “or” is intended to mean an inclusive “or” and not an exclusive “or.” That is, unless otherwise specified in the present disclosure or the meaning is not clear from the context, “x uses a or b” should be understood to mean one of natural implicit substitutions. For example, unless otherwise specified in the present disclosure or the meaning is not clear from the context, “x uses a or b” means that x uses a, x uses b, or x uses a and It can be interpreted as one of the cases where both b are used.

The term “and/or” as used in this disclosure should be understood to refer to and include all possible combinations of one or more of the listed related concepts.

The terms “comprise” and/or “comprising” as used in this disclosure should be understood to mean that certain features and/or elements are present. However, the terms "comprise" and/or "including" should be understood as not excluding the presence or addition of one or more other features, other components, and/or combinations thereof.

Unless otherwise specified in this disclosure or the context is clear to indicate a singular form, the singular should generally be construed to include “one or more.”

The term "th nth (n is a natural number)" used in the present disclosure can be understood as an expression used to distinguish the components of the present disclosure according to a predetermined standard such as a functional perspective, a structural perspective, or explanatory convenience. there is. For example, in the present disclosure, components performing different functional roles may be distinguished as first components or second components. However, components that are substantially the same within the technical spirit of the present disclosure but must be distinguished for convenience of explanation may also be distinguished as first components or second components.

The term “acquisition” used in this disclosure is understood to mean not only receiving data through a wired or wireless communication network with an external device or system, but also generating data in an on-device form. It can be.

Meanwhile, the term "module" or "unit" used in this disclosure refers to a computer-related entity, firmware, software or part thereof, hardware or part thereof. , can be understood as a term referring to an independent functional unit that processes computing resources, such as a combination of software and hardware. At this time, the “module” or “unit” may be a unit composed of a single element, or may be a unit expressed as a combination or set of multiple elements. For example, a "module" or "part" in the narrow sense is a hardware element or set of components of a computing device, an application program that performs a specific function of software, a process implemented through the execution of software, or a program. It can refer to a set of instructions for execution, etc. Additionally, as a broad concept, “module” or “unit” may refer to the computing device itself constituting the system, or an application running on the computing device. However, since the above-described concept is only an example, the concept of “module” or “unit” may be defined in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

As used in this disclosure, the term "model" refers to a system implemented using mathematical concepts and language to solve a specific problem, a set of software units to solve a specific problem, or a process to solve a specific problem. It can be understood as an abstract model of a process. For example, a neural network “model” may refer to an overall system implemented as a neural network that has problem-solving capabilities through learning. At this time, the neural network can 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 set in which multiple neural networks are combined.

The term “block” used in the present disclosure can be understood as a set of components divided based on various criteria such as type, function, etc. Accordingly, the configuration classified as one “block” can be changed in various ways depending on the standard. For example, a neural network “block” can be understood as a set of neural networks containing at least one neural network. At this time, it can be assumed that the neural networks included in the neural network “block” perform the same specific operation. The explanation of the foregoing terms is intended to aid understanding of the present disclosure. Therefore, if the above-mentioned terms are not explicitly described as limiting the content of the present disclosure, it should be noted that the content of the present disclosure is not used in the sense of limiting the technical idea.

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

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 processing and calculation of data, or may be a software-based computing environment connected to a communication network. For example, the computing device 100 may be a server that performs intensive data processing functions and shares resources, or it may be a client that shares resources through interaction with the server. Additionally, the computing device 100 may be a cloud system in which a plurality of servers and clients interact to comprehensively process data. Since the above description is only an example related to the type of computing device 100, the type of computing device 100 may be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

Referring to FIG. 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. there is. However, since FIG. 1 is only an example, the computing device 100 may include other components for implementing a computing environment. Additionally, only some of the configurations disclosed above may be included in computing device 100.

The processor 110 according to an embodiment of the present disclosure may be understood as a structural unit including hardware and/or software for performing computing operations. For example, the processor 110 may read a computer program and perform data processing for machine learning. The processor 110 may process computational processes such as processing input data for machine learning, extracting features for machine learning, and calculating errors based on backpropagation. The processor 110 for performing such data processing includes a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), a tensor processing unit (TPU), and a custom processing unit (TPU). It may include a semiconductor (ASICc: application specific integrated circuit), or a field programmable gate array (FPGA: field programmable gate array). Since the type of processor 110 described above is only an example, the type of processor 110 may be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

The processor 110 uses a pre-trained neural network model to diagnose and predict diseases based on the acquired electrocardiogram data of emergency patients, and ensures that emergency patients are transferred to the optimal hospital when an emergency situation occurs. At this time, the processor 110 may extract ECG features based on ECG data and train a neural network model that calculates a predicted value corresponding to the probability of occurrence of each of a plurality of heart diseases based on the extracted ECG features. For example, the processor 110 may learn a neural network model to estimate heart disease by analyzing the ECG based on biological information including information such as gender, age, weight, height, etc., along with the ECG data.

Specifically, the processor 110 may input electrocardiogram data and various biological information into the neural network model and train the neural network model to detect changes in the electrocardiogram due to arrhythmia or other heart diseases. At this time, the neural network model can perform learning based on an ECG dataset that includes ECG features extracted from ECG data and diagnostic data for arrhythmia and other heart diseases. The processor 110 may perform an operation representing at least one neural network block included in the neural network model during the learning process of the neural network model.

The processor 110 may extract ECG features from ECG data obtained from an ECG meter using a neural network model generated through the above-described learning process, and estimate ECG reading data based on the extracted ECG features. The processor 110 inputs biological information including electrocardiogram data and information such as gender, age, weight, height, etc. into a neural network model learned through the above-described process to generate inference data representing the result of estimating the probability of heart disease. can be created. For example, the processor 110 may input electrocardiogram data into a trained neural network model and provide predicted values such as the presence or progression of arrhythmia or other heart disease.

In addition to the examples described above, the types of medical data and the output of the neural network model may be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

The memory 120 according to an embodiment of the present disclosure may be understood as a structural unit including hardware and/or software for storing and managing data processed in the computing device 100. That is, the memory 120 can 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 be a flash memory type, hard disk type, multimedia card micro type, card type memory, or random access memory (RAM). ), SRAM (static random access memory), ROM (read-only memory), EEPROM (electrically erasable programmable read-only memory), PROM (prom: programmable read-only memory), magnetic memory , may include at least one type of storage medium among a magnetic disk and an optical disk. Additionally, the memory 120 may include a database system that controls and manages data in a predetermined system. Since the type of memory 120 described above is only an example, the type of memory 120 may be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

The memory 120 can structure, organize, and manage data necessary for the processor 110 to perform operations, combinations of data, and program codes executable on the processor 110. For example, the memory 120 may store ECG data received through the network unit 130, which will be described later. The memory 120 includes program code that operates the neural network model to receive medical data and perform learning, program code that operates the neural network model to receive medical data and perform inference according to the purpose of use of the computing device 100, and Processed data generated as the program code is executed can be saved.

The network unit 130 according to an embodiment of the present disclosure may be understood as a structural unit that transmits and receives data through any type of known wired or wireless communication system. For example, the network unit 130 may be connected to a local area network (LAN), wideband code division multiple access (WCDMA), long term evolution (LTE), or wireless (WIBRO). broadband internet, 5th generation mobile communication (5g), ultra wide-band wireless communication, zigbee, radio frequency (RF) communication, wireless LAN, wireless fidelity ), data transmission and reception can be performed using a wired or wireless communication system such as near field communication (NFC), or Bluetooth. Since the above-described communication systems are only examples, the wired and wireless communication systems for data transmission and reception of the network unit 130 may be applied in various ways other than the above-described examples.

The network unit 130 may receive data necessary for the processor 110 to perform calculations through wired or wireless communication with any system or client. Additionally, the network unit 130 may transmit data generated through the calculation of the processor 110 through wired or wireless communication with any system or any client. For example, the network unit 130 may receive medical data through communication with an electrocardiogram monitor 10, including a wearable device. The network unit 130 may transmit output data of the neural network model, intermediate data derived from the calculation process of the processor 110, processed data, etc. through communication with the above-mentioned devices.

FIG. 2 is a block diagram illustrating the configuration of a system that provides transport services for emergency patients and monitoring of hospitalized patients based on electrocardiograms according to an embodiment of the present disclosure, and FIG. 3 is a neural network according to an embodiment of the present disclosure. This diagram explains the process of identifying change trends using a model.

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

The local device 10 is a device capable of measuring electrocardiograms and may be installed in 119 paramedics, emergency patients, or ambulances. This local device 10 uses a variety of devices capable of measuring electrocardiograms, such as wearable devices that are worn on the emergency patient's body and can measure and collect various health indicators such as heart rate, body fat percentage, and blood pressure, portable electrocardiogram meters, and biosignal measurement equipment. You can. At this time, the local device 10 can measure the electrocardiogram using various electrode combinations, such as a 12-lead method or a 6-lead method, as well as a single-guide method using a wearable device such as a wrist watch or a patch. It is desirable that the ECG measurement time is also set by adding or subtracting depending on the signal to be obtained.

The computing device 100 uses the pre-trained neural network model 200 to extract ECG features including P waves, QRS complexes, and T waves based on ECG data acquired from the ECG meter 10. You can. At this time, the neural network model may be learned based on ECG characteristics including at least one of the frequency of tachycardia, the length of the QT interval, the direction of deviation of the P wave, R wave, and T wave, or the QRS duration.

This computing device 100 includes a first server 110 for electrocardiogram reading and a second server 120 for emergency patient management, where the first server 110 and the second server 120 operate independently. Or, it can be integrated and operated.

As shown in FIG. 3, the first server 110 uses a pre-trained neural network model 200 to calculate a predicted value corresponding to the probability of occurrence of each of a plurality of heart diseases based on electrocardiogram data, and calculates Based on the predicted value, the severity level for classifying emergency patients is calculated. The first server 110 may include a classification model in which the pre-trained neural network model 200 can calculate a prediction value corresponding to the probability of occurrence of each heart disease. Therefore, the first server 110 gradually inputs the ECG data into a plurality of pre-trained classification models to classify it as a heart disease with high accuracy, and uses each classification model to generate a predicted value corresponding to the probability of occurrence of each heart disease. It can be calculated.

For example, a neural network model can build multiple classification models corresponding to the type of heart disease you want to identify, such as ST-segment elevation myocardial infarction (STEMI), Left ventricular systolic dysfunction (LVSD), 24 It is possible to predict the probability of occurrence of each disease, such as cardiac arrest and NSTEMI (Non-ST segment elevation myocardial infarction), within an hour.

At this time, the predicted value provided by each classification model can be calculated as a numerical value within 0 to 100, and after identifying the change trend in the predicted value of each classification model, the level of severity is determined according to the identified change trend and the characteristics of the plurality of diseases. can do.

The level of severity can be determined by selecting the following judgment methods to determine the change trend of the predicted value according to the characteristics of a plurality of diseases, and determining the level of severity based on the change trend identified according to the selected judgment method.

That is, the second server 120 determines whether the predicted value (or disease score, numerical value) calculated by the neural network model is in an upward trend, determines whether the predicted value is in a downward trend or repeats decline and rise, and determines whether the predicted value is in a downward trend or repeats decline and rise. A method of judging using the steepness (e.g., slope) of the rising curve, a method of determining whether the predicted value is outside of a predetermined cutoff, and a method of calculating the size of the area after displaying the predicted value on a graph. Among the methods of determining whether the size exceeds the preset size, a judgment method is selected according to the characteristics of the disease and the severity level is finally determined.

For example, the level of severity is the first level corresponding to the case where the predicted value is on an upward trend, the second level corresponding to the case where the predicted value repeats rise and fall without an upward trend within the preset upper limit category, and the second level corresponding to the case where the predicted value is within the upper limit category. (e.g., 70) and a third level that corresponds to cases where the predicted value repeats rises and falls within the preset lower limit category (e.g., 30) and corresponds to cases where the predicted value repeats rises and falls within the lower limit category. It can be divided into the fourth level.

Based on the classification model of STEMI, the first server 110 sets the level of severity to the third level because the trend of change in the predicted value repeats rise and fall within the upper and lower limit categories as the number of ECG measurements increases. , Based on the LVSD classification model, as the number of ECG measurements increases, the range of the predicted value tends to rise beyond the upper limit range, so the level of severity is set to the first level. In addition, the first server 110 determines that the change trend in the predicted value based on the classification model for cardiac arrest within 24 hours cannot be determined as an upward trend or a falling trend, and therefore, the change trend in the predicted value based on the NSTEMI classification model is the lower limit. Since it repeats rise and fall within the category, set it to the fourth level.

At this time, when the level of severity is determined to be the fourth level more than a preset number of times, the first server 110 may terminate prediction value calculation using the neural network model 200 and stop electrocardiogram measurement.

The second server 120 uses the calculated severity to select a target institution or facility suitable for treatment of the emergency patient and ensures that the emergency patient is transferred to the selected target institution or facility. This second server 120 is linked to the 119 reporting center or emergency situation management center, and can deliver dispatch information to the fire department or 119 safety center according to the emergency situation report, and plan the transport of emergency patients depending on the emergency situation or medical environment. can be established.

The second server 120 uses the severity of the emergency patient based on the severity classification commonly used by emergency personnel and medical staff and the severity calculated based on the predicted value to classify the emergency patient as the first patient requiring a specific procedure or a specific procedure. It can be classified as one of the second patients who do not need this. For example, the triage commonly used by emergency personnel and medical staff can use the Korean Prehospital Korean Triage and Acuity Scale (Pre-KTAS) method.

[Table 1: Comparison of 119 Paramedic Service and KTAS classification for emergency patients]

As shown in Table 1, the Korean Prehospital Korean Triage and Acuity Scale (Pre-KTAS) is classified into grade 1 (resuscitation: very serious), grade 2 (urgent), depending on the level of emergency of the emergency patient at the prehospital stage. It is classified into Grade 3 (emergency), Grade 4 (semi-emergency), and Grade 5 (non-emergency: very mild), and the medical treatment time for each grade is defined as immediate, within 10 minutes, 30 minutes, 60 minutes, and 120 minutes. The Korean pre-hospital triage (Pre-KTAS) indicates that the lower the triage level, the higher the severity, and the higher the priority of treatment.

Before transferring the emergency patient to the hospital, the second server 120 uses the severity calculated based on the severity and predicted value of the emergency patient measured by the severity classification commonly used by emergency personnel and medical staff to treat the emergency patient. Classified as either a first patient requiring a specific procedure or a second patient not requiring a specific procedure. For example, the second server 120 may perform a procedure that can only be performed at a specific hospital or through a specific medical staff (e.g., PCI Patients who require surgery or whose severity calculated based on the predicted value is judged to be higher than the preset standard for each disease (for example, patients whose severity level based on the STEMI classification model is the second level or higher) can be classified as first patients. You can.

In addition, the second server 120 provides treatment of emergency patients in a group of hospitals matched to 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. Extract candidate hospitals for each candidate hospital, calculate the suitability of the candidate hospitals using capacity information including at least one of emergency room congestion, emergency facility information, or medical staff information for each candidate hospital, and then calculate suitability based on the calculated suitability. A transfer plan can be established according to hospital priorities.

In addition, the second server 120 continuously determines the severity of emergency patients transferred from the emergency room by providing alternative transfer plans and transfers to emergency patients as well as monitoring services for inpatients, and transfers them to other hospitals according to the determined severity. It allows you to decide whether to transfer the patient or move the patient from a general ward to an intensive care ward.

FIG. 4 is a flowchart illustrating a method of providing transport services for emergency patients and monitoring of hospitalized patients based on electrocardiograms according to an embodiment of the present disclosure.

Referring to FIG. 4, the computing device 100 acquires electrocardiogram data of an emergency patient at preset time intervals according to an emergency situation report (S10). At this time, the second server 120 can transmit a link or QR code that can measure and transmit an electrocardiogram to the emergency patient, and when connection using the link or QR code is completed by the emergency patient, guardian, or 119 paramedic, By connecting to the local device 10, the emergency patient's electrocardiogram can be automatically measured and transmitted at periodic time intervals (for example, 3 minutes). Even if the periodic time interval for ECG measurement is reached, the second server 120 waits for a certain period of time to measure the ECG if the emergency patient is moving or has a lot of movement, and then measures the ECG again after a certain period of time has elapsed. can do. This is because when an emergency patient is on the move or has a lot of movement, the accuracy of the measured electrocardiogram may decrease and the electrocardiogram may be judged as undetectable when reading.

The second server 120 transmits the acquired ECG data to the first server 110, and the first server 110 uses a pre-trained neural network model to detect myocardial infarction and cardiac arrest within 24 hours based on the ECG data. , a predictive value corresponding to the probability of occurrence of each of multiple heart diseases such as arrhythmia is calculated (S20).

The first server 110 transmits the calculated predicted value to the second server 120, and the second server 120 determines the change trend in the predicted value transmitted at preset time intervals, and determines the identified change trend and a plurality of The severity is calculated to classify emergency patients according to the characteristics of the diseases (S30), and the calculated severity is used to select target institutions or facilities suitable for treating emergency patients (S40).

FIG. 5 is a flowchart illustrating in detail a method of selecting a target institution or facility suitable for treating emergency patients according to an embodiment of the present disclosure.

Referring to FIG. 5, the computing device 100 uses the severity of the emergency patient measured by the severity classification commonly used by emergency personnel and medical staff and the severity calculated based on the predicted value calculated by the neural network model, The patient is classified as either a first patient requiring a specific procedure or a second patient not requiring a specific procedure (S41).

At this time, the first patient may include at least one of a patient in need of a procedure that can only be performed at a specific hospital or by a specific medical staff, or a patient whose severity calculated based on the predicted value is determined to be higher than a preset level for each disease.

For the first patient, computing device 100 may provide 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 a hospital capable of performing a specific procedure (e.g., a PCI procedure). As a basis, candidate hospitals for treatment of emergency patients are extracted from the hospital group matching the first patient (S42, S43). At this time, the computing device 100, that is, the second server 120, is capable of collecting real-time traffic information through the ITS National Traffic Information Center and provides access to the hospital through a navigation operator that guides the route based on the user's real-time location information. The number of ambulances heading to can be collected.

In the case of the second patient, computing device 100 provides the patient 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, depending on the severity according to pre-KTAS. 2 Candidate hospitals are extracted from the hospital group matching the patient (S42, S44). If the level of severity according to Pre-KTAS corresponds to the first and second levels, the computing device 100 operates at a regional/severe emergency center, and if the level of severity corresponds to the second and third levels, the computing device 100 operates at a regional emergency medical center. If the center and level of severity correspond to level 4 and level 5, they are matched to the hospital group of the local emergency medical institution, respectively.

The computing device 100 can use location and traffic information to calculate expected transfer time information for each hospital included in the hospital group matching the patient classification, and extract candidate hospitals based on the expected transfer time information. there is.

The computing device 100 calculates the suitability of the candidate hospitals using capacity information including at least one of emergency room congestion, emergency facility information, or medical staff personnel information for each of the extracted candidate hospitals (S45), and calculates the calculated suitability. Establish a transfer plan according to hospital priorities based on (S46). The second server 120 can periodically collect capacity information such as real-time congestion for each emergency room, emergency facility information, and medical staff personnel information through each hospital's website, hospital website, or the National Emergency Medical Services Information Network (NEDIS).

At this time, when establishing a transfer plan, the computing device 100 may provide communication services such as a wired inquiry from an emergency medical technician or a voice AI inquiry to confirm whether or not the patient is accepted at N hospitals selected according to hospital priority. After transporting an emergency patient to an appropriate hospital according to hospital priority, the computing device 100 uses the accumulated ECG data and analysis results (predicted values, change trends, etc.) from the reporting of the emergency situation until arrival at the final hospital to treat the emergency patient. It can be delivered to the medical staff in charge. In addition, the computing device 100 continuously determines the severity of emergency patients even in medical environments, including emergency rooms, and continuously determines whether to transfer to another hospital or move from a general ward to an intensive care ward based on the judged severity. Monitoring services for emergency patients can be provided for a certain period of time or until treatment of emergency patients is completed.

As such, in the present disclosure, the electrocardiogram of an emergency patient can be measured at periodic time intervals, and a predicted value for each possibility of occurrence of heart disease can be calculated using a pre-trained neural network model, and a predicted value for the possibility of occurrence of heart disease We are establishing a transport plan for emergency patients based on the change trends and characteristics of multiple diseases. At this time, in the present disclosure, if the probability of occurrence of one or more heart diseases is estimated to be low according to the change in the predicted value, the level of severity of the emergency patient is set to a preset level or lower, and the level of severity of the emergency patient is set to a level lower than the preset level, and the level of severity of the emergency patient is set to a high probability of occurrence of one or more heart diseases. If it is estimated, the severity level of the emergency patient is determined to be very high, and a transfer plan is established so that the emergency patient can be quickly transferred to a hospital that can provide treatment or procedures for cardiac disease.

Therefore, the present disclosure can provide a transport plan, such as a hospital and transport route capable of emergency treatment and specific procedures, based on a fast and accurate prediction value for the possibility of occurrence of heart disease using a pre-trained neural network model, and thereby No unnecessary time is spent on the rapid transfer of emergency patients, and resources and time needed for emergency treatment are not wasted. Above all, the present disclosure uses a neural network model, rather than an emergency medical technician (or 119 paramedic), to classify patients such as patients with simple chest pain and patients with myocardial infarction, rather than myocardial infarction, and is able to classify patients with emergency symptoms at the pre-hospital stage of emergency patients. The appropriateness of first aid can be further improved.

The various embodiments of the present disclosure described above may be combined with additional embodiments and may be changed within the scope understandable to those skilled in the art in light of the above detailed description. The embodiments of the present disclosure should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form. Accordingly, all changes or modified forms derived from the meaning and scope of the claims of the present disclosure and their equivalent concepts should be construed as being included in the scope of the present disclosure.

Claims (10)

1. A method of providing transport services for emergency patients and monitoring of hospitalized patients based on electrocardiograms, the method performed by a computing device comprising at least one processor, the method comprising:
Acquiring electrocardiogram data of an emergency patient at preset time intervals;
Using a pre-trained neural network model, calculating a predicted value corresponding to the probability 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; and
Using the calculated severity, selecting a target institution or facility suitable for treatment of the emergency patient;
Including,
method.
According to paragraph 1,
The step of calculating the severity for classifying emergency patients based on the predicted value is,
Identifying a change trend in the predicted value and determining the level of severity according to the identified change trend and characteristics of the plurality of diseases;
Including,
method.
According to paragraph 2,
Identifying a change trend in the predicted value and determining the level of severity according to the identified change trend and characteristics of the plurality of diseases,
selecting judgment methods for identifying a change trend in the predicted value according to characteristics of the plurality of diseases; and
determining the level of severity based on a change trend identified according to the selected judgment method;
Including,
method.
According to paragraph 3,
The above judgment method is,
A method of determining whether the predicted value calculated by the neural network model is in an upward trend, a method of determining whether the predicted value is a downward trend or repeats decline and rise, a method of determining using the slope of an upward curve for the predicted value, A method of determining whether the predicted value deviates from a preset cutoff, or a method of displaying the predicted value on a graph and calculating the size of the area to determine whether it deviates from the preset size,
method.
According to paragraph 1,
The step of selecting a target institution or facility suitable for treatment of the emergency patient using the calculated severity,
Using the severity of the emergency patient measured by the severity classification commonly used by emergency personnel and medical staff and the severity calculated based on the predicted value, the emergency patient is classified as the first patient requiring a specific procedure or the first patient not requiring a specific procedure. classifying the second patient as one of the second patients;
Extracting candidate hospitals for treatment of 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. step; and
Calculate the suitability of the candidate hospitals using capacity information including at least one of emergency room congestion, emergency facility information, or medical staff personnel information for each of the candidate hospitals, and transfer according to hospital priority based on the calculated suitability. making a plan;
Including,
method
According to clause 5,
The first patient was,
Including at least one of patients who require a procedure that can only be performed at a specific hospital or by a specific medical staff, or patients whose severity calculated based on the above predicted value is judged to be higher than the preset standard for each disease,
method.
According to clause 5,
Extracting candidate hospitals for treatment of 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. The steps are,
Using the location and traffic information, calculating expected transfer time information for hospitals included in the hospital group matching the classification; and
extracting candidate hospitals for treatment of the emergency patient from a group of hospitals matching the classification, based on the expected transfer time information;
Including,
method.
According to clause 5,
The suitability of the candidate hospitals is calculated using capacity information including at least one of emergency room congestion, emergency facility information, or medical staff manpower information, and a transfer plan is made according to hospital priority based on the calculated suitability. The steps to establish are:
Providing a communication service to check whether patients are accepted at N hospitals selected according to the hospital priority;
Including,
method.
A computer program stored in a computer-readable storage medium, wherein the computer program, when executed on one or more processors, performs operations for providing transport services for emergency patients and monitoring of hospitalized patients based on electrocardiograms. And
The above operations are:
An operation of acquiring electrocardiogram data of an emergency patient at preset time intervals;
Using a pre-trained neural network model, calculating a predicted value corresponding to the probability 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; and
An operation of selecting a target institution or facility suitable for treatment of the emergency patient using the calculated severity;
Including,
computer program.
A computing device for providing transport services for emergency patients and monitoring of hospitalized patients based on electrocardiograms,
A processor including at least one core; and
a memory containing program codes executable on the processor;
Including,
The processor, according to execution of the program code,
Obtain electrocardiogram data from emergency patients at preset time intervals,
Using a pre-trained neural network model, a predicted value corresponding to the probability of occurrence of each of a plurality of diseases is calculated based on the electrocardiogram data,
Calculate the severity for classifying the emergency patient based on the predicted value,
Using the calculated severity, select a target institution or facility suitable for treatment of the emergency patient,
Device.

Images