KR20090049426A - Customized healthcare support service - Google Patents
Customized healthcare support service Download PDFInfo
- Publication number
- KR20090049426A KR20090049426A KR1020070115679A KR20070115679A KR20090049426A KR 20090049426 A KR20090049426 A KR 20090049426A KR 1020070115679 A KR1020070115679 A KR 1020070115679A KR 20070115679 A KR20070115679 A KR 20070115679A KR 20090049426 A KR20090049426 A KR 20090049426A
- Authority
- KR
- South Korea
- Prior art keywords
- data
- words
- health
- user
- algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Epidemiology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
가.[요약]란에는 발명의 내용을 용이하게 파악할 수 있도록 다음 내용에 관한 사항을 기재하여야 합니다.A. In the [summary] section, the following matters should be described so that the contents of the invention can be easily understood.
(1) 발명이 속한 기술분야(30자 내외) (1) The technical field to which the invention belongs (about 30 words)
지능형시스템, 진단지원 Intelligent system, diagnostic support
(2) 발명의 목적(80자 내외) (2) Purpose of invention (about 80 characters)
본 발명 시스템은 사용자의 자신의 생활패턴에 맞는 일반적인 건강상태 확인하기 위하여 개발된 시스템이다. 즉 사람이 살아가면서 생체신호가 발생하게 되는데 이에 따른 데이터를 지능형 알고리즘인 신경망 알고리즘을 이용하여 학습하게 되고 이를 기반으로 자신의 생체신호에 따른 건강상태를 체크하게 된다. The present invention is a system developed to check the general state of health according to the user's own life patterns. In other words, a bio signal is generated as a person lives, and the data is learned using an neural network algorithm, which is an intelligent algorithm, and based on this, a health state according to a bio signal is checked.
(3) 발명의 구성(250자 내외) (3) Composition of invention (about 250 words)
본 시스템은 신경망 알고리즘으로 구성되어 있으며 입력단자에는 생체신호와 활동량 그리고 음식의 영양소를 입력하게 되며 학습 데이터는 의사나 혹은 전문가가 진단한 위험수위 1~3가 선정하여 이용하게 되며 사용자가 생활을 하면서 측정하게 되는 데이터는 학습시킨 데이터를 통하여 발생된 가중치를 통하여 자신의 건강상태를 확인할수 있다. This system is composed of neural network algorithm, and input signal inputs bio signal, activity amount and nutrient of food, and learning data is selected and used by dangerous level 1 ~ 3 diagnosed by doctor or expert. The data to be measured can check their own health status through the weights generated from the learned data.
(4) 발명의 효과(50자 내외) (4) Effect of invention (about 50 words)
본 시스템은 사용자에 일반적인 생체리듬을 학습한 모델을 이용하였기 때문에 사용 자 개개인에 맞는 맞춤형 진단 지원이 가능하다.This system uses a model that learns biorhythms that are common to users, so it is possible to support customized diagnosis for each user.
[대표도][Representative diagram]
맞춤형, 건강상태, 학습형 알고리즘, 진단지원 시스템, CAD, CDSS Customized, health status, learning algorithm, diagnostic support system, CAD, CDSS
Description
현재 점차적으로 의료 기술이 발달하게 되면서 전세계적으로 인구의 노령화가 사회적으로 문제가 되고 있으며 그로 인하여 독거노인의 수가 증가하고 있는 실정이다. 통계청의 자료에 의하면 이러한 노인들의 약 75%가 고위험군 환자이거나 성인병 및Metabolic Syndrome(대사증후군)으로 분류되고 있다. 이와 같은 질병은 우리의 나쁜 생활습관을 통하여 발생되는 질병들이며 이는 다른 질병들과 합병증으로 동반될 수 있는 질병들이다. 따라서 지속적인 관리가 필요한 질병들이다. 그러나 현재의 의료서비스로서는 사용자 및 환자를 실시간으로 모니터링 할 수 없음으로 지속적인 관리가 불가능한 실정이다. 또한 의료에서 실시하는 표준은 모든 사람의 통계적인 데이터를 이용하기 때문에 각각의 사람에게는 틀리는 경우도 발생한다. 예를 들면 노인의 경우 혈압이 140 / 100 임에도 불구하고 의사들은 어르신이니까 그럴수도 있다고 하는경우인데 이는 의료인의 관점에서 본다면 고혈압으로 판명된다. 그러나 만약 자신의 평균적인 상태를 지속적으로 학습하고 있고 만약 이상태에서 벗어나게 된다면 건강상태가 이상하다는 것을 확인 할 수 있다면 이것은 자신에 맞는 건강상 태를 보다 구체적으로 확인 할수 있다는 결론을 얻게 된다. 그러나 지금까지의 기술에서는 많은 어려움이 존재하였으나 최근 정보 통신 기술 발달하게 되면서 점차 사람을 중심으로 한 유비쿼터스 환경에 대한 관심이 높아지고 있는 가운데 본 연구에서는 의료도메인과 IT기술을 접목한 사람중심의 Wellbeing lifecare 서비스가 필요함을 인지하였고 그 중에서도 가장에서 자신의 생체 신호를 배경으로 한 지능형 건강관리 시스템의 필요성을 느끼게 되었다. As the medical technology is gradually developed, the aging of the population is a social problem worldwide, and the number of elderly people living alone is increasing. According to statistics from the National Statistical Office, about 75% of these elderly people are high-risk patients or classified as adult disease and Metabolic Syndrome. These diseases are those that occur through our bad lifestyles, which can be accompanied by complications with other diseases. Therefore, these diseases need constant care. However, current medical services cannot monitor users and patients in real time, so continuous management is impossible. In addition, standards used in medicine use statistical data of all people, which is sometimes wrong for each person. For example, in the elderly, even though the blood pressure is 140/100, doctors say they may be because they are older, which is proven to be high blood pressure from the medical practitioner's point of view. However, if you are continuously learning your average condition and if you can get out of this condition, you can confirm that your health is abnormal. However, there have been many difficulties in the technology up to now, but as the information and communication technology has been developed recently, the interest in the ubiquitous environment centered on people is increasing. In this study, the wellbeing lifecare service centered on the medical domain and IT Was aware of the necessity, and most of them felt the need for an intelligent health care system based on their bio signals.
따라서 본 발명은 자신의 생체신호 및 생활패턴 데이터를 지속적으로 획득하여 이를 학습하여 지속적으로 측정하는 데이터의 형태가 현재의 상태와 벗어나게 되면 건강상태의 이상을 확인해 주는 시스템이다. 이를 건강상태 지원 시스템이라고 부르게 되었다. Therefore, the present invention is a system that checks the abnormality of the state of health when the form of the data that continuously acquires its own bio-signal and life-pattern data and learns it continuously and out of the current state. This is called the health support system.
[발명의 구성]란에는 발명의 목적을 해결하기 위하여 강구한 수단과 구성을 함께 기재하여야 합니다. 해당발명의 기술분야에 대한 통상의 지식을 가진 자의 실시를 위하여 필요한 경우에는 그 발명의 구성이 실제상 어떻게 구체화되는가를 나타내는 실시 예를 기재하여야 합니다. 그 실시 예는 특허출원인이 가장 좋은 결과를 얻는 것이라고 생각되는 것을 가급적으로 여러 종류를 기재하고 필요에 따라 구체적 숫자에 기인한 사실을 기재하여야 합니다.The [Structure of the Invention] field shall include the means and the constitution which have been devised to solve the object of the invention. If necessary for the implementation of a person having ordinary knowledge in the technical field of the present invention, an embodiment showing how the configuration of the invention is actually specified should be described. The examples should describe as many as possible what the patent applicant believes are the best results and the facts due to specific numbers as necessary.
본 발명은 사람의 건강상태를 생활습관을 통하여 확인할 수 있는 컴퓨터 기반의 건강상태 지원 시스템을 의사결정 AGENT를 통하여 구성하였다. 본 건강상태 지원 시스템은 신경망 알고리즘을 통하여 구축되어 있다. The present invention is a computer-based health status support system that can confirm the health status of people through the lifestyle through the decision AGENT. This health state support system is constructed through neural network algorithm.
의료 진단 에이전트는 최초 실행 시 DB 에이전트에서 관리하고 있는 데이터베이스의 정보를 이용하여 DB 에이전트에 자료를 요청하고 요청된 자료를 이용하여 학습을 하게 된다. 이를 통해 학습된 연결강도(Weight)들은 학습 시간을 단축하기 위해 별도로 내부 컴퓨터에서 관리하도록 한다. 학습이 끝난 후, 진단 에이전트는 DB 에이전트에서 제공하는 데이터베이스의 정보를 일정한 시간마다 감시를 한다. 감시 중 환자의 측정 데이터가 입력되면 그 데이터를 요청하고 진단한 후 그 결과를 다시 데이터베이스에 입력 요청을 한다. 또한 전문의로부터 환자의 생체 데이터에 대한 진단이 이루어지면 다시 그 진단 데이터를 학습하게 된다.The medical diagnostic agent requests data from the DB agent using the information of the database managed by the DB agent at the first execution and learns from the requested data. Through this, the learned connection strengths are managed separately in the internal computer to reduce the learning time. After the training, the diagnostic agent monitors the database information provided by the DB agent at regular intervals. When the patient's measurement data is entered during monitoring, the data is requested, diagnosed, and the results are entered into the database. In addition, when the diagnosis of the patient's biometric data is made by a specialist, the diagnosis data is learned again.
신경망 알고리즘 (Back Propagation)Neural Network Algorithm (Back Propagation)
역전파 알고리즘(Backpropagation)은 지도학습(Supervised learning)모델로 입력값과 목표값이 각 뉴런이 연결된 연결강도(Weight)를 조절함으로써 이루어지는데 이것은 출력값(Output value)과 목표값(Target value)을 비교하여 오차를 줄여가는 방향으로 진행함으로써 학습이 되어간다. 전방향 역전파 알고리즘은 각 학습패턴에 따른 입력벡터가 입력층에 주어지면 이들 값으로부터 은닉층의 노드값들이 구해지게 되고 다시 이들 은닉노드들의 값으로부터 출력노드들의 값이 구해지게 된다. 이후 출력값과 주어진 목표값과 비교하여 에러를 계산한다. 이러한 에러를 0에 가까운 최소값으로 만들기 위해 출력된 값과 목표 출력치와의 차이인 에러에 근거하여 , 즉 출력층과 은닉층 사이의 연결강도를 수정한 다음 역방향으로 은닉층과 입력 층 사이의 연결강도를 수정한다. Backpropagation is a supervised learning model in which the input and target values are adjusted by adjusting the weight of each neuron to which the neurons are connected. This compares the output value with the target value. Learning by going in the direction of reducing errors. In the omnidirectional backward propagation algorithm, when the input vector corresponding to each learning pattern is given to the input layer, the node values of the hidden layer are obtained from these values, and the output nodes are obtained from the values of these hidden nodes. The error is then calculated by comparing the output with the given target value. Based on the error, which is the difference between the output value and the target output value, to make this error a minimum value close to zero. In other words, the connection strength between the output layer and the hidden layer is modified, and then the connection strength between the hidden layer and the input layer is reversed.
<그림 2: 신경망 시스템 >Figure 2: Neural Network System
입력데이터 속성 Input data attribute
1.흡연 유무 및 흡연량 1. Smoking and smoking amount
2.수면시간2.sleep time
3. 수면 만족도3. Sleep satisfaction
4. 하루 운동량 (만보계를 이용)4. Daily exercise (using a pedometer)
5. 생체신호 (현재 사용자의 혈압, 혈당 등의 기초 생체 신호)5. Biosignal (basic biosignal of current user's blood pressure, blood sugar, etc.)
Target 데이터 Target data
위험상태 Level 1~3Danger Level 1 ~ 3
Level 1: 정상Level 1: Normal
Level 2: 조심Level 2: Beware
Level 3: 위험Level 3: Danger
[발명의 효과]란에는 당해 발명에 의하여 발생한 특유의 효과를 구체적으로 기재하여야 합니다.[Effects of the Invention] should specifically describe the unique effects caused by the invention.
Claims (4)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020070115679A KR20090049426A (en) | 2007-11-13 | 2007-11-13 | Customized healthcare support service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020070115679A KR20090049426A (en) | 2007-11-13 | 2007-11-13 | Customized healthcare support service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| KR20090049426A true KR20090049426A (en) | 2009-05-18 |
Family
ID=40858182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| KR1020070115679A Withdrawn KR20090049426A (en) | 2007-11-13 | 2007-11-13 | Customized healthcare support service |
Country Status (1)
| Country | Link |
|---|---|
| KR (1) | KR20090049426A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9547820B2 (en) | 2011-11-08 | 2017-01-17 | Samsung Electronics Co., Ltd. | Method of classifying input pattern and pattern classification apparatus |
| KR20180014559A (en) | 2016-08-01 | 2018-02-09 | 한국 한의학 연구원 | Symptoms summary method |
-
2007
- 2007-11-13 KR KR1020070115679A patent/KR20090049426A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9547820B2 (en) | 2011-11-08 | 2017-01-17 | Samsung Electronics Co., Ltd. | Method of classifying input pattern and pattern classification apparatus |
| KR20180014559A (en) | 2016-08-01 | 2018-02-09 | 한국 한의학 연구원 | Symptoms summary method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dhruba et al. | [Retracted] Development of an IoT‐Based Sleep Apnea Monitoring System for Healthcare Applications | |
| JP5465250B2 (en) | Detection of decompensated congestive heart failure | |
| Aboukhalil et al. | Reducing false alarm rates for critical arrhythmias using the arterial blood pressure waveform | |
| US20190076098A1 (en) | Artificial Neural Network Based Sleep Disordered Breathing Screening Tool | |
| Chumbler et al. | The association of home-telehealth use and care coordination with improvement of functional and cognitive functioning in frail elderly men | |
| CN112151172A (en) | Patient risk assessment based on data from multiple sources in healthcare settings | |
| CN110033866A (en) | Healthalert method, apparatus, computer equipment and storage medium | |
| US20090170056A1 (en) | Method, medium, and apparatus for providing educational material in remote monitoring system | |
| CN118379173B (en) | Comprehensive safety monitoring method based on digital aged care | |
| CN111820879A (en) | A health evaluation management method suitable for patients with chronic diseases | |
| Akhtar et al. | Detection of Sleep Paralysis by using IoT Based Device and Its Relationship Between Sleep Paralysis And Sleep Quality. | |
| Kostishyn et al. | Design features of automated diagnostic systems for family medicine | |
| CN116965776A (en) | Child severe monitoring system and method based on PEWS classification | |
| CN107403061A (en) | User's medical assessment model building method and medical assessment server | |
| Despins et al. | Using sensor signals in the early detection of heart failure: A case study | |
| Marcos et al. | Radial basis function classifiers to help in the diagnosis of the obstructive sleep apnoea syndrome from nocturnal oximetry | |
| CN112309570A (en) | Personalized benchmarking, visualization and handover | |
| CN112786199B (en) | Interface for displaying patient data | |
| Valsalan et al. | Remote healthcare monitoring using expert system | |
| Tamura et al. | Preliminary study of a new home healthcare monitoring to prevent the recurrence of stroke | |
| McCollum et al. | Inconsistent health perceptions for US women and men with diabetes | |
| CN115910346A (en) | A monitoring and early warning system and method for diabetic patients | |
| KR20090049426A (en) | Customized healthcare support service | |
| CN116453641B (en) | A data processing method and system for auxiliary analysis information of traditional Chinese medicine | |
| CN112957017B (en) | Real-time physical sign monitoring method and system for coma patient |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PA0109 | Patent application |
Patent event code: PA01091R01D Comment text: Patent Application Patent event date: 20071113 |
|
| PG1501 | Laying open of application | ||
| PC1203 | Withdrawal of no request for examination | ||
| WITN | Application deemed withdrawn, e.g. because no request for examination was filed or no examination fee was paid |