• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2003년도 추계학술발표논문집 (중)
• /
• pp.833-836
• /
• 2003

본 논문에서는 생물학적 문헌으로부터 유의미한 정보를 추출하는 바이오 텍스트 마이닝의 기본 단계인 생물학적 개체명 인식 모델을 제안하였다. 기존의 생물학적 개체명 인식은 규칙 혹은 코퍼스 구축뿐만 아니라 개체명 인식에 요구되는 기본 자원을 구축하는데만도 많은 시간과 비용이 요구되므로 한정된 도메인을 대상으로 연구가 진행되어 왔다. 본 논문에서 제안하는 개체명 인식 방법은 이러한 비용 문제 및 새로운 도메인으로의 이식성 문제를 극복하기 위해 UMLS 로부터 통계적인 방법으로 정보를 추출해 기본적인 언어자원을 구축하고 이를 이용해 규칙을 생성함으로써 개체명인식을 수행한다. 본 연구에서 제안하는 방법은 바이오 텍스트 마이닝 연구의 도메인 한정적인 문제를 해결하는데 기여할 수 있을 것으로 기대된다.

• 정보관리학회지
• /
• 제21권3호
• /
• pp.141-160
• /
• 2004

최근 의학정보 분야에서는 임상의 지식관리와 의학정보 검색의 효율화를 위한 수단으로 온톨로지의 개념 모델링을 이용한 의학용어 시스템에 관심이 모아지고 있다. 본 연구는 우리나라의 의학정보 분야에 이러한 시스템의 응용이나 새로운 시스템 개발애 기초적인 자료제공을 목적으로 , 정보 모델링과 온톨로지의 이론에 대해 고찰하였고, 외국의 의학정보 분양에서 온톨로지를 이용한 용어 시스템이 개발된 4가지 대표적인 사례를 분석하여 비교하였다. 연구결과 비형식적인 수준의 온톨로지로 파악된 MeSH의 의학용어 표준화와 UMLS의 용어 개념화, 형식적인 수준의 온톨로지인 ON9의 의학 온톨로지 통합의 이론화, 그리고 GALEN의 의학지식의 의미 모델과 형식화로 핵심적 특징을 요약할 수 있었다. 온톨로지의 응용은 목적하는 시스템에 따른 수준적 차별화가 이루어져야 하 것이고, 본 연구의 분석 결과가 참고 될 수 있을 것이다.

• 한국한의학연구원논문집
• /
• 제18권3호
• /
• pp.133-139
• /
• 2012

Objective : UMLS is 'Ontology' which establishes the database for medical terminology by gathering various medical vocabularies representing same fundamental concepts. Method : Although Chinese character are represented in the Chinese part of Korean Unicode system in a computer, writing of Chinese characters is vary depending on Chinese input systems and Chinese writers' levels of knowledge. As the result of this, representation of Chinese writing in a computer will be considerably different from an old Chinese document. Therefore, a meaningful relationship between digital Chinese terminology and translated Korean is necessary in order to build Ontology for Chinese medical terms from Oriental medical prescription in a computer system. Result : This research will present 1:1 mapping information among the Chinese characters used in the Oriental medical prescription with analysis of 'same character different sound' and 'same meaning different shape' in Chinese part of Unicode systems. Conclusions : Furthermore, the research will provide top-down menu of relationship between Chinese term and Korean term in medical prescription with assumption of that the Oriental medical prescription has its own unique meaning.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권1호
• /
• pp.35-40
• /
• 2022

본 논문에서는 임상 의사 결정 지원을 위하여 의학 지식을 통해 임상 관계를 추출하고 딥러닝 모델을 이용하여 질병을 예측하는 방법을 제안한다. 의학 사전인 UMLS(Unified Medical Language System)와 암 관련 의학 지식에 포함된 임상 용어를 5가지로 분류한다. 분류된 임상 용어들을 사용하여 위키피디아 의학 문서를 추출한다. 추출한 위키피디아 의학 문서와 추출한 임상 용어를 매칭하여 임상 관계를 구축한다. 구축한 임상 관계를 이용하여 딥러닝 학습을 진행한 후 질의에서 표현된 의학 용어를 바탕으로 질의와 연관된 질병을 예측한다. 이후, 예측한 질병과 관계가 있는 의학 용어를 확장 질의로 선택한 뒤 질의를 확장한다. 제안 방법의 유효성을 검증하기 위해 TREC Clinical Decision Support(CDS), TREC Precision Medicine(PM) 테스트 컬렉션에 대해 비교 평가한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 컴퓨터소사이어티 추계학술대회논문집
• /
• pp.129-132
• /
• 2003

The metathesaurus(UMLS, 2003AA edition) supports multi language and includes 875, 233 concepts, 2, 146, 897 concept names. It is impossible for PubMed or NLM serve searching of the metatheaurus to retrieval using a query that is not to be text, a fault sentence structure or a part of concept name. That means the user notice correctly suitable medical words in order to get correct answer, otherwise she or he can't find information that they want to find I propose that the method of searching unified medical language system using automatic modified a query for problem that I mentioned. This method use dictionary that is standard for automation of modified query gauge similarity between query and dictionary using string comparison algorithm. And then, the tested term converse the form of metathesaurus for optimized result. For the evaluation of method, I select some query and I contrast NLM method that renewed Aug. 2003.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2010년도 추계학술발표대회
• /
• pp.465-465
• /
• 2010

A controlled medical vocabulary is a vital component of medical information management because it enables computers to use information meaningfully and different institutions to share the medical data. There are currently many standard medical vocabularies - SNOMED-CT, ICD-10, UMLS, GALEN, MED, etc, but none is universally accepted as an optimal controlled medical vocabulary for application to medical information system. Moreover, it is difficult to settle the well-designed local data dictionary consisting of controlled medical vocabularies for the individual hospital information system (HIS). One of the major reasons is the local terminology with poor contents have been used in the hospital. Thus, as a trial, the local controlled vocabulary referencing system has being constructed in a limited medical field - nuclear medicine. We selected practical nuclear medicine terms from interpretation reports and electronic medical records, and removed ambiguity and redundancy, mapping the selected terms to standard medical vocabularies. Relationship and hierarchy structure between terms have being made, referring to standard medical vocabularies. Further studies may be warranted.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권4호
• /
• pp.881-902
• /
• 2024

Fast decision support systems and accurate diagnosis have become significant in the rapidly growing healthcare sector. As the number of disparate medical IoT devices connected to the human body rises, fast and interrelated healthcare data retrieval gets harder and harder. One of the most important requirements for the Healthcare Internet of Things (HIoT) is semantic interoperability. The state-of-the-art HIoT systems have problems with bandwidth and latency. An extension of cloud computing called fog computing not only solves the latency problem but also provides other benefits including resource mobility and on-demand scalability. The recommended approach helps to lower latency and network bandwidth consumption in a system that provides semantic interoperability in healthcare organizations. To evaluate the system's language processing performance, we simulated it in three different contexts. 1. Polysemy resolution system 2. System for hyponymy-hypernymy resolution with polysemy 3. System for resolving polysemy, hypernymy, hyponymy, meronymy, and holonymy. In comparison to the other two systems, the third system has lower latency and network usage. The proposed framework can reduce the computation overhead of heterogeneous healthcare data. The simulation results show that fog computing can reduce delay, network usage, and energy consumption.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2006년도 Principles and Practice of Microarray for Biomedical Researchers
• /
• pp.30-36
• /
• 2006

Tissue microarray (TMA) is an array-based technology allowing the examination of hundreds of tissue samples on a single slide. To handle, exchange, and disseminate TMA data, we need standard representations of the methods used, of the data generated, and of the clinical and histopathological information related to TMA data analysis. This study aims to create a comprehensive data model with flexibility that supports diverse experimental designs and with expressivity and extensibility that enables an adequate and comprehensive description of new clinical and histopathological data elements. We designed a Tissue Microarray Object Model (TMA-OM). Both the Array Information and the Experimental Procedure models are created by referring to Microarray Gene Expression Object Model, Minimum Information Specification For In Situ Hybridization and Immunohistochemistry Experiments (MISFISHIE), and the TMA Data Exchange Specifications (TMA DES). The Clinical and Histopathological Information model is created by using CAP Cancer Protocols and National Cancer Institute Common Data Elements (NCI CDEs). MGED Ontology, UMLS and the terms extracted from CAP Cancer Protocols and NCI CDEs are used to create a controlled vocabulary for unambiguous annotation. We implemented a web-based application for TMA-OM, supporting data export in XML format conforming to the TMA DES or the DTD derived from TMA-OM. TMA-OM provides a comprehensive data model for storage, analysis and exchange of TMA data and facilitates model-level integration of other biological models.

• Journal of Information Science Theory and Practice
• /
• 제3권1호
• /
• pp.6-23
• /
• 2015

This study develops an effective method for sentiment analysis of user-generated content on drug review websites, which has not been investigated extensively compared to other general domains, such as product reviews. A clause-level sentiment analysis algorithm is developed since each sentence can contain multiple clauses discussing multiple aspects of a drug. The method adopts a pure linguistic approach of computing the sentiment orientation (positive, negative, or neutral) of a clause from the prior sentiment scores assigned to words, taking into consideration the grammatical relations and semantic annotation (such as disorder terms) of words in the clause. Experiment results with 2,700 clauses show the effectiveness of the proposed approach, and it performed significantly better than the baseline approaches using a machine learning approach. Various challenging issues were identified and discussed through error analysis. The application of the proposed sentiment analysis approach will be useful not only for patients, but also for drug makers and clinicians to obtain valuable summaries of public opinion. Since sentiment analysis is domain specific, domain knowledge in drug reviews is incorporated into the sentiment analysis algorithm to provide more accurate analysis. In particular, MetaMap is used to map various health and medical terms (such as disease and drug names) to semantic types in the Unified Medical Language System (UMLS) Semantic Network.

• Journal of Computing Science and Engineering
• /
• 제2권2호
• /
• pp.109-136
• /
• 2008

In this survey paper, we discuss biomedical ontologies and major text mining techniques applied to biomedicine and healthcare. Biomedical ontologies such as UMLS are currently being adopted in text mining approaches because they provide domain knowledge for text mining approaches. In addition, biomedical ontologies enable us to resolve many linguistic problems when text mining approaches handle biomedical literature. As the first example of text mining, document clustering is surveyed. Because a document set is normally multiple topic, text mining approaches use document clustering as a preprocessing step to group similar documents. Additionally, document clustering is able to inform the biomedical literature searches required for the practice of evidence-based medicine. We introduce Swanson's UnDiscovered Public Knowledge (UDPK) model to generate biomedical hypotheses from biomedical literature such as MEDLINE by discovering novel connections among logically-related biomedical concepts. Another important area of text mining is document classification. Document classification is a valuable tool for biomedical tasks that involve large amounts of text. We survey well-known classification techniques in biomedicine. As the last example of text mining in biomedicine and healthcare, we survey information extraction. Information extraction is the process of scanning text for information relevant to some interest, including extracting entities, relations, and events. We also address techniques and issues of evaluating text mining applications in biomedicine and healthcare.