KR102655620B1 - Remote Patient Management Systems and Methods - Google Patents

Abstract

According to the embodiment, the patient's prior management reservation information registered online is input into the first learning model unit to output the first questionnaire result, and whether the patient receives general treatment or remote treatment is determined according to the first questionnaire result. a cooperative medical institution server that transmits reservation confirmation information to the terminal of the user who has registered the patient information; And the patient's post-care reservation information registered online is entered into the second learning model unit to output the second questionnaire result, and the patient's abnormal signs are remotely monitored according to the second questionnaire result and the patient's previous medical history. Provided is a remote patient management system that includes a higher-level medical institution server that determines whether the patient should visit a medical institution.

Description

Remote Patient Management Systems and Methods}

One embodiment of the present invention relates to a remote patient management system and method.

Due to the periodic outbreak of infectious diseases imported from overseas, a social consensus is being formed on the need for non-face-to-face medical treatment, and the introduction of a full-scale business model for telemedicine is accelerating, with countries restrictively allowing telemedicine outside medically vulnerable areas.

The telemedicine system, which had been introduced on a limited basis in existing islands and mountainous areas, military bases, and correctional facilities, had significant spatial limitations in construction, and quality problems also existed.

However, with the development of communication technology and mobile devices, it has become possible to transmit and receive various high-definition/high-quality medical images without installing additional bulky equipment. In addition, the number of cases of using mobile devices as a means of managing chronic diseases is increasing, and there is a need for a platform that integrates and manages non-face-to-face consulting between patients and medical practitioners and medical practitioners and medical practitioners by linking them with telemedicine systems.

The technical problem to be achieved by the present invention is to provide a remote patient management system and method that enables online collaboration between medical facilities lacking medical equipment and higher-level medical institutions.

In addition, it provides a remote patient management system and method that can identify symptoms before visiting a medical institution, schedule a visit to a medical institution, and manage abnormal symptoms through an application after the visit.

In addition, the goal is to provide a remote patient management system and method that can perform accurate and rapid non-face-to-face treatment between medical staff and patients through high-resolution image transmission and medical measurement information transmission online.

According to the embodiment, the patient's prior management reservation information registered online is input into the first learning model unit to output the first questionnaire result, and whether the patient receives general treatment or remote treatment is determined according to the first questionnaire result. a cooperative medical institution server that transmits reservation confirmation information to the terminal of the user who has registered the patient information; And the patient's post-care reservation information registered online is entered into the second learning model unit to output the second questionnaire result, and the patient's abnormal signs are remotely monitored according to the second questionnaire result and the patient's previous medical history. Provided is a remote patient management system that includes a higher-level medical institution server that determines whether the patient should visit a medical institution.

The cooperative medical institution server and the higher-level medical institution server may perform remote collaborative consultation through remote imaging equipment and medical measurement equipment.

The advanced medical institution server transmits a medical information request message to the cooperative medical institution server, and analyzes the patient's medical information received in response to the medical information request message to remotely monitor abnormal signs of the patient. .

The cooperative medical institution server may transmit the measurement results of the medical measurement equipment to the higher-level medical institution server using the remote imaging equipment.

According to an embodiment, a collaborative medical institution server inputs advance management reservation information of a patient registered online into a first learning model unit and outputs a first questionnaire result; The cooperative medical institution server determining whether to provide general medical treatment or medical treatment for the patient according to the results of the first questionnaire and then transmitting reservation confirmation information to the terminal of the user who has registered the patient information; A higher-level medical institution server inputs the patient's post-care reservation information registered online into a second learning model unit and outputs a second questionnaire result; And providing a remote patient management method comprising the step of the higher-level medical institution server remotely monitoring abnormal signs of the patient according to the results of the second questionnaire and the patient's previous medical history and then determining whether the patient should visit the medical institution. .

The remote patient management system and method according to the embodiment can perform online collaboration between a medical facility lacking medical equipment and a higher-level medical institution.

In addition, you can identify symptoms before visiting a medical institution, schedule a visit to a medical institution, and manage abnormal symptoms through the application after the visit.

In addition, accurate and rapid non-face-to-face treatment can be performed between medical staff and patients by transmitting high-resolution images and medical measurement information online.

Figure 1 is a conceptual diagram of a remote patient management system according to an embodiment.
Figure 2 is a block diagram of a cooperative medical institution server according to an embodiment.
Figure 3 is a block diagram of a higher-level medical institution server according to an embodiment.
Figure 4 is a diagram for explaining the operation of a remote patient management system according to an embodiment.
Figure 5 is a flowchart of a remote patient management method according to an embodiment.

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

However, the technical idea of the present invention is not limited to some of the described embodiments, but may be implemented in various different forms, and as long as it is within the scope of the technical idea of the present invention, one or more of the components may be optionally used between the embodiments. It can be used by combining and replacing.

In addition, terms (including technical and scientific terms) used in the embodiments of the present invention, unless explicitly specifically defined and described, are generally understood by those skilled in the art to which the present invention pertains. It can be interpreted as meaning, and the meaning of commonly used terms, such as terms defined in a dictionary, can be interpreted by considering the contextual meaning of the related technology.

Additionally, the terms used in the embodiments of the present invention are for describing the embodiments and are not intended to limit the present invention.

In this specification, the singular may also include the plural unless specifically stated in the phrase, and when described as "at least one (or more than one) of A and B and C", it is combined with A, B, and C. It can contain one or more of all possible combinations.

Additionally, when describing the components of an embodiment of the present invention, terms such as first, second, A, B, (a), and (b) may be used.

These terms are only used to distinguish the component from other components, and are not limited to the essence, sequence, or order of the component.

And, when a component is described as being 'connected', 'coupled' or 'connected' to another component, the component is not only directly connected, coupled or connected to that other component, but also is connected to that component. It can also include cases where other components are 'connected', 'combined', or 'connected' due to another component between them.

Additionally, when described as being formed or disposed "above" or "below" each component, "above" or "below" refers not only to cases where two components are in direct contact with each other, but also to one This also includes cases where another component described above is formed or placed between two components. In addition, when expressed as "top (above) or bottom (bottom)", it may include not only the upward direction but also the downward direction based on one component.

Hereinafter, embodiments will be described in detail with reference to the attached drawings, but identical or corresponding components will be assigned the same reference numbers regardless of reference numerals, and duplicate descriptions thereof will be omitted.

Figure 1 is a conceptual diagram of a remote patient management system according to an embodiment, Figure 2 is a block diagram of a cooperative medical institution server according to an embodiment, and Figure 3 is a block diagram of a superior medical institution server according to an embodiment.

1 to 3, the remote patient management system 1 according to the embodiment may include a cooperative medical institution server 10 and a superior medical institution server 20 located remotely from the cooperative medical institution server 10. You can.

The cooperative medical institution server 10 is a server deployed at a specialized medical institution in a remote area such as a rural, mountainous, or island area with low accessibility to specialized medical services, and a higher-level medical institution is a server placed at a specialized medical institution in an urban area or a medical benefit area. You can.

The cooperative medical institution server 10 includes a first input unit 11, a first learning model unit 12, a first communication unit 13, a first remote imaging equipment 14, a first medical measurement equipment 15, and a first communication unit 13. It may include a docking station 16 and a first database 17.

The cooperative medical institution server 10 inputs the patient's prior management reservation information registered online into the first learning model and outputs the first questionnaire result, and determines whether the patient is receiving regular treatment or remote treatment according to the first questionnaire result. After making the decision, reservation confirmation information can be transmitted to the terminal of the user who has registered patient information.

Additionally, the cooperative medical institution server 10 may perform remote collaborative consultation with the higher-level medical institution server 20 through the first remote imaging equipment 14 and the first medical measurement equipment 15.

Additionally, the cooperative medical institution server 10 may transmit the measurement results of the first medical measurement equipment 15 to the higher-level medical institution server 20 using the first remote imaging equipment 14.

In addition, the cooperative medical institution server 10 determines whether remote collaboration is possible through the visiting patient's primary treatment and transmits a request for remote collaboration to the higher medical institution server 20. After receiving the remote collaboration approval message, the higher medical institution server ( At the request of 20), the patient's medical information can be transmitted through the first remote imaging equipment 14 and the first medical measurement equipment 15.

The cooperative medical institution server 10 may be provided with a first database 17 that stores electronic medical record information including medical data, and may record medical result information received through the first communication unit 13 as an electronic medical record. Information can be integrated and managed.

In addition, the cooperative medical institution server 10 further includes the unique number for each medical device, the date of production or registration date for each unique number of the medical device, the number of examinations, etc., in the first database 17, so that the hospital manager can determine the medical device asset. and may be configured to facilitate maintenance.

The first database 17 can accumulate and store patient attribute information and medical measurement data and calculate statistical values. Medical measurement data is divided by connection port and medical device and stored cumulatively for a certain period of time, and statistical values can refer to the average value or total of power parameters over a certain period of time.

The cooperative medical institution server 10 may perform primary treatment through the first learning model unit 12, which performs learning using advance management reservation information including patient attribute information. The cooperative medical institution server 10 can use these primary medical treatment results to automatically select the patient's department and appointment schedule and transmit them to the patient's terminal. Additionally, the cooperative medical institution server 10 may output the first questionnaire result. The collaborative medical institution server 10 determines whether the patient needs general treatment or treatment at a higher medical institution based on the results of the first questionnaire, and, if necessary, can transmit a remote collaborative medical treatment request to the higher medical institution server 20.

The first input unit 11 can receive patient attribute information. Patient attribute information may include personal attributes, clinical attributes, examination attributes, and disease attributes. Personal attributes are about the patient's personal information and may include, for example, information about gender, age, height, weight, department, country, smoking, drinking, coffee, exercise, sleep time, etc. necessary for clinical decision-making. there is. Clinical attributes are information about tests performed for the diagnosis or treatment of patients and may include hematological information, serological information, biochemical information, physiological information, bacterial virological information, urine fecal information, imaging information, etc. . Test properties may include numerical information about various tests received by the patient. Disease attributes may include information about the disease possessed by the patient.

The first learning model unit 12 learns the correlation between patient attribute information and medical treatment cases, determines similar medical treatment cases from the input patient attribute information, and outputs them as the first questionnaire result.

The deep learning model can extract similar patient cases that can be induced from the input patient attribute information, and through this, the medical treatment result corresponding to the patient attribute information can be output as the first questionnaire result.

In other words, when the patient's attribute information is input, the deep learning model compares the weighted attribute information for each attribute with the previously learned patient case information and extracts similar cases. At this time, the previously learned information may include patient information from other medical institutions that have entered into agreements in addition to patient information from a specific medical institution, and the patient information may also be included in an integrated server operated jointly by multiple medical institutions.

Figure 4 is a diagram for explaining the operation of a remote patient management system according to an embodiment.

Referring to Figure 4 together, in the embodiment, the first learning model unit 12 is a technology that can pre-screen diseases similar to the patient's symptoms before treatment, and symptoms related to the advance management reservation information entered by the patient in stages. The first learning model unit 12 queries and predicts, helping to search for and register for relevant hospitals. Artificial intelligence-based questionnaire technology is an A.I. that has learned medical big data such as data from the Health Insurance Review and Assessment Service, medical papers, portals, and articles. Before visiting the hospital, the symptom check engine searches personal medical records for similar diseases and recommends departments based on the user's symptoms, and connects with the hospital's medical information system to deliver patient information, preliminary questionnaire information, and symptom information. It may be a bullet-based medical support solution.

In the first learning model unit (12), when a patient inputs information, artificial intelligence that has learned about 500,000 pieces of medical knowledge data, including medical practical exams, and about 13 million pieces of insurance claim data from the past three years, derives related symptoms. It is recommended to users, and similar disease information can be provided by inferring meaning through a series of processes.

In addition, the first learning model unit 12 can derive a result by applying unsupervised learning (K-means++), which predicts possible diseases based on the patient's symptoms and the results of additional questionnaires.

This artificial intelligence technology can be implemented by closely replicating the decision-making model that treats patients based on medical examination, and can be designed to provide information on the department that deals with the disease and guide patients to the appropriate department.

The first learning model unit 12 may be configured to include dictionary questionnaire content to enhance the AI questionnaire algorithm, and may include a dictionary questionnaire algorithm strengthened through learning of the symptom check engine.

For example, through learning, the first learning model unit 12 outputs the results of a urology preliminary questionnaire when the patient's attribute information is input, and provides a first questionnaire that includes physical symptoms, urinary related information, and information suspected of benign prostatic hyperplasia as detailed information. The results can be printed.

Alternatively, the first learning model unit 12 outputs the results of a pulmonology preliminary questionnaire through learning when the patient's attribute information is input, and provides a first questionnaire including physical symptoms, respiratory related, and suspected COVID-19 information as detailed information. The results can be printed.

Alternatively, the first learning model unit 12 outputs the results of the geriatric depression scale preliminary questionnaire through learning when the patient's attribute information is input, and provides a first learning model including psychological symptoms, depression-related information, and Korean version of geriatric depression suspicion information as detailed information. The results of the questionnaire can be printed.

Alternatively, the first learning model unit 12 outputs the results of the alcohol addiction preliminary questionnaire through learning when the patient's attribute information is input, and outputs the results of the first questionnaire including psychological symptoms and Korean-style alcoholism suspicion information as detailed information. can do.

Alternatively, the first learning model unit 12 outputs the fatigue symptom scale preliminary questionnaire results when inputting the patient's attribute information through learning, and outputs the first questionnaire results including physical symptoms and fatigue symptom information as detailed information. You can.

Alternatively, the first learning model unit 12 outputs the dementia scale preliminary questionnaire results through learning when the patient's attribute information is input, and provides the first questionnaire results including psychological symptoms, depression, and elderly depression suspicion information as detailed information. Can be printed.

In addition, the first learning model unit 12 can provide hospital recommendation and reservation functions based on AI dictionary questionnaire technology and the results of the first questionnaire. The first learning model unit 12 may be configured to include a voice recognition-based pre-interrogation technology and a self-diagnosis pre-interrogation technology, and if a doctor's consultation for symptoms is necessary, medical services can be provided through a chat service. there is.

Additionally, the first learning model unit 12 may be designed to be interoperable with non-face-to-face image monitoring technology through the first remote imaging equipment 14 through collection of preliminary questionnaire data.

The first learning model unit 12 can use general hospital information, general pharmacy information, hospital cost information, doctor information, and medical encyclopedia (disease/drug/test) information as learning data. In addition, it is possible to learn together with preliminary questionnaire data composed by professional medical staff and medical institution workers.

The cooperative medical institution server 10 may transmit the measurement results of the first medical measurement equipment 15 to the higher-level medical institution server 20 using the first remote imaging equipment 14.

The cooperative medical institution server 10 according to the embodiment may operate in conjunction with the first remote imaging equipment 14 and the first medical measurement equipment 15. The first remote imaging device 14 may be configured to be portable, and when mounted on a first docking station placed within a cooperative medical institution, the cooperative medical institution server 10 and the first medical measurement equipment 15 can be operated through a plug-and-play operation. ) can be linked to.

The first docking station may be equipped with a first remote imaging device 14, a plurality of first medical measurement devices 15, and a plurality of ports corresponding to a hospital server. The plurality of ports include a parallel interface unit, a serial interface unit, a USB interface unit, a Dicom interface unit, an external memory interface unit, an analog video interface unit, and a wireless communication module unit, and each interface unit is configured to have at least one port. It can be.

The first remote imaging device 14 can photograph a patient, medical staff, or the first medical measurement device 15, generate image information including video and audio, and transmit it to the first communication unit 13 in real time.

The first remote imaging equipment 14 may include a display capable of displaying image data received from the advanced medical institution server 20 and various data. The display receives image data from the advanced medical institution server 20 and displays it in real time, allowing practitioners to conduct real-time consultation with remote medical experts.

The first medical measurement equipment 15 includes medical devices that measure the operating status of various organs of the patient, such as imaging medical devices, electrocardiogram measurement devices, and blood pressure measurement devices that image the patient's body and organs, and the patient's It may include clinical devices that measure and analyze levels of various elements in samples collected from the body or from nature.

Additionally, the first medical measurement equipment 15 may further include one of a blood test device, a medical scope, a stress meter, a psychotherapy device, a blood pressure meter, a body fat meter, a blood sugar meter, and a thermometer. Medical measurement equipment can also refer to electronic devices that can measure various biosignals of a user, and can refer to wearable devices that are worn directly on the user's body, such as those built into clothing or on a belt.

The first medical measurement equipment 15 can measure the user's biosignals using various devices and transmit the medical measurement data generated accordingly to the first communication unit 13.

The first communication unit 13 can perform wireless communication with the higher-level medical institution server 20. The first communication unit 13 is, for example, long-term evolution (LTE), LTE Advance (LTE-A), code division multiple access (CDMA), wideband CDMA (WCDMA), universal mobile telecommunications system (UMTS), and WiBro. It may be configured to include at least one communication module, such as (Wireless Broadband) or GSM (global system for mobile communications).

Additionally, the first communication unit 13 can receive a medical opinion and prescription from the higher-level medical institution server 20. Medical staff opinions and prescriptions may contain a variety of formal or informal information about medical measurement data, such as the medical expert's personal opinion or prescription opinion.

The advanced medical institution server 20 includes a second input unit 21, a second learning model unit 22, a second communication unit 23, a second remote imaging equipment 24, a second medical measurement equipment 25, and a second input unit 21. It may include a second docking station 26 and a second database 27.

The advanced medical institution server 20 inputs the patient's post-care reservation information registered online into the second learning model unit 22 and outputs the second questionnaire result, according to the second questionnaire result and the previous patient's medical history. After remotely monitoring the patient's abnormalities, it is possible to decide whether the patient should visit a medical institution.

In addition, the advanced medical institution server 20 transmits a medical information request message to the cooperative medical institution server 10, and analyzes the patient's medical information received in response to the medical information request message to remotely monitor abnormal signs of the patient. can do.

The higher-level medical institution server 20 can output the results of the second questionnaire through follow-up treatment of the visiting patient and continuously monitor abnormal signs of the patient.

The higher-level medical institution server 20 may be provided with a second database 27 that stores electronic medical record information including medical data, and may record medical result information received through the second communication unit 23 as an electronic medical record. Information can be integrated and managed.

In addition, the higher-level medical institution server 20 further includes the unique number for each medical device, the date of production or registration date for each unique number of the medical device, the number of examinations, etc., in the second database 27, so that the hospital manager can determine the medical device assets. and may be configured to facilitate maintenance.

The second database 27 can accumulate and store patient attribute information and medical measurement data and calculate statistical values. Medical measurement data is divided by connection port and medical device and stored cumulatively for a certain period of time, and statistical values can refer to the average value or total of power parameters over a certain period of time.

The advanced medical institution server 20 may perform secondary medical treatment through the second learning model unit 22, which performs learning using follow-up management reservation information including patient attribute information. The higher-level medical institution server 20 can use these secondary medical treatment results to automatically select the patient's department and appointment schedule and transmit them to the patient's terminal. Additionally, the advanced medical institution server 20 may output the second questionnaire result. The higher-level medical institution server 20 may determine whether the patient needs treatment at a higher-level medical institution based on the results of the second questionnaire, and, if necessary, transmit a request for remote collaborative treatment to the cooperative medical institution server 10.

The second input unit 21 can receive patient attribute information. Patient attribute information may include personal attributes, clinical attributes, examination attributes, and disease attributes. Personal attributes are about the patient's personal information and may include, for example, information about gender, age, height, weight, department, country, smoking, drinking, coffee, exercise, sleep time, etc. necessary for clinical decision-making. there is. Clinical attributes are information about tests performed for the diagnosis or treatment of patients and may include hematological information, serological information, biochemical information, physiological information, bacterial virological information, urine fecal information, imaging information, etc. . Test properties may include numerical information about various tests received by the patient. Disease attributes may include information about the disease possessed by the patient.

The second learning model unit 22 learns the correlation between patient attribute information and medical treatment cases, determines similar medical treatment cases from the input patient attribute information, and outputs them as a second questionnaire result.

The deep learning model can extract similar patient cases that can be induced from the input patient attribute information, and through this, the treatment results corresponding to the patient attribute information can be output as the second questionnaire result.

In other words, when the patient's attribute information is input, the deep learning model compares the weighted attribute information for each attribute with the previously learned patient case information and extracts similar cases. At this time, the previously learned information may include patient information from other medical institutions that have entered into agreements in addition to patient information from a specific medical institution, and the patient information may also be included in an integrated server operated jointly by multiple medical institutions.

In the embodiment, the second learning model unit 22 is a technology that can pre-screen diseases similar to abnormal signs of the patient after treatment, and the symptoms related to the follow-up care reservation information entered by the patient in stages are used in the second learning model unit. By querying and predicting (22), it helps predict abnormal signs and diseases, and searches for and registers for relevant hospitals. Artificial intelligence-based questionnaire technology is an A.I. that has learned medical big data such as data from the Health Insurance Review and Assessment Service, medical papers, portals, and articles. Before visiting the hospital, the symptom check engine searches personal medical records for similar diseases and recommends departments based on the user's symptoms, and connects with the hospital's medical information system to deliver patient information, preliminary questionnaire information, and symptom information. It may be a bullet-based medical support solution.

In the second learning model unit (22), when a patient inputs information, artificial intelligence that has learned about 500,000 pieces of medical knowledge data, including medical practical exams, and about 13 million pieces of insurance claim data from the past three years, derives related symptoms. It is recommended to users, and similar disease information can be provided by inferring meaning through a series of processes.

In addition, the second learning model unit 22 can derive results by applying unsupervised learning (K-means++), which predicts possible diseases based on the patient's symptoms and the results of additional questionnaires.

This artificial intelligence technology can be implemented by closely replicating the decision-making model that treats patients based on medical examination, and can be designed to provide information on the department that deals with the disease and guide patients to the appropriate department.

The second learning model unit 22 may be configured to include pre-questionnaire content to enhance the AI questionnaire algorithm, and may include a post-questionnaire algorithm strengthened through learning of the symptom check engine.

For example, the second learning model unit 22 outputs the results of a urology preliminary questionnaire through learning when the patient's attribute information is input, and provides a second questionnaire including physical symptoms, urinary related information, and information suspected of benign prostatic hyperplasia as detailed information. The results can be printed.

Alternatively, the second learning model unit 22, through learning, outputs the results of a pulmonology post-questionnaire when the patient's attribute information is entered, and provides a second questionnaire that includes physical symptoms, respiratory-related, and suspected COVID-19 information as detailed information. The results can be printed.

Alternatively, the second learning model unit 22 outputs the results of the geriatric depression scale preliminary questionnaire through learning when the patient's attribute information is input, and provides a second learning model including psychological symptoms, depression-related information, and Korean version of geriatric depression suspicion information as detailed information. The results of the questionnaire can be printed.

Alternatively, the second learning model unit 22 outputs the results of the alcohol addiction preliminary questionnaire through learning when the patient's attribute information is input, and outputs the results of the second questionnaire including psychological symptoms and Korean-style alcoholism suspicion information as detailed information. can do.

Alternatively, the second learning model unit 22 outputs the fatigue symptom scale preliminary questionnaire results when inputting the patient's attribute information through learning, and outputs the second questionnaire results including physical symptoms and fatigue symptom information as detailed information. You can.

Alternatively, the second learning model unit 22 outputs the results of the dementia scale preliminary questionnaire through learning when the patient's attribute information is input, and outputs the results of the second questionnaire including psychological symptoms, depression, and information suspected of elderly depression as detailed information. Can be printed.

In addition, the second learning model unit 22 can provide hospital recommendation and reservation functions based on AI preliminary questionnaire technology and the results of the second questionnaire. The second learning model unit 22 may be configured to include a voice recognition-based pre-interrogation technology and a self-diagnosis pre-interrogation technology, and if a doctor's consultation for symptoms is necessary, medical services can be provided through a chat service. there is.

Additionally, the second learning model unit 22 may be designed to be interoperable with non-face-to-face image monitoring technology through the second remote imaging equipment 24 through collection of preliminary questionnaire data.

The second learning model unit 22 can use general hospital information, general pharmacy information, hospital cost information, doctor information, and medical encyclopedia (disease/drug/test) information as learning data. In addition, it is possible to learn together with preliminary questionnaire data composed by professional medical staff and medical institution workers.

The advanced medical institution server 20 may transmit the measurement results of the second medical measurement equipment 25 to the cooperative medical institution server 10 using the second remote imaging equipment 24.

The advanced medical institution server 20 according to the embodiment may operate in conjunction with the second remote imaging equipment 24 and the second medical measurement equipment 25. The second remote imaging device 24 may be configured to be portable, and when mounted on the second docking station 26 placed within a higher medical institution, the upper medical institution server 20 and the second medical institution can be measured through a plug-and-play operation. It can be linked to equipment 25.

The second docking station 26 may be equipped with a second remote imaging device 24, a plurality of second medical measurement devices 25, and a plurality of ports corresponding to a hospital server. The plurality of ports include a parallel interface unit, a serial interface unit, a USB interface unit, a Dicom interface unit, an external memory interface unit, an analog video interface unit, and a wireless communication module unit, and each interface unit is configured to have at least one port. It can be.

The second remote imaging device 24 can photograph a patient, medical staff, or the second medical measurement device 25, generate image information including video and audio, and transmit it to the second communication unit 23 in real time.

The second remote imaging equipment 24 may include a display capable of displaying image data received from the cooperative medical institution server 10 and various data. The display receives image data from the cooperative medical institution server 10 and displays it in real time, allowing practitioners to conduct real-time consultations with remote medical experts or patients.

The second medical measurement equipment 25 includes medical devices that measure the operating status of various organs of the patient, such as imaging medical devices, electrocardiogram measurement devices, and blood pressure measurement devices that image the patient's body and organs, and the patient's It may include clinical devices that measure and analyze levels of various elements in samples collected from the body or from nature.

Additionally, the second medical measurement equipment 25 may further include one of a blood test device, a medical scope, a stress meter, a psychotherapy device, a blood pressure meter, a body fat meter, a blood sugar meter, and a thermometer. Medical measurement equipment can also refer to electronic devices that can measure various biosignals of a user, and can refer to wearable devices that are worn directly on the user's body, such as those built into clothing or on a belt.

The second medical measurement equipment 25 can measure the user's biosignals using various devices and transmit the medical measurement data generated accordingly to the second communication unit 23.

The second communication unit 23 may perform wireless communication with the cooperative medical institution server 10. The second communication unit 23 is, for example, long-term evolution (LTE), LTE Advance (LTE-A), code division multiple access (CDMA), wideband CDMA (WCDMA), universal mobile telecommunications system (UMTS), and WiBro. It may be configured to include at least one communication module, such as (Wireless Broadband) or GSM (global system for mobile communications).

Additionally, the second communication unit 23 may receive advance management reservation information, first questionnaire results, etc. from the cooperative medical institution server 10.

The remote patient management system according to the embodiment is a high-quality non-face-to-face system in medically vulnerable areas or infection-risk areas in order to ensure the safety of citizens and medical institutions, eliminate medical blind spots, reduce the burden of medical expenses, and improve the convenience of patients and guardians, such as at screening clinics when diseases such as infectious diseases are prevalent. It can be designed to utilize medical services. The remote patient management system can provide on-site video communication-based non-face-to-face treatment support medical services by combining commercially available tablet terminals and V2oIP (Voice and Video over Internet Protocol) software.

The remote patient management system according to the embodiment is a non-face-to-face treatment system that can be moved from various types of medically vulnerable areas such as screening clinics, public health centers, etc., to provide medical treatment throughout the entire cycle of treatment (Pre-Hospital, On-Hospital, After-Hospital). We can provide support to enable non-face-to-face treatment.

In an embodiment, Pre-Hospital includes a processor that pre-checks the patient's medical history through an artificial intelligence-based medical examination system, On-Hospital includes a non-face-to-face remote collaborative examination process using a high-resolution video docking station, and After-Hospital. may include follow-up management and monitoring processes through a non-face-to-face treatment support system.

In addition, through IoMT linkage and a docking system for high-resolution images, accurate positioning of the patient's affected area is possible at a remote advanced medical institution, and high-resolution images that can be delivered without screen enlargement and distortion of the patient's image can be provided.

In addition, non-face-to-face treatment can be supported by linking various medical images to a tablet PC through a docking station for linking IoMT (Internet of Medical Things)-based medical measurement equipment.

The remote patient management system according to the embodiment applies AI questionnaire-based medical diagnosis assistance guidance technology, quickly detecting the presence or absence of a patient's health abnormality through linkage with medical devices using the big data-based AI questionnaire of the Health Insurance Review and Assessment Service and IoMT interconnection technology. We can provide diagnostic assistance guidance services that can help medical staff make decisions.

In addition, through the smartphone application, patients can receive non-face-to-face after-care services even after treatment, and can continuously receive services such as AI questionnaires, medical appointments, and non-face-to-face treatment.

First, the cooperative medical institution server may input the patient's prior management reservation information registered online into the first learning model unit and output the first questionnaire result (S501).

Next, the cooperative medical institution server may determine whether the patient should receive regular treatment or remote treatment based on the results of the first questionnaire and then transmit reservation confirmation information to the terminal of the user who has registered the patient information. The cooperative medical institution server can automatically select the patient's department and appointment schedule using the results of the first questionnaire and transmit it to the patient's terminal. Additionally, the collaborative medical institution server may use the results of the first questionnaire to determine whether treatment at a higher medical institution is necessary and, if necessary, transmit a request for remote collaborative medical treatment to the higher medical institution server (S502).

Next, the higher-level medical institution server may confirm the remote collaborative consultation request received from the collaborating medical institution server and then transmit a remote collaboration approval message to the collaborating medical institution server. The higher-level medical institution server may determine whether remote collaborative consultation is possible in response to the remote collaborative consultation request and then transmit a message to the collaborative medical institution server (S503).

The cooperative medical institution server may receive a remote collaborative medical treatment approval message.

Next, the higher-level medical institution server may transmit a medical information request message to the cooperative medical institution server approved for remote collaboration. The medical information request message may be a message including a request for patient image information, medical measurement information, etc. (S504).

Next, the cooperative medical institution server may transmit the patient's medical information through remote imaging equipment and medical measurement equipment at the request of the superior medical institution server (S505).

In this case, the remote video equipment of the cooperative medical institution server and the higher-level medical institution server can each photograph patients, medical staff, or medical measurement equipment, generate image information including video and audio, and transmit it to the other party in real time. In addition, the medical measurement equipment of the cooperative medical institution server can measure the user's biosignals using various devices and transmit the resulting medical measurement data to the higher-level medical institution server.

Next, the higher-level medical institution server may transmit the medical staff opinion and prescription that analyzed the patient's medical information to the cooperative medical institution server (S506).

Next, the higher-level medical institution server can input the patient's post-care reservation information registered online into the second learning model unit and output the second questionnaire result (S507).

Next, the higher-level medical institution server can remotely monitor the patient's abnormal signs according to the results of the second questionnaire and the patient's previous medical history and then decide whether or not the patient should visit the medical institution. The higher-level medical institution server can use the results of the second questionnaire and the previous patient's medical history to determine abnormal signs of the patient, automatically select the department and appointment schedule, and transmit the information to the patient's terminal. Additionally, the higher-level medical institution server may use the second questionnaire result to determine whether collaborative medical treatment with a cooperative medical institution is necessary and, if necessary, transmit a remote collaborative medical examination request to the cooperative medical institution server. Alternatively, if there are no abnormal signs or if abnormal signs exist but a visit to a medical institution is not necessary, the monitoring findings can be transmitted to the user terminal (S508).

The term '~unit' used in this embodiment refers to software or hardware components such as FPGA (field-programmable gate array) or ASIC, and the '~unit' performs certain roles. However, '~part' is not limited to software or hardware. The '~ part' may be configured to reside in an addressable storage medium and may be configured to reproduce on one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. In addition, the components and 'parts' may be implemented to regenerate one or more CPUs within the device or secure multimedia card.

Although the present invention has been described above with reference to preferred embodiments, those skilled in the art may make various modifications and changes to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that you can do it.

10: Partner medical institution server
11: first input unit
12: First learning model part
13: First Department of Communications
14: First remote imaging equipment
15: First medical measurement equipment
16: first docking station
17: First database
20: Higher medical institution server
21: second input unit
22: Second learning model part
23: Second Department of Communications
24: Second remote imaging equipment
25: Second medical measurement equipment
26: second docking station
27: Second database

Claims (5)

The patient's prior management reservation information registered online is entered into the first learning model unit, the first questionnaire results are output, and the patient's general treatment or remote treatment is decided based on the first questionnaire results, and then the patient information is registered. A cooperative medical institution server that transmits reservation confirmation information to the user's terminal; and
The patient's follow-up care reservation information registered online is entered into the second learning model unit to output the second questionnaire result, and the patient's abnormal signs are remotely monitored according to the second questionnaire result and the patient's previous medical history. It includes a higher-level medical institution server that determines whether the patient should visit the medical institution,
The advance management reservation information is information that the patient inputs step by step before treatment, and the first learning model unit uses the advance management reservation information to query and predict related symptoms to screen for diseases similar to the patient's symptoms before treatment. Printing the results of the first questionnaire,
The after-care reservation information is information that the patient enters step by step after treatment, and the second learning model unit uses the after-care reservation information to query and predict related symptoms, thereby predicting abnormal signs and diseases after treatment. 2Remote patient management system that prints questionnaire results.
According to paragraph 1,
A remote patient management system in which the cooperative medical institution server and the superior medical institution server perform remote collaboration through remote imaging equipment and medical measurement equipment.
According to paragraph 2,
The advanced medical institution server transmits a medical information request message to the cooperative medical institution server, and remotely monitors the patient's abnormalities by analyzing the medical information of the patient received in response to the medical information request message. Management system.
According to paragraph 3,
A remote patient management system in which the cooperative medical institution server transmits measurement results of the medical measurement equipment to the higher-level medical institution server using the remote imaging equipment.
A cooperative medical institution server inputting advance management reservation information of a patient registered online into a first learning model unit and outputting a first questionnaire result;
The cooperative medical institution server determines whether to provide general medical treatment or remote medical treatment for the patient according to the results of the first questionnaire, and then transmitting reservation confirmation information to the terminal of the user who has registered patient information;
A higher-level medical institution server inputs the patient's post-care reservation information registered online into a second learning model unit and outputs a second questionnaire result; and
A step wherein the higher-level medical institution server remotely monitors abnormal signs of the patient according to the results of the second questionnaire and the patient's previous medical history, and then determines whether the patient should visit the medical institution,
The advance management reservation information is information that the patient inputs step by step before treatment, and the first learning model unit uses the advance management reservation information to query and predict related symptoms to screen for diseases similar to the patient's symptoms before treatment. Printing the results of the first questionnaire,
The after-care reservation information is information that the patient enters step by step after treatment, and the second learning model unit uses the after-care reservation information to query and predict related symptoms, thereby predicting abnormal signs and diseases after treatment. 2Remote patient management method that prints questionnaire results.

Images