KR102479692B1 - Big data and cloud system based AI(artificial intelligence) emergency medical care decision-making and emergency patient transfer system and method thereof - Google Patents

Abstract

The present invention relates to an artificial intelligence emergency medical decision-making and emergency patient transfer system and method based on big data and cloud systems.
The big data and cloud system-based artificial intelligence emergency medical decision-making and emergency patient transport method according to the present invention includes the steps of a user terminal accessing the site of an emergency medical service provider when an emergency patient occurs, recording and transmitting the emergency patient's condition ; Step of the emergency medical service providing server receiving the emergency patient's condition information and transmitting the patient's condition information to the cloud platform server; The cloud platform server receives the patient's condition information, and derives an estimated diagnosis, necessary examination and treatment based on the patient's condition information by artificial intelligence trained with big data; Transmitting the patient's condition information from the cloud platform server to a server of a hospital capable of treating an emergency patient; And the hospital server receives the estimated diagnosis derived from the cloud platform server, necessary examination and treatment information, and the patient's condition information, and based on it, determines the order of treatment (treatment) according to the severity of the emergency patient so that prompt response can be made Including processing related tasks.

Description

Big data and cloud system based AI(artificial intelligence) emergency medical care decision-making and emergency patient transfer system and method thereof}

The present invention relates to a big data and cloud system-based artificial intelligence emergency medical decision-making and emergency patient transport system and method, and more particularly, to help patients in medical decision-making in the event of an emergency and to quickly transport emergency patients. It relates to a big data and cloud system-based artificial intelligence emergency medical decision-making and emergency patient transportation system and method for transporting to a hospital and enabling medical treatment and treatment (treatment) in the fastest possible time.

In general, when an emergency occurs, the patient himself makes a decision about the medical situation and decides whether to visit the hospital. Also, even the hospital you visit must be decided by yourself. Therefore, unnecessary time and cost are caused, and limited resources are consumed in the emergency room.

Currently, emergency medical consultations are being operated by the Emergency Situations Center of the Fire and Disaster Management Agency, and the Central Emergency Medical Center is assisting them, but the realistic emergency room situation is not so optimistic. Large emergency rooms, starting with university hospitals in the metropolitan area, are always full, and even if patients go to the hospital with help from 119, they will wait for a very long time. This not only causes the golden time to be missed, but also lowers the quality of health care that patients receive.

A further problem is that each patient's condition is different, and since the fire department, not a medical expert, leads the medical consultation, in most cases it is only a fragmentary and peripheral medical consultation. Therefore, the reliability of medical consultation is not high and the location of responsibility is also unclear.

Currently, many university hospitals are trying to build a 'smart emergency medical system'. The national emergency medical information network (NEDIS), the National Fire Agency, and the emergency room are trying to collect scattered emergency medical data in one place, but there are currently no clear results, and the landscape of the emergency room has not changed much either.

On the other hand, Korean Patent Publication No. 10-2014-0089021 (Patent Document 1) discloses "integrated emergency medical center management system and method using mobile devices", and accordingly, integrated emergency medical center management using mobile devices. The system connects to the emergency management integration server to request hospital guidance and location service that manages the hospital's GPS coordinates and guidance, specialist management service request of the hospital, and emergency medical center information service request, and receives information provided from the emergency management integration server. a user mobile device receiving information; An integrated emergency management server that processes information requested from the user's mobile device, collects and provides information requested by the user; A hospital information and location service unit providing hospital information and location information upon request for information from the emergency management integrated server, a specialist management service unit providing specialist information, and an emergency medical center providing emergency medical center information in the hospital. It is characterized in that it includes; information service unit.

According to such Patent Document 1, there is an advantage in providing integrated emergency medical services in accordance with the amendment to the Emergency Medical Care Act by searching for specialists in emergency medical centers in each hospital and showing the situation and location of the emergency medical centers in real time. However, there is a problem in that it is not possible to help the patient make a decision about the medical situation because there is no means to quickly respond to the patient's inquiry based on professional medical knowledge.

Korean Patent Publication No. 10-2014-0089021 (2014.07.14.)

The present invention was created in consideration of the above matters comprehensively, and helps the patient in making medical decisions, and the emergency medicine department, as well as the corresponding medical doctor or medical artificial intelligence, responds to the patient's inquiry in real time 24 hours a day. In addition, to provide an artificial intelligence emergency medical decision-making and emergency patient transportation system and method based on big data and cloud systems that enable emergency patients to be quickly transported to hospitals and receive medical treatment and treatment (treatment) in the fastest possible time. There is a purpose.

In order to achieve the above object, the artificial intelligence emergency medical decision-making and emergency patient transport system based on big data and cloud system according to the present invention,

When an emergency patient occurs, a user terminal that records and transmits the condition of the emergency patient by accessing the site of the emergency medical service provider from the site where the emergency patient is located or from the emergency patient transport vehicle;

An emergency medical service providing server built in an emergency medical service provider, receiving emergency patient condition information from the user terminal and transmitting the patient's condition information to a cloud platform server;

Personal health record data or information is stored in a database (DB), receives patient condition information from the emergency medical service providing server, and estimates diagnosis based on the patient condition information by artificial intelligence trained with big data, A cloud platform server that derives necessary tests and treatments and transmits the patient's condition information to a hospital server capable of treating the emergency patient; and

Estimated diagnosis derived from the cloud platform server, necessary examination and treatment information, and patient condition information are received, and based on this, the order of treatment (treatment) is determined according to the severity of emergency patients, and related tasks are performed so that prompt response can be made. Its feature is that it includes a hospital server that handles it.

Here, the cloud platform server is equipped with an application that fuses medical information obtained from external doctors, medical institutions, and national emergency medical networks linked to the network with personal health record data or information stored in the database (DB) It can be.

In addition, the cloud platform server may be equipped with an application for real-time identification of hospital beds and human resources capable of testing and treating the emergency patient.

At this time, the cloud platform server may also be equipped with an application for transmitting condition information of the patient to a server of a hospital capable of treating the emergency patient based on the identification result.

In addition, the artificial intelligence employed in the cloud platform server can be trained to explore and statistically analyze medical data in which Korean, English, and medical terms are mixed using an exploratory data analysis (EDA) technique.

In this case, the artificial intelligence may be based on a federated learning method in which a plurality of local clients and a central server cooperate to modify and learn a global model in a situation where data is decentralized.

In addition, the artificial intelligence employed in the cloud platform server may have a function of answering when a patient inquires about an emergency.

At this time, when the patient is connected by phone to inquire about an emergency situation, the artificial intelligence can answer the inquiry using a Korean voice recognition system using CTC (Connectionist Temporal Classification) and LAS (Listen and Spell) algorithms. .

At this time, when the patient uses the Internet homepage to inquire about an emergency, the artificial intelligence understands the inquiry using natural language understanding (NLU) and natural language generation (NLG). You can respond to inquiries by creating response contents through.

At this time, when the patient uses an application to inquire about an emergency, the artificial intelligence provides a body-map that allows the patient to display his or her painful area in a touch-type manner provided by the app for an accurate answer. After collecting the patient's opinion or judgment through the body-map screen or STT (Speech-to-Text) function tool that allows patients with poor eyesight to express their symptoms verbally, Information to help patients make decisions can be provided in response to inquiries.

Here, the app may preferably further include a multilingual conversion (language selection) function.

Also, preferably, the emergency patient transfer vehicle may be equipped with a fingerprint reader, a face recognition device, a biometric information extraction device, etc. for identifying the emergency patient and extracting information about the emergency patient.

In addition, in order to achieve the above object, the artificial intelligence emergency medical decision-making and emergency patient transfer method based on big data and cloud system according to the present invention,

a) the user terminal accessing the site of an emergency medical service provider at the site where the emergency patient is located or the emergency patient transport vehicle when an emergency patient occurs, and recording and transmitting the state of the emergency patient;

b) an emergency medical service providing server of an emergency medical service provider receiving emergency patient condition information from the user terminal and transmitting the patient's condition information to a cloud platform server;

c) receiving, by a cloud platform server, the patient's condition information from the emergency medical service providing server, and deriving an estimated diagnosis, necessary examination and treatment based on the patient's condition information by artificial intelligence trained with big data;

d) transmitting, by a cloud platform server, state information of the patient to a server of a hospital capable of treating the emergency patient; and

e) The hospital server receives the estimated diagnosis derived from the cloud platform server, necessary examination and treatment information, and the patient's condition information, and based on it, determines the order of treatment (treatment) according to the severity of the emergency patient, while prompt response is achieved. Its feature is that it includes steps to process related tasks so that

Here, in the step c), the cloud platform server fuses medical information obtained from external doctors, medical institutions, and national emergency medical networks linked to the network with personal health record data or information stored in its own database (DB) An application that does this can be loaded.

In addition, the cloud platform server may be equipped with an application for real-time identification of hospital beds and human resources capable of testing and treating the emergency patient.

At this time, the cloud platform server may also be equipped with an application for transmitting condition information of the patient to a server of a hospital capable of treating the emergency patient based on the identification result.

In addition, the artificial intelligence employed in the cloud platform server can be trained to explore and statistically analyze medical data in which Korean, English, and medical terms are mixed using an exploratory data analysis (EDA) technique.

In this case, the artificial intelligence may be based on a federated learning method in which a plurality of local clients and a central server cooperate to modify and learn a global model in a situation where data is decentralized.

In addition, the artificial intelligence employed in the cloud platform server may have a function of answering when a patient inquires about an emergency.

At this time, when the patient is connected by phone to inquire about an emergency situation, the artificial intelligence can answer the inquiry using a Korean voice recognition system using CTC (Connectionist Temporal Classification) and LAS (Listen and Spell) algorithms. .

At this time, when the patient uses the Internet homepage to inquire about an emergency, the artificial intelligence understands the inquiry using natural language understanding (NLU) and natural language generation (NLG). You can respond to inquiries by creating response contents through.

At this time, when the patient uses an application to inquire about an emergency, the artificial intelligence provides a body-map that allows the patient to display his or her painful area in a touch-type manner provided by the app for an accurate answer. After collecting the patient's opinion or judgment through the body-map screen or STT (Speech-to-Text) function tool that allows patients with poor eyesight to express their symptoms verbally, Information to help patients make decisions can be provided in response to inquiries.

Here, the app may preferably further include a multilingual conversion (language selection) function.

Also, preferably, the emergency patient transfer vehicle may be equipped with a fingerprint reader, a face recognition device, a biometric information extraction device, etc. for identifying the emergency patient and extracting information about the emergency patient.

According to the present invention, the patient is assisted in medical decision-making, the emergency medicine department and the corresponding medical doctor or medical artificial intelligence respond to the patient's inquiry in real time 24 hours a day, and the emergency patient is quickly transported to the hospital. It has the advantage of being able to receive medical treatment and treatment (treatment) in the fastest possible time by transporting it.

In addition, the hospital side has the advantage of being able to efficiently manage the limited resources and manpower of the emergency room.

1 is a diagram schematically showing the configuration of an artificial intelligence emergency medical decision-making and emergency patient transport system based on big data and cloud systems according to the present invention.
Figure 2 is a flowchart showing the execution process of the artificial intelligence emergency medical decision-making and emergency patient transfer method based on big data and cloud system according to the present invention.
3 is a diagram showing the operating state of the big data and cloud system-based artificial intelligence emergency medical decision-making and emergency patient transport system according to the present invention.
4 is a view showing a body-map for displaying a patient's painful area by touch and a screen for providing an oral expression STT function.
5 is a diagram illustrating a process of determining severity by an artificial intelligence prediction model based on information about a patient obtained through an app employed in the present invention.
6 is a diagram showing a severity classification system and a multilingual conversion (language selection) function employed in the present invention.
7 is a diagram showing an emergency treatment process employed in the present invention.
8 is a diagram showing evaluation items of a record form recorded for a patient by emergency personnel.
9 is a diagram showing an outline of federated learning in which a plurality of local clients and a central server cooperate to learn a global model employed in the present invention.
10 is a diagram showing the configuration of a 5G communication artificial intelligence (AI)-based emergency medical system employed in the present invention.
11 is a diagram showing an outline of a smart emergency medical service (SEMS) system employed in the present invention.
12 is a diagram showing a comparison between a conventional emergency patient treatment process and the services of an artificial intelligence emergency medical decision-making and emergency patient transfer system according to the present invention.

The terms or words used in this specification and claims should not be construed as being limited to their usual or dictionary meanings, and the inventors can properly define the concept of terms in order to best explain their invention. Based on the principle, it should be interpreted as meaning and concept consistent with the technical idea of the present invention.

Throughout the specification, when a certain component is said to "include", it means that it may further include other components without excluding other components unless otherwise stated. In addition, terms such as "...unit", "...unit", "module", and "device" described in the specification mean a unit that processes at least one function or operation, which is hardware or software, or a combination of hardware and software. can be implemented as

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram schematically showing the configuration of an artificial intelligence emergency medical decision-making and emergency patient transport system based on big data and cloud systems according to an embodiment of the present invention, and FIG. 3 is a diagram showing the operating state of the system.

1 and 3, the big data and cloud system-based artificial intelligence emergency medical decision-making and emergency patient transport system 100 according to the present invention includes a user terminal 110, an emergency medical service providing server 120, a cloud It is configured to include a platform server 130 and a hospital server 140 .

When an emergency patient occurs, the user terminal 110 is located at the site where the emergency patient is located (for example, the patient's home or workplace, or the place where he or she is traveling when he or she is out of town) or the site of an emergency medical service provider in an emergency patient transportation vehicle. Connects to and records and transmits the emergency patient's condition. Here, the user terminal 110 may include a smart phone 110a, a notebook PC 110b, a tablet PC, a desktop PC, a personal digital assistant (PDA), an emergency kiosk, and the like. Here, the user terminal 110 may also be a terminal of the patient himself, the patient's guardian, emergency paramedics, or other emergency patient reporters. Here, in addition, the emergency patient transportation vehicle (eg, 119 ambulance vehicle) includes a fingerprint reader for identifying the emergency patient and extracting information about the emergency patient, a face recognition device, and biometric information (eg, iris, vein, voice) , comparable) extraction devices and the like may be provided. This is to quickly obtain information about the emergency patient when the emergency patient is unconscious or difficult to communicate even if he or she is conscious. Here, of course, as described above, when a fingerprint reader, a face recognition device, and a biometric information extraction device are installed and used, the patient's fingerprint, face (face) photo (scan) data, and biometric information are stored in hospitals, emergency medical centers, etc. It is assumed that the state stored in the database (DB) of

The emergency medical service providing server 120 is built in the emergency medical service provider, receives emergency patient condition information from the user terminal 110, and transfers the patient condition information to the cloud platform server 130. Such an emergency medical service providing server 120 serves as a medical assistance tool that helps medical staff quickly diagnose and treat by identifying and providing emergency patient condition and severity information based on artificial intelligence (AI). In addition, the emergency medical service providing server 120 is linked to various external medical doctors, hospitals, national emergency medical networks, etc. through wired/wireless networks to collect various medical data and information and store them in its own database (DB). .

The cloud platform server 130 has personal health record data or information stored in its own database (DB), receives the patient's condition information from the emergency medical service providing server 120, and uses artificial intelligence trained with big data. Based on the patient's condition information, an estimated diagnosis, necessary examination and treatment are derived, and the patient's condition information is transmitted to a hospital server capable of treating the emergency patient. Such a cloud platform server 130 may be composed of a single server or may be composed of a plurality of servers 130a and 130b.

The hospital server 140 receives the estimated diagnosis derived from the cloud platform server 130, necessary examination and treatment information, and the patient's condition information, and determines the order of treatment (treatment) according to the severity of the emergency patient based on it. Handle related tasks so that a quick response can be made.

Here, the cloud platform server 130 includes an application that fuses medical information obtained from external doctors, medical institutions, and national emergency medical networks linked to the network with personal health record data or information stored in the database (DB). ) can be mounted.

In addition, the cloud platform server 130 may be equipped with an application for real-time identification of hospital beds and human resources capable of testing and treating the emergency patient.

At this time, the cloud platform server 130 may also be equipped with an application that transmits the patient's condition information to a hospital server capable of treating the emergency patient based on the identification result.

In addition, the artificial intelligence employed in the cloud platform server 130 will be trained to explore medical data in which Korean, English, and medical terms are mixed with exploratory data analysis (EDA) techniques and perform statistical analysis. can

At this time, as shown in FIG. 9, the artificial intelligence is based on a Federated Learning method in which a plurality of local clients and one central server cooperate to modify and learn a global model in a decentralized data situation. can do.

In addition, the artificial intelligence employed in the cloud platform server 130 may have a function of answering when a patient inquires about an emergency.

At this time, when the patient is connected by phone to inquire about an emergency situation, the artificial intelligence can answer the inquiry using a Korean voice recognition system using CTC (Connectionist Temporal Classification) and LAS (Listen and Spell) algorithms. .

At this time, when the patient uses the Internet homepage to inquire about an emergency, the artificial intelligence understands the inquiry using natural language understanding (NLU) and natural language generation (NLG). You can respond to inquiries by creating response contents through.

At this time, when the patient uses an application to inquire about an emergency situation, the artificial intelligence provides an accurate answer, as shown in FIG. Through a body-map screen that can be displayed or a STT (Speech-to-Text) function tool (tool 401) that can express their symptoms in words in the case of patients with poor eyesight, the patient's After collecting opinions or judgments, based on them, we can provide information to help patients make decisions in response to inquiries. Here, the app may preferably further include a multilingual conversion (language selection) function, as shown in (b) of FIG. 6 . As a result, foreigners who are not familiar with English, such as Chinese, Thai, and Vietnamese, can accurately express their symptoms through the app. In FIG. 4, (a) shows that the patient touches his or her painful part on the body-map, (b) shows that the corresponding part is displayed on the body-map as a result of the touch, and (c) shows the body-map It shows a side view.

Here, as shown in FIG. 5, the artificial intelligence (eg, artificial intelligence prediction model) classifies the information input through the app into severity levels 1 to 5, and transfers the information to a hospital that can be treated according to each level. make it possible Figure 6 (a) shows the details of the severity classification system from levels 1 to 5. As can be seen through the severity classification system in (a) of FIG. 6, the first stage of emergency (resuscitation) corresponds to patients who need immediate medical attention because their lives are in danger, and the second stage of emergency (urgent) can be life-threatening. Emergency level 3 (emergency) corresponds to patients whose life is not currently in danger, but more serious conditions may occur and require medical attention within 30 minutes. In addition, emergency level 4 (semi-emergency) is for patients who are not in critical condition and are unlikely to deteriorate even if treated within 60 minutes. for patients who need to

Then, in the following, an artificial intelligence emergency medical decision-making and emergency patient transportation method based on big data and cloud system-based artificial intelligence emergency medical decision-making and emergency patient transportation system according to the present invention having the above configuration will be explained. do it with

2 is a flowchart illustrating an execution process of an artificial intelligence emergency medical decision-making and emergency patient transfer method based on big data and a cloud system according to an embodiment of the present invention.

Referring to FIG. 2, the big data and cloud system-based artificial intelligence emergency medical decision-making and emergency patient transfer method according to the present invention includes the user terminal 110, the emergency medical service providing server 120, and the cloud platform as described above. Artificial intelligence emergency medical decision-making based on big data and cloud system including server 130 and hospital server 140 and artificial intelligence emergency medical decision-making based on big data and cloud system based on emergency patient transfer system 100 and As an emergency patient transportation method, first, when an emergency patient occurs, the user terminal 110 connects to the site of an emergency medical service provider from the site where the emergency patient is located or an emergency patient transport vehicle, records and transmits the state of the emergency patient (step S201). Here, preferably, the emergency patient transportation vehicle (eg, 119 ambulance vehicle) includes a fingerprint reader for identifying the emergency patient and extracting information about the emergency patient, a face recognition device, and biometric information (eg, iris) , vein, voice, handwriting) extraction device, etc. can be installed. As described above, this is to quickly obtain information about the emergency patient when the emergency patient is unconscious or difficult to communicate even if he or she is conscious.

As described above, when the user terminal 110 records and transmits the condition of the emergency patient, the emergency medical service providing server 120 of the emergency medical service provider receives the condition information of the emergency patient from the user terminal 110 The patient's condition information is transmitted to the cloud platform server 130 (step S202).

Then, the cloud platform server 130 receives the patient's condition information from the emergency medical service providing server 120, and estimates diagnosis, necessary examination and treatment based on the patient's condition information by artificial intelligence trained with big data. is derived (step S203). At this time, the cloud platform server 130 may determine and classify the degree of severity of the emergency patient, and transmit the result to the hospital server 140 .

At this time, the cloud platform server 130 also transmits the patient's condition information to the server 140 of the hospital capable of treating the emergency patient (step S204).

Then, the hospital server 140 receives the estimated diagnosis derived from the cloud platform server 130, necessary examination and treatment information, and the patient's condition information, and based on it, the emergency patient is treated (treated) according to the degree of severity. On the other hand, related tasks are processed so that a quick response can be made (step S205).

Here, in the above series of processes, in the step S203, the cloud platform server 130 stores medical information obtained from external doctors, medical institutions, national emergency medical networks, etc. linked to the network in its own database (DB). An application that fuses with personal health record data or information stored in may be loaded.

In addition, the cloud platform server 130 may be equipped with an application for real-time identification of hospital beds and human resources capable of testing and treating the emergency patient.

At this time, the cloud platform server 130 may also be equipped with an application that transmits the patient's condition information to a hospital server capable of treating the emergency patient based on the identification result.

In addition, the artificial intelligence employed in the cloud platform server 130 will be trained to explore medical data in which Korean, English, and medical terms are mixed with exploratory data analysis (EDA) techniques and perform statistical analysis. can

At this time, as shown in FIG. 9, the artificial intelligence is based on a Federated Learning method in which a plurality of local clients and one central server cooperate to modify and learn a global model in a decentralized data situation. can do.

In addition, the artificial intelligence employed in the cloud platform server 130 may have a function of answering when a patient inquires about an emergency.

At this time, when the patient is connected by phone to inquire about an emergency situation, the artificial intelligence can answer the inquiry using a Korean voice recognition system using CTC (Connectionist Temporal Classification) and LAS (Listen and Spell) algorithms. .

At this time, when the patient uses the Internet homepage to inquire about an emergency, the artificial intelligence understands the inquiry using natural language understanding (NLU) and natural language generation (NLG). You can respond to inquiries by creating response contents through.

At this time, when the patient uses an application to inquire about an emergency situation, the artificial intelligence, as shown in FIG. Through a body-map screen that can be displayed by touch or a speech-to-text (STT) function tool 401 that allows patients with poor eyesight to express their symptoms verbally. After collecting the patient's opinions or judgments, based on them, information to help the patient's decision-making can be provided in response to inquiries. Here, the app may preferably further include a multilingual conversion (language selection) function, as shown in (b) of FIG. 6 .

Here, as shown in FIG. 5, the artificial intelligence (eg, artificial intelligence prediction model) classifies the information input through the app into severity levels 1 to 5, and hospitals that can treat each level. so that it can be transported to

Here, the big data and cloud system-based artificial intelligence emergency medical decision-making and emergency patient transfer method according to the present invention as described above, not only uses artificial intelligence, but also collaborates with doctors to prevent possible errors in artificial intelligence ( In preparation for errors, measures are sought to minimize the resulting problems. In addition, upon arrival at the scene where an emergency patient occurred, not only the primary evaluation, but also the secondary evaluation during the transfer of the patient enables the patient to be transferred to the optimal medical institution. In this regard, it will be described in more detail with reference to FIG. 7 .

7 is a diagram showing an emergency treatment process employed in the present invention.

Referring to (a) of FIG. 7, this shows the overall process of the emergency medical treatment process. When emergency response personnel (eg, 119 paramedics) arrive at the scene where an emergency patient occurs, they first conduct a site survey and take action. With taking the patient, a primary evaluation is performed on the patient using the patient record form as shown in FIG. 8, and corresponding treatment is performed (steps S701 and S702). Here, the record form for the patient may include basic observation, patient occurrence location, patient symptom, patient occurrence type, circulatory adequacy confirmation, and severity determination as evaluation items. At this time, the severity determination is basically determined by artificial intelligence, but if necessary, the field crew (119 paramedics) may additionally input opinions to determine the final severity.

Thereafter, the severity of the patient is determined, and if immediate transfer is determined, a secondary evaluation treatment is performed, and corresponding treatment is performed while continuously monitoring the patient during the transfer (steps S703 to S706).

Figure 7 (b) shows in more detail the process after the severity determination in step S703 and the immediate transfer determination in S704 of Figure 7 (a), when the severity determination and immediate transfer determination are made (step S711). , It is determined whether the damage mechanism is systemic (step S712). Here, the damage mechanism means a condition that can cause damage to the head, neck, and spine. In this determination, if the damage mechanism is systemic, a quick physical examination is performed, vital signs are measured, and a medical history is investigated (steps S713 to S715). Here, the quick physical examination can be performed in the order of head → neck → chest → abdomen → pelvis → extremities → posterior region. Vital signs may include blood pressure (systolic and diastolic), pulse (beats per minute, quality and regularity of beats), and respiration (respiration per minute, quality of breathing). In addition, the medical history survey may include symptoms and signs complained of by the patient or bystanders, allergy, drug intake history, past disease, last meal, occurrence prior to the occurrence of an emergency, and onset history.

In this way, when the rapid physical examination, vital sign measurement, and medical history investigation are completed, a detailed physical examination is performed based on them (step S716).

In addition, in the determination of step S712, if the damage mechanism is not systemic (i.e., local), the main complaint of the patient or guardian is listened to (step S717), and after taking a medical history and measuring vital signs as described above ( Steps S718 and S719), and a detailed physical examination is performed (step S720).

Meanwhile, FIG. 10 is a diagram showing the configuration of a 5G communication artificial intelligence (AI)-based emergency medical system employed in the present invention.

Referring to FIG. 10, this shows the configuration of the 5G communication artificial intelligence (AI)-based emergency medical system employed in the present invention. As shown, information linkage infrastructure is established throughout the emergency medical system process, and accurate field data It collects and quickly shares information through cloud and 5G, and develops and provides emergency medical AI services for each stage of emergency patient transportation. In addition, through the development of a practical system, we will conduct a demonstration in the local community and ultimately establish a social consensus, including legal and institutional arrangements for service expansion.

11 is a diagram showing an outline of a smart emergency medical service (SEMS) system employed in the present invention.

As shown in FIG. 11, the smart emergency medical service (SEMS) system organically shares information through wired/wireless networks such as Hospital Information Systems, Authentication, ambulance vehicles, and control systems. and provide the best emergency medical services.

12 is a diagram showing a comparison between a conventional emergency patient treatment process and the services of an artificial intelligence emergency medical decision-making and emergency patient transfer system according to the present invention.

Referring to FIG. 12, in the conventional emergency patient treatment process, when an emergency patient occurs, the patient is transported to an emergency room, basic information is prepared (at this time, the main symptoms are simply asked), and reception is performed. Then, after the emergency room doctor first diagnoses the critically ill patient after provisional classification, the necessary X-rays and blood tests are performed, the doctor treats the patient, and treatment begins with the critically ill patient.

In the conventional emergency patient treatment process as described above, it takes about 12 hours from the time the emergency patient is transferred to the emergency room until the doctor proceeds to treat the critically ill patient.

In contrast, according to the artificial intelligence emergency medical decision-making and emergency patient transfer system service according to the present invention, the user terminal 110 accesses the emergency medical service providing server 120 (ie, the AI emergency patient self-diagnosis system) Record the patient's symptoms. At this time, record detailed symptoms (past history and underlying diseases, medications and allergies, etc.).

After that, the patient's condition is quickly identified by the AI algorithm. Accordingly, waiting time is reduced. In addition, presumptive diagnoses and critically ill patients are selected and provided with information. Accordingly, doctors can quickly select and treat seriously ill patients.

When the service of the artificial intelligence emergency medical decision-making and emergency patient transport system according to the present invention as described above is applied, it takes about 3 hours from transporting an emergency patient to an emergency room to selectively treating a seriously ill patient by a doctor. As such, the service of the AI emergency medical decision-making and emergency patient transfer system according to the present invention has the advantage of dramatically reducing the time required from patient transfer to the emergency room to critical care treatment by a doctor compared to the conventional emergency patient treatment process there is

As described above, the big data and cloud system-based artificial intelligence emergency medical decision-making and emergency patient transfer system and method according to the present invention help patients in medical decision-making, and provide emergency medicine and related medical departments 24 hours a day in real time. Doctors or medical artificial intelligence answers patients' inquiries, and has the advantage of quickly transporting emergency patients to hospitals so that they can receive medical treatment and treatment (treatment) in the fastest possible time.

In addition, the hospital side has the advantage of being able to efficiently manage the limited resources and manpower of the emergency room.

Although the present invention has been described in detail through preferred embodiments, the present invention is not limited thereto, and various changes and applications can be made without departing from the technical spirit of the present invention. self-explanatory for technicians Therefore, the true scope of protection of the present invention should be construed by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

100: (Invention) Artificial intelligence emergency medical decision-making and emergency patient transportation system based on big data and cloud system
110: user terminal 120: emergency medical service providing server
130: cloud platform server 140: hospital server
401: STT (Speech-to-Text) function tool

Claims (24)

When an emergency patient occurs, a user terminal that records and transmits the condition of the emergency patient by accessing the site of the emergency medical service provider from the site where the emergency patient is located or from the emergency patient transport vehicle;
An emergency medical service providing server built in an emergency medical service provider, receiving emergency patient condition information from the user terminal and transmitting the patient's condition information to a cloud platform server;
Personal health record data or information is stored in a database (DB), receives patient condition information from the emergency medical service providing server, and estimates diagnosis based on the patient condition information by artificial intelligence trained with big data, A cloud platform server that derives necessary tests and treatments and transmits the patient's condition information to a hospital server capable of treating the emergency patient; and
Estimated diagnosis derived from the cloud platform server, necessary examination and treatment information, and patient condition information are received, and based on this, the order of treatment (treatment) is determined according to the severity of emergency patients, and related tasks are performed so that prompt response can be made. Including a hospital server that processes,
The cloud platform server is equipped with an application that fuses medical information obtained from external doctors, medical institutions, and national emergency medical networks linked to the network with personal health record data or information stored in a database (DB), ,
The artificial intelligence employed in the cloud platform server is trained to explore and statistically analyze medical data in which Korean, English, and medical terms are mixed with exploratory data analysis (EDA) techniques,
The artificial intelligence is a big data and cloud system-based artificial intelligence emergency based on a federated learning method in which a plurality of local clients and a central server cooperate to modify and learn a global model in a decentralized data situation. Medical decision making and emergency patient transport systems.
delete According to claim 1,
The cloud platform server has an application for real-time identification of hospital beds and human resources capable of testing and treatment necessary for the emergency patient, and artificial intelligence emergency medical decision-making and emergency patient transportation based on cloud system. system.
According to claim 3,
Artificial intelligence emergency medical decision-making based on big data and cloud system equipped with an application that transmits the patient's condition information to the server of the hospital capable of treating the emergency patient based on the identification result on the cloud platform server. and emergency patient transportation systems. delete delete According to claim 1,
The artificial intelligence employed in the cloud platform server is a big data and cloud system-based artificial intelligence emergency medical decision-making and emergency patient transport system having a function to answer when a patient inquires about an emergency.
According to claim 7,
When the patient is connected by phone to inquire about an emergency situation, the artificial intelligence uses a Korean voice recognition system using CTC (Connectionist Temporal Classification) and LAS (Listen and Spell) algorithms to answer the inquiry using big data and AI emergency medical decision-making and emergency patient transportation system based on cloud system.
According to claim 7,
When the patient uses the Internet homepage to inquire about an emergency, the artificial intelligence understands the inquiry using Natural Language Understanding (NLU) and responds through Natural Language Generation (NLG). An artificial intelligence emergency medical decision-making and emergency patient transportation system based on big data and cloud systems that creates contents and answers inquiries.
According to claim 7,
When the patient uses an application to inquire about an emergency situation, the artificial intelligence provides a body-map (body-map) in which the patient can display his or her painful area in a touch-type manner provided by the app for an accurate answer. After collecting the patient's opinions or judgments through the STT (Speech-to-Text) function tool, which allows patients with -map) screens or patients with poor eyesight to express their symptoms verbally, An artificial intelligence emergency medical decision-making and emergency patient transportation system based on big data and cloud systems that provides information helpful for decision-making as an answer to inquiries.
According to claim 10,
The app is a big data and cloud system-based artificial intelligence emergency medical decision-making and emergency patient transport system further equipped with a multilingual conversion (language selection) function.
According to claim 1,
Artificial intelligence emergency medical care based on big data and cloud systems equipped with at least one of a fingerprint reader, a face recognition device, and a biometric information extraction device for identifying the emergency patient and extracting information about the emergency patient in the emergency patient transportation vehicle. Decision-making and emergency patient transport systems.
a) the user terminal accessing the site of an emergency medical service provider at the site where the emergency patient is located or the emergency patient transport vehicle when an emergency patient occurs, and recording and transmitting the state of the emergency patient;
b) an emergency medical service providing server of an emergency medical service provider receiving emergency patient condition information from the user terminal and transmitting the patient's condition information to a cloud platform server;
c) receiving, by a cloud platform server, the patient's condition information from the emergency medical service providing server, and deriving an estimated diagnosis, necessary examination and treatment based on the patient's condition information by artificial intelligence trained with big data;
d) transmitting, by a cloud platform server, state information of the patient to a server of a hospital capable of treating the emergency patient; and
e) The hospital server receives the estimated diagnosis derived from the cloud platform server, necessary examination and treatment information, and the patient's condition information, and based on it, determines the order of treatment (treatment) according to the severity of the emergency patient, while prompt response is achieved. Including steps to process related tasks so that
In step c), the cloud platform server has an app that fuses medical information obtained from external doctors, medical institutions, and national emergency medical networks linked to the network with personal health record data or information stored in its own database (DB). (application) is installed,
The artificial intelligence employed in the cloud platform server is trained to explore and statistically analyze medical data in which Korean, English, and medical terms are mixed with exploratory data analysis (EDA) techniques,
The artificial intelligence is a big data and cloud system-based artificial intelligence emergency based on a federated learning method in which a plurality of local clients and a central server cooperate to modify and learn a global model in a decentralized data situation. How to make medical decisions and transport emergency patients.
delete According to claim 13,
The cloud platform server has an application for real-time identification of hospital beds and human resources capable of testing and treatment necessary for the emergency patient, and artificial intelligence emergency medical decision-making and emergency patient transportation based on cloud system. method.
According to claim 15,
Artificial intelligence emergency medical decision-making based on big data and cloud system equipped with an application that transmits the patient's condition information to the server of the hospital capable of treating the emergency patient based on the identification result on the cloud platform server. and how to transport emergency patients.
delete delete According to claim 13,
The artificial intelligence employed in the cloud platform server is an artificial intelligence emergency medical decision-making and emergency patient transfer method based on big data and cloud systems having a function to answer when a patient inquires about an emergency.
According to claim 19,
When the patient is connected by phone to inquire about an emergency situation, the artificial intelligence uses a Korean voice recognition system using CTC (Connectionist Temporal Classification) and LAS (Listen and Spell) algorithms to answer the inquiry using big data and AI emergency medical decision-making and emergency patient transfer method based on cloud system.
According to claim 19,
When the patient uses the Internet homepage to inquire about an emergency, the artificial intelligence understands the inquiry using Natural Language Understanding (NLU) and responds through Natural Language Generation (NLG). Artificial intelligence emergency medical decision-making and emergency patient transportation method based on big data and cloud system that creates contents and answers inquiries.
According to claim 19,
When the patient uses an application to inquire about an emergency situation, the artificial intelligence provides a body-map (body-map) in which the patient can display his or her painful area in a touch-type manner provided by the app for an accurate answer. After collecting the patient's opinions or judgments through the STT (Speech-to-Text) function tool, which allows patients with -map) screens or patients with poor eyesight to express their symptoms verbally, Big data and cloud system-based artificial intelligence emergency medical decision-making and emergency patient transport methods that provide information helpful for decision-making as answers to inquiries.
The method of claim 22,
The app is an artificial intelligence emergency medical decision-making and emergency patient transport method based on big data and cloud systems further having a multilingual conversion (language selection) function.
According to claim 13,
In step a), the emergency patient transfer vehicle is equipped with at least one of a fingerprint reader, a face recognition device, and a biometric information extraction device for identifying the emergency patient and extracting information about the emergency patient. Big data and cloud system AI-based emergency medical decision-making and emergency patient transfer method.

Images