• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.35-40
• /
• 2022

In this paper, we propose a method of constructing clinical knowledge with clinical concept relations and predicting diseases based on a deep learning model to support clinical decision-making. Clinical terms in UMLS(Unified Medical Language System) and cancer-related medical knowledge are classified into five categories. Medical related documents in Wikipedia are extracted using the classified clinical terms. Clinical concept relations are established by matching the extracted medical related documents with the extracted clinical terms. After deep learning using clinical knowledge, a disease is predicted based on medical terms expressed in a query. Thereafter, medical terms related to the predicted disease are selected as an extended query for clinical document retrieval. To validate our method, we have experimented on TREC Clinical Decision Support (CDS) and TREC Precision Medicine (PM) test collections.

• KOREAN POULTRY JOURNAL
• /
• v.18 no.7 s.201
• /
• pp.91-96
• /
• 1986

닭의 산란능력에 영향을 미치는 요인들을 개괄하였으며 특히 바이러스성 질병에 대하여 논의하였다. 전염성질병은 예측할 수 없는 상황에서 발생하므로 질병의 발생을 방지할 수 있는 모든 방법들이 사전에 강구되어야만 한다. 최근들어 전염성기관염이 전국적으로 확산됨에 따라 채란계농가나 종계농가의 피해가 날로 높아가리라 사료되며, 우리 모두의 지혜를 모아 어려움을 슬기롭게 풀어가야 하리라 믿는다

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.1
• /
• pp.57-66
• /
• 2017

SIR model (Kermack and McKendrik, 1927) is one of the most popular method to explain the spread of disease, In order to construct SIR model, we need to estimate transition rate parameter and recovery rate parameter. If we don't have any information of the two rate parameters, we should estimate using observed whole trajectory of pandemic of disease. Thus, with restricted observed data, we can't estimate rate parameters. In this research, we introduced Reed-Frost model (Andersson and Britton, 2000) to calculate the probability of infection in the early stage of pandemic with the restriction of data. When we have an initial number of susceptible and infected, and a final number of infected, we can apply Reed - Frost model and we can get the probability of infection. We applied the Reed - Frost model to the Vibrio cholerae pandemic data from Republic of the Cameroon and calculated the probability of infection at the early stage. We also construct SIR model using the result of Reed - Frost model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.602-604
• /
• 2017

As human life span has increased, people have wanted to live healthier desires. Especially Korea has rapidly entered an aging society, leading to the burden of medical expenses to the increase of disease accompanying aging. To alleviate the burden of medical expenses, prediction and prevention are important rather than treatment of diseases. It is possible to predict and prevent diseases by measuring individual genetic information. In order to utilize individual's genetic information Korea's genetic information is grasped through SNP (800 thousand) and GWAS optimized for the discovery of genetic factors of phenotype and disease of Koreans, The genetic information of each individual is analyzed in the genetic (constitutional) characteristics of the individual. In this thesis we develop a classification index so that we can classify populations of specific chronic diseases (obesity, diabetes or cardiovascular system). Try to develop health care services to manage custom diet and exercise associated with chronic illness.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.12
• /
• pp.1095-1105
• /
• 2013

This paper proposes the RDMS(Rough Set Theory based Disease Monitoring System) which efficiently manages diseases in Healthcare System. The RDMS is made up of DCM(Data Collection Module), RDRGM(RST based Disease Rules Generation Module), and HMM(Healthcare Monitoring Module). The DCM collects bio-metric informations from bio sensor of patient and stores it in RDMS DB according to the processing procedure of data. The RDRGM generates disease rules using the core of RST and the support of attributes. The HMM predicts a patient's disease by analyzing not only the risk quotient but also that of complications on the patient's disease by using the collected patient's information by DCM and transfers a visualized patient's information to a patient, a family doctor, etc according to a patient's risk quotient. Also the HMM predicts the patient's disease by comparing and analyzing a patient's medical information, a current patient's health condition, and a patient's family history according to the rules generated by RDRGM and can provide the Patient-Customized Medical Service and the medical information with the prediction result rapidly and reliably.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.1-3
• /
• 2006

대사증후군은 당뇨병, 고혈압, 복부 비만, 고지혈증 등의 질병이 한 개인에게 동시에 발현하는 것을 말하며, 최근 경제여건의 향상 및 식생활 습관의 변화와 함께 우리나라에서도 심각한 문제가 되고 있다. 한편 불확실성의 처리를 위해 많이 사용되는 베이지안 네트워크는 사람이 분석 가능한 확률 기반의 모델로 최근 의학분야에서 질병의 진단이나 예측모델을 구성하기 위한 방법으로 유용하게 사용되고 있다. 베이지안 네트워크의 구조를 학습하는 대표적인 알고리즘인 K2 알고리즘은 속성이 입력되는 순서의 영향을 받으며, 따라서 이 또한 하나의 주제로써 연구되어 왔다. 본 논문에서는 유전자 알고리즘을 이용하여 베이지안 네트워크에 입력되는 속성 순서를 최적화하며 이 과정에서 의학지식을 적용해 효율적인 최적화가 가능하도록 하였다. 제안하는 모델을 통해 1993년의 데이터를 가지고 1995년의 상태를 예측하는 분류 실험을 수행한 결과 속성 순서 최적화 후에 이전보다 향상된 예측율을 보였으며 또한 다층 신경망, k-최근접 이웃 등을 이용한 다른 모델보다 더 높은 예측율을 보였다.

• Tuberculosis and Respiratory Diseases
• /
• v.60 no.2
• /
• pp.215-220
• /
• 2006

Background : A spirometric reference equation was recently developed for the general population in Korea. The applicability of the new Korean equation to clinical practice was examined by comparing it with the Morris equation, which is one of the most popular reference equations used for interpreting the spirometric patterns and for grading the disease severity in Korea. Methods : Spirometry was performed on 926 men and 694 women, aged 20 years or older, in November 2004 at the Asan Medical Center, Seoul, Korea. The subjects' age, gender, height, weight, and spirometric values ($FEV_1$ [forced expiratory volume in one second], FVC [forced vital capacity], and $FEV_1/FVC$) were obtained. The spirometric patterns and disease severity were evaluated using both equations, and the results of the Korean equation were compared with the Morris equation. The spirometric patterns were defined as normal, restrictive, obstructive, and undetermined according to the level of $FEV_1/FVC$ and FVC. The disease severity was defined according to the level of $FEV_1$ level for subjects with an airflow limitation, and according to the FVC level for those subjects without an airflow limitation. Results : Spirometric patterns were differently interpreted in 22.5% (208/926) of the men and 24.8% (172/694) of the women after the application of the Korean equation compared with the Morris equation. Of the subjects with airflow limitation, disease severity was differently graded in 30.2% (114/378) of the men and 39.4% (37/94) of the women after the application of the Korean equation. Of the subjects without airflow limitation, disease severity was differently graded in 27.9% (153/548) of the men and 30.2% (181/600) of the women after the application of the Korean equation. Conclusion : Achange in the reference equation for spirometry could have an effect on the interpretation of spirometric patterns and on the grading of disease severity.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1266-1271
• /
• 2022

Cats have strong wildness so they have a characteristic of hiding diseases well. The disease may have already worsened when the guardian finds out that the cat has a disease. It will be of great help in treating the cat's disease if the owner can recognize the cat's polydipsia, polyuria, and frequent urination more quickly. In this paper, 1) Efficient version of DeepLabCut for pose estimation, 2) YOLO v4 for object detection, 3) LSTM is used for behavior prediction, and 4) BoT-SORT is used for object tracking running on an artificial intelligence device. Using artificial intelligence technology, it predicts the cat's next, polyuria and frequency of urination through the analysis of the cat's behavior pattern from the home CCTV video and the weight sensor of the water bowl. And, through analysis of cat behavior patterns, we propose an application that reports disease prediction and abnormal behavior to the guardian and delivers it to the guardian's mobile and the server system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.165-167
• /
• 2022

The proportion of cat cats among companion animals has been increasing at an average annual rate of 25.4% since 2012. Cats have strong wildness compared to dogs, so they have a characteristic of hiding diseases well. Therefore, when the guardian finds out that the cat has a disease, the disease may have already worsened. Symptoms such as anorexia (eating avoidance), vomiting, diarrhea, polydipsia, and polyuria in cats are some of the symptoms that appear in cat diseases such as diabetes, hyperthyroidism, renal failure, and panleukopenia. It will be of great help in treating the cat's disease if the owner can recognize the cat's polydipsia (drinking a lot of water), polyuria (a large amount of urine), and frequent urination (urinating frequently) more quickly. In this paper, 1) Efficient version of DeepLabCut for posture prediction running on an artificial intelligence server, 2) yolov4 for object detection, and 3) LSTM are used for behavior prediction. Using artificial intelligence technology, it predicts the cat's next, polyuria and frequency of urination through the analysis of the cat's behavior pattern from the home CCTV video and the weight sensor of the water bowl. And, through analysis of cat behavior patterns, we propose an application that reports disease prediction and abnormal behavior to the guardian and delivers it to the guardian's mobile and the main server system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.627-629
• /
• 2023

생체 신호를 분석하여 사용자의 건강과 정신 상태를 예측하고, 관련 질병에 관해 예방하는 연구가 늘어나고 있다. 생체 신호 중 심박은 사람의 육체, 정신적인 상태를 반영하는 대표적인 신호이지만 기존의 접촉 패드를 통한 ECG나 광학 센서를 통한 PPG로 심박을 예측할 때는 구속적인 환경이 필요하여 일상적인 상황 속에 적용하기 어려웠다. 이러한 단점을 해결하고자 본 논문은 UBFC-RPPG 데이터셋의 동영상 프레임을 RGB 채널마다 다른 가중치를 적용하는 전처리를 하여 학습 데이터의 크기를 줄이면서 정확도를 높이고, 3D-CNN을 활용한 딥러닝으로 순간적인 영상에서도 PPG 신호를 예측할 수 있도록 1초 전처리 영상을 학습한 후, 신호를 예측하는 것을 목표로 한다. 이렇게 비접촉식으로 취득된 신호는 더 다양한 환경에서의 감정분류, 우울증 진단, 질병 감지 등 다양한 분야에 활용될 수 있다.