KR20220148957A - Ai alarm system based on edge computing in remote patient monitoring environment - Google Patents

Abstract

An edge computing-based AI alarm system in a remote patient monitoring environment is provided. The edge computing-based AI alarm system in a remote patient monitoring environment according to various embodiments of the present invention may predict not only diseases but also various risk situations such as falls for patients receiving care at home, and provide notifications based on the prediction results.

Description

AI ALARM SYSTEM BASED ON EDGE COMPUTING IN REMOTE PATIENT MONITORING ENVIRONMENT in remote patient monitoring environment

Various embodiments of the present invention relate to an edge computing-based AI alarm system in a remote patient monitoring environment, and more specifically, predicts various risk situations such as a fall as well as a disease for a patient who is recuperating at home, and predicts the prediction result. It relates to an edge computing-based AI alarm system in a remote patient monitoring environment that provides notifications according to

Remote patient monitoring literally means that patients have their health status managed remotely even when they are not in the hospital.

Remote patient monitoring transmits 'patient-derived medical data' measured in various ways such as digital devices in an environment outside the hospital, such as at home, to a hospital, etc. This can be of great help in disease management and quality of life for patients undergoing surgery who need to closely monitor the prognosis of surgery after surgery, or for patients with severe chronic diseases who have to live with the disease all the time outside of the hospital.

However, in remote patient monitoring, the areas of monitoring and action for data transmitted remotely are still dependent on people, and in the case of non-hospital home care, 24-hour nursing is difficult in most cases, and there is no reporter or late-night hours. In this case, there is a problem that insufficient first aid measures due to lack of patient monitoring can lead to serious accidents.

Therefore, there is a need for an intelligent detection/warning system that automatically communicates the appropriate situation and whether emergency services are needed according to the monitored patient data to guardians and hospitals.

The problem to be solved by the present invention is a remote patient management service based on Patient Monitor that can be used at home and a remote that can provide a warning system for various emergency situations such as “shock prediction”, “pneumonia prediction”, “fall detection”, etc. It is to provide an edge computing-based AI alarm system in a patient monitoring environment.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

The edge computing-based AI alarm system in a remote patient monitoring environment according to an embodiment of the present invention for solving the above-described problems predicts and predicts various dangerous situations such as a fall as well as a disease for a patient who is recuperating at home Depending on the result, a notification can be provided.

Other specific details of the invention are included in the detailed description and drawings.

According to various embodiments of the present invention, it is possible to provide a remote patient management service based on Patient Monitor that can be used at home and a warning system for various emergency situations such as “shock prediction”, “pneumonia prediction”, “fall detection”, etc. It can provide an edge computing-based AI alarm system in a remote patient monitoring environment.

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1-8 are diagrams illustrating an edge computing-based AI alarm system in a remote patient monitoring environment, in various embodiments.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully inform those skilled in the art of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may be the second component within the spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used herein will have the meaning commonly understood by those of ordinary skill in the art to which this invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless clearly specifically defined.

As used herein, the term “unit” or “module” refers to a hardware component such as software, FPGA, or ASIC, and “unit” or “module” performs certain roles. However, “part” or “module” is not meant to be limited to software or hardware. A “part” or “module” may be configured to reside on an addressable storage medium or may be configured to reproduce one or more processors. Thus, by way of example, “part” or “module” refers to components such as software components, object-oriented software components, class components and task components, processes, functions, properties, Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. Components and functionality provided within “parts” or “modules” may be combined into a smaller number of components and “parts” or “modules” or additional components and “parts” or “modules”. can be further separated.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe the correlation between a component and other components. A spatially relative term should be understood as a term that includes different directions of components during use or operation in addition to the directions shown in the drawings. For example, when a component shown in the drawing is turned over, a component described as “beneath” or “beneath” of another component may be placed “above” of the other component. can Accordingly, the exemplary term “below” may include both directions below and above. Components may also be oriented in other orientations, and thus spatially relative terms may be interpreted according to orientation.

In this specification, a computer means all types of hardware devices including at least one processor, and may be understood as encompassing software configurations operating in the corresponding hardware device according to embodiments. For example, a computer may be understood to include, but is not limited to, smart phones, tablet PCs, desktops, notebooks, and user clients and applications running on each device.

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

Each step described in this specification is described as being performed by a computer, but the subject of each step is not limited thereto, and at least a portion of each step may be performed in different devices according to embodiments.

1-8 are diagrams illustrating an edge computing-based AI alarm system in a remote patient monitoring environment, in various embodiments.

1 to 8 , in various embodiments, an edge computing-based AI alarm system in a remote patient monitoring environment includes a Patient Monitor-based remote patient management service that can be used at home and “shock prediction”, “pneumonia prediction”, A warning system for various emergency situations such as “fall detection” can be provided.

In 2018, the global population aged 65 and over exceeded the number of children under the age of 5, and the number of people aged 80 and over is expected to increase from 143 million in 2019 to 426 million in 2050. It is predicted that the elderly population aged 65 or older will account for more than 14% of the population, and by 2026, it will become a 'super-aged society', accounting for more than 20% of the total population.

As a result of the National Health Insurance Corporation survey, among the 131,802 seniors aged 65 and over who died in 2018, the average length of time spent in a nursing home or facility for 10 years before death was 707 days, 406 days in nursing homes and 904 days in nursing homes.

In addition, patients with severe disease in Korea are discharged when acute treatment is completed at a tertiary hospital. A total of 67.5% of the medical staff said they had an experience of feeling anxious.

In addition, in a survey of 200 patients who visited the hospital in the same year, 39% of the respondents said that they had “experienced feeling uneasy at discharge,” and 78.5% of those who complained of difficulties in caring after discharge were also counted.

As described above, in addition to responding to the aging population, systematic and high-quality visiting medical services for discharged patients are very necessary.

In contrast, in Korea, it is predicted that the age of 1 million dementia patients in 2024 and 10 million elderly people in 2026 will arrive. They are experiencing difficulties due to lack of health care and social services.

Accordingly, in November 2018, the Ministry of Health and Welfare announced the Basic Plan for Community Integration Care (Community Integration Care: Residents in need of care, such as the elderly and the disabled, live in the home (home or group home, etc.) A community-driven social service policy that provides integrated support for housing, health care, nursing care, and independent living so that people can enjoy services that meet their needs and live in harmony with the local community.

- Provided services: visit health care at public health centers, home care at medical institutions, long-term care visits

-Provided effect: improvement of health-dangerous practices of the subject, improvement of self-health management ability for chronic diseases, improvement of self-health management ability for chronic diseases, reduction of risk of complications, reduction of medical expenses

- Problems: - Different providers, service providers, contents, financial resources, etc., lack of integrated linkage system, overlapping or similar services provided by providers, regional imbalance (existence of regions that do not receive services) (services are not unified, overlapping There is a case of provision and there is a difference depending on the region)

Also, in Japan, the Regional Comprehensive Care Project was promoted in 2011 to strengthen the linkage with medical care, such as the establishment of a 24-hour regular round-the-clock temporary response service and a complex service, and the establishment of a comprehensive care prevention and daily life support project.

One installed in each of the 47 prefectures, and the medical insurance system for the elderly (aged 75 or older) was operated through a medical regional federation to which the city, gu, eup, and myeon joined. Various types of services were provided, such as a function-reinforced visiting nursing station that can respond 24 hours a day, and a small-scale, multi-functional home care that has a day ward and provides long-term care services.

An average of 6 employees work at the visiting nursing station, and nurses account for 80% of the time, and an average of 67 people provide nursing care and the number of recipients is 5-6 times/month. It is common for nursing positions such as nurses, public health nurses, and associate nurses working in medical institutions to visit and provide services.

In order to promote at-home medical care suitable for a super-aged society, depending on the patient's condition, a nurse may perform 'specific actions (constant medical assistance: 38 actions that require advanced expertise - respiratory management, artificial respiration therapy, catheter management, etc.)' This is possible because it is difficult to select nurses with 5 or more years of practical experience or 3 or more years of home nursing experience when selecting nurses at the relevant institution.

The Regional Comprehensive Support Center is an institution operated by a municipality or a corporation entrusted by the municipality, and provides services by placing a public health nurse, social worker, chief, and nursing support specialist within 30 minutes of the target person. It provides integrated medical and social services through collaboration with various medical experts in the region.

Also, in the United States, home nursery has developed for early discharge patient management.

In order to reduce the cost of visiting nursing, the number of visits per beneficiary is limited, and the home nursing business is actively operated centering on independent home nursing offices. Operate programs such as Medicare/Medicaid for the elderly (elderly, disabled, low-income) (Medicare: for the elderly over 65 years old, disabled people, etc.)

Home health services are provided by home health agencies, and about 11,385 home health centers are in operation, and national medical expenditures accounted for about 15% of gross domestic product (GDP) in 2018, the highest among OECD countries. Medicare spending is $731 billion, almost 50% of which is spent on home care services, a growing share of which comes primarily from federal funding.

Nurses participating in home care must have at least a bachelor's degree, and nurses who provide primary care must have a master's degree or higher.

- Services: Salary (professional nursing, rehabilitation treatment, care service, social welfare counseling service, security device), non-pay (mobility support, 24-hour care, lunch box support, housework support, etc.)

- Professional Nursing Services: Management and evaluation of treatment plans, education and training of patients/patient guardians/caregivers, drug management including injections, tube replacement, aspiration, catheter cleaning and replacement, wound treatment including pressure sores, colostomy management, rehabilitation nursing etc.

Medicare home health care aims to provide medical services similar to medical institutions at home, to treat diseases or injuries in the short term, and to maintain the best health in the long term.

Since 2017, the Catholic Central Medical Center has been implementing an inpatient alternative nursing service in which a professional nurse visits the patient's home for patients who have difficulty visiting the hospital. Products and services that have limitations in the form of 'enforcement' that are measured only at home, and that enable continuous monitoring of the patient's condition even during times when nurses are not at home, are needed.

In addition, there is a system that sounds a notification when the value of the Patient Monitor is abnormal, but there is no intelligent product in the market that predicts the shock based on artificial intelligence. In addition, it is difficult to find a place that has established an environment where the notification of such an emergency can be identified by securing simultaneity in places that act as central control centers such as hospitals outside of individual homes.

Therefore, after an alarm is generated by an artificial intelligence-based prediction algorithm, the follow-up response service must be defined in the Community Care solution in advance. There should be a service mapping for 'whether evacuation is necessary'.

To this end, various embodiments of the present invention, a total of three systems (Patient Monitoring Device (a device that can measure the patient's condition at the patient's home), the Centralized Monitoring System (a system that can observe the patient's condition in the hospital), Cloud Patient Monitoring System (a detection/prediction system for observed patient conditions) can be developed and provided.

Context Diagram: EMR/PACS interworking (real-time/direct interworking impossible --> service implementation in an indirect connection method in batch units), My Health Record APP interworking (service interlocking through the interface with API provided by the APP), Cloud Patient Monitoring System Accessed by patients, nurses and hospital monitoring personnel.

Heath Monitoring Device (IoMT): Attached to the patient's body and collects a total of 8 signals (blood pressure is measured for each contraction/relaxation). Since it will be distributed and attached to individual homes, the volume and weight approach a portable level.

Remote Patient Monitoring System: Consists of 3 subsystems (system management, monitoring support, platform), system management (functions as a system administrator, and system configuration and status management are the main functions), monitoring support (screen viewed by real users) ) and platform (which handles most events as well as pneumonia prediction, fall detection, and shock prediction services).

Nurses/administrators will be provided with the following functions according to their certifications and privileges (e.g. can view data on patient status received from Patient Monitor, can receive pneumonia prediction, shock prediction and fall detection notifications, complete equipment (Patient Monitor operation status and overall patient status can be inquired).

Front-End Technical Stack (Administrator & Nurse): The front-end technology that administrators and nurses see is based on React, and supports not only Chrome browsers, but also MS Edge, Firefox, and Apple's Safari.

Back-End Technical Stack (overall monitoring system): Back-End consists of a total of 7 Main Stacks, hierarchy/analysis is composed of ELK-based, message broker is Kafa-based, and storage is SQL and No-SQL such as PostgreSQL and MongoDB is mixed according to the system configuration, the library is also mixed according to the system configuration such as WebSocket and MQTT, and the whole system is based on Linux.

Through the above system, acute and chronic stage patients have a common characteristic that they are difficult to monitor in small open hospitals or have a large burden after discharge from a tertiary hospital to a stable stage due to difficulty in movement and high severity, which may lead to a vacuum in the local community. There is an advantage that more thorough medical benefits can be provided to a group of patients who can be treated.

In addition, the non-face-to-face remote monitoring project can provide an opportunity to end concerns about the collapse of the medical delivery system that is widespread in the medical field by presenting and demonstrating a mutually cooperative model of an appropriate local medical institution-higher medical institution.

In various embodiments, an early warning of pneumonia occurrence may be performed using wearable monitoring equipment having an IoT function.

Community-acquired pneumonia is one of the most common causes of death among infectious diseases, with a mortality rate of 12-14% despite antibiotic treatment.

A large number of patients with squats are included among the recipients of visiting nursing/visiting treatment, and most of them are using tube feeding. Appropriate diagnosis and early treatment of pneumonia are important issues, as it is judged that they will show similar trends.

Common symptoms of pneumonia are cough, fever, sputum, chest pain, and shortness of breath. Fever occurs in about 80% of cases, but no fever in the elderly. It is difficult to accurately predict the presence of pneumonia.

If one of the vital signs abnormalities (temperature >38 degrees, pulse >100 beats/min, respiration rate > 20 beats/min) and clinical findings are present at the same time, chest radiography is recommended for pneumonia.

Therefore, in this research and development project, focusing on a part of the Pneumonia Severity Index (PSI), which predicts the severity of pneumonia, even when non-medical personnel observe it during home medical care and remote monitoring, only an index that can be caught early based on data based on 3 PSI cases Since it is a standard for recommending outpatient visits for class 2 pneumonia and inpatient treatment in cases of 4 to 5 cases, an AI platform-based early alarm function can be devised.

In various embodiments, an automated fall reporting system may be provided using a motion monitoring sensor.

Falls are a serious accident that has not been resolved for a long time not only at home, but also in medical institutions and nursing homes for the elderly.

In 5.0~10.0% of falls, serious injuries such as fractures or more may occur and even lead to death. Even if there is no death, hospitalization is often required. can lead to deterioration.

According to the results of a study published in 2019, more than 80% of the elderly at home over the age of 65 suffered a fall injury, of which 62.8% received treatment, and 55.6% of those treated were hospitalized.

As a solution for patient safety from the risk of falls, it can provide a smart notification system for early detection and evacuation of falls.

Through this, in terms of health and medical care, the procedure can be simplified by digitizing handover between hospitals by type according to the medical delivery system, and after the pilot project, it is possible to establish a standard medical system by expanding the applied disease group and present a commercialization and commercialization model. With the initial experimental nature of the initial model of non-face-to-face and telemedicine, it can lay the foundation for forming a smart medical block chain in the future, and use it as data for clinical research and form big data for the introduction of AI medical care in the future. (Prove the clinical effectiveness of telemedicine and use it as a basic research data linked to a large-scale clinical study) Through the expansion of disease, the hospital-centered medical environment will provide a basis for commercialization by reflecting the demand for patient-centered customized medical services) It will be used to lay the foundation for the creation of the telemedicine market), and as a standard model of the K-telemedicine system, it can occupy a key role in the rapidly emerging telemedicine ecosystem in countries around the world in the future.

In addition, from a clinical point of view, effective disease management can be achieved by improving the quality of medical care by receiving the patient's regular medical information in real time through a platform with clear interaction and applying it to treatment at the same time, and real-time biosensor information It can contribute to the development of an immediate response medical delivery system by presenting and judging the results of It is possible to provide effective medical services while minimizing hospital visits and unnecessary financial resources through remote management of diseases, and to prevent voluntary medical disconnection by providing more convenient medical services to the elderly and patients who need post-operative management with reduced mobility. There is an effect of preventing the consolidation of serious diseases through better disease management, and there is an effect of reducing the cost of medical treatment.

As mentioned above, although embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can realize that the present invention can be embodied in other specific forms without changing its technical spirit or essential features. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

Claims (1)

Predicting various dangerous situations such as falls as well as diseases for patients undergoing treatment at home, and providing notifications according to the prediction results,
Edge computing based AI alarm system in remote patient monitoring environment.

Images