• The korean journal of orthodontics
• /
• v.29 no.1 s.72
• /
• pp.1-22
• /
• 1999

As people are more concerned about their health and medical care, there have been an increasing number of medical disputes due to increased medical demand. In order to prevent and provide solution to currently surging medical accidents and disputes related to orthodontic treatment, in July 1998, the Korean Association Of Orthdontists surveyed 2,200 members of Korean Association of orthodontists on 30 items to recognize the pattern of medical accidents and prevent them. The survey was about accident-related items including personal profiles of members and patients who have undergone medical accidents or disputes, the cause and solution to the accidents, cautions related to members orthodontic treatment, and medical recording and archival. Based on the survey result, we analyzed characteristics of medical accidents and disputes in orthodontic area. It is more important to predict and prevent possible medical accidents or disputes based on current situation than to solve them after disputes occur. For this, we should not be negligent in raising treatment proficiency level based on patient-doctor trust and in obtaining new medical information. We should also provide medical environment where Patients themselves can decide whether to get treatment after they are offered detailed explanation on diagnosis, treatment procedure, complication, and possible hazard. We should take caution when treating patients and pay attention to charting and maintenance, which is the most fundamental, as well. Also at the Korean Association of orthodontists level, it is desired to provide education program on prevention and solution to medical accidents and disputes, and actions and organizations that can help when accidents and disputes occur.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• Journal of Preventive Medicine and Public Health
• /
• v.26 no.3 s.43
• /
• pp.457-468
• /
• 1993

This study was conducted to investigate the repeat test rate for diagnosis at a tertiary hospital for the outpatients who were referred themselves to the hospital by the clinics and other medical facilities. The study population consisted of 498 patients who visited outpatient department of internal medicine, general surgery, orthopedic surgery and neurosurgery in the hospital between March 16 and April 11, 1992. This study was surveyed by the questionnaire about the tests for diagnosis at first level medical facilities, and then, was investigated by the medical record about the tests for diagnosis at a tertiary hospital. The proportion of test among the patients who utilized the first level medical facilities was 20.9% for the X-ray test, 10.6% for the urinalysis, 9.0% for the electrocardiogram, 3.4% for the computer tomogram and 6.4% for the ultrasonogram. At the tertiary hospital, the X-ray test was 45.2%, the liver function test was 24.1%, the urinalysis was 19.1%, and the electrocardiogram was 15.7%. The proportion of patients who possessed results of test for diagnosis at the first level medical facilities was 76.5% for the computer tomogram, and 31.3% for the ultrasonogram. As the repeat test rate between the first level medical facilities and the tertiary hospital, the thyroid function test was the first rank as 71.4%, the second rank was the routine CBC as 67.9%, and the third rank was the X-ray test as 64.4%. But among the patients that brought the result for tests at the first level medical facilities, the repeat test rate was as follow : the routine CBC was 75.0%, the liver function test was 72.1%, and the computer tomogram was 15.4%.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2017.08a
• /
• pp.104-104
• /
• 2017

연구 데이터란 과학적 연구에서 사용된 일차 자료와 연구자에 의해 직접 작성된 연구의 결과로서 수치, 문자, 이미지, 음성 등의 사실적 기록을 의미한다. 이 연구의 주제 분야인 의학은 잠재적 가치와 활용 가능성이 높고 공익적 성격을 가지고 있는 학문 분야로 의학 연구 데이터의 종류와 관리의 필요성을 통해서 그 가치와 공유 의미를 찾아보고자 한다. 또한 연구 데이터의 대표적인 임상 시험 기록과 연구 논문의 발표와 공유 현황에 대해서도 살펴보고 그 안에서 도서관의 역할이 어떤 것인가를 짚어보고자 한다. 의학 연구 데이터는 환자 진료기록, 건강 검진 기록, 임상 기록, 사망 기록, 임상 시험 기록, 유전체 정보, 연구 논문 등 그 종류와 형태가 다양하며 대용량인 경우가 많다. 의학 연구는 개인 정보보호와 윤리적인 문제 등 연구 수행 과정에서 어려운 점이 많은 성격을 가지고 있으나 질병 치료나 예방 나아가 인류의 건강과 직접적으로 관련된 학문 분야로 의학 연구 데이터의 보존과 공개, 공유를 위한 관리는 큰 의미가 있다. 의학 연구 데이터관리는 새로운 연구의 밑받침이 될 뿐만 아니라 중 저개발 국가의 연구자들에게도 큰 기회를 부여하여 세계적인 의학 발전에 기여할 수 있다. 또한 임상 시험 결과에 대한 은폐와 거짓 연구 방지에도 의미가 있어 미국뿐만 아니라 전세계적으로 학술 연구 논문 발표에 사용된 데이터는 등록하도록 규정하고 있다. 임상 시험 등록으로 공인된 사이트는 NIH의 ClinicalTrials.gov, ICTRP의 Primary Registry 등이 있으며, 우리나라에도 질병관리본부 국립보건연구원에서 관리하는 CRIS 등이 있다. 의학 연구자들은 연구의 시작부터 연구 데이터를 수집, 사용, 보존, 공유의 문제를 고려해야 하나 시간적 물리적인 문제 등으로 어려움을 겪고 있으며, 이를 지원하는 서비스는 도서관에서도 관심이 높아지고 있는 분야로 Virginia Commonwealth 대학 도서관과 Emory 대학 도서관 등에서 시도되고 있다. 이 서비스는 연구 과정에서 사서의 지원이 가능한 새로운 기회로 연구자의 데이터관리를 위한 단계별 스토리를 조직하고 DMP 작성 지원 및 교육 등을 통해서 학술 커뮤니케이션에서 새로운 역할자로 자리잡을 수 있을 것이다.

• Journal of The Korean Dental Society of Anesthesiology
• /
• v.2 no.1 s.2
• /
• pp.21-26
• /
• 2002

연구배경: 장애인의 치과치료는 일반인의 치과치료와는 달리 많은 문제점들을 가지고 있다. 이러한 장애인 환자의 치과치료를 위하여 서울대학교 치과병원에서는 치과마취과를 중심으로 임상 각과가 협진하여 외래마취 기반 하에 1999년부터 장애인 진료실을 운영하고 있다. 이번 연구에서는 서울대학교 치과병원 장애인 진료실의 치료방법을 소개하고 그 동안 치료받은 장애인 환자들의 자료를 바탕으로 마취과적인 특징을 분석하였다. 방법: 2001년 1월부터 2002년 5월까지 치료받은 총 54명의 장애인 환자들의 치료기록지와 마취, 그리고 회복실 기록지를 검토하였다. 환자의 성별, 나이, 전신질환, 수술 전 시행된 검사, 치료에 참여한 협진과, 마취 유도제와 유지제, 총 마취시간과 회복실 체류시간, 그리고 회복실에서 관찰된 합병증을 조사하였다. 결과: 총 54명의 환자들을 대상으로 58건 치과치료가 시행되었다. 한 건의 의식진정 법을 제외하고는 모두 전신마취 하에서 치과치료가 시행되었다. 마취유도제는 thiopental sodium, 근이완제는 vecuronium과 succinylcholine가 가장 많이 사용되었으며 마취 유지를 위해서는 enflurane과 isoflurane의 흡입마취제를 이용하거나 TCI를 이용한 propofol 지속정주를 이용하였다. 총 마취지속시간은 $160.2{\pm}55.5$분이었으며 회복실에서의 체류시간은 $132.8{\pm}50.1$분, 그리고 완전한 회복을 확인하기 위해 병동에 단기 입원시킨 소아환자에서는 $58.7{\pm}16.8$분이었다. 회복실에서 심각한 합병증은 발생하지 않았다. 지속적인 감시를 위하여 4명의 환자가 입원을 권유받았으나 특별한 합병증 없이 다음 날 퇴원하였다. 결론: 서울대학교 치과병원 장애인 진료실은 외래마취에 대한 기존의 연구들보다 긴 마취시간과 회복실 체류시간을 보였다. 그러나 별다른 합병증 없이 일회 방문으로 장애인 환자들에게 필요한 치과치료를 모두 제공할 수 있었다.

• Journal of Korean Medical classics
• /
• v.24 no.1
• /
• pp.1-14
• /
• 2011

Background : Much Opinions of inefficiency to put the standard term of oriental medicine in and around literature into medical records. Purpose : Suggest an alternative according to analysis of differences between 'Term System' from in and around literature and term of medical records. Method : Research on the difference according to analysis of difference between producing term from in and around literature using DB Program and term from medical records. Result : The best System is that reflecting 'Korean Expression' of term of oriental medicine and part of term of western medicine and general.

• Annual Conference of KIPS
• /
• 2012.04a
• /
• pp.916-919
• /
• 2012

EMR(Electronic Medical Records) 시스템은 기존의 의무 기록을 전산화 한 것으로 의료 서비스 시용자의 신체정보 및 진료정보 등을 전산화 하여 저장하는 시스템이다. 노령화 사회로 들어서게 되면서 많은 의료 소비자들이 의료 서비스 기관들에 발걸음이 잦아지고 각 환자마다 늘어나게 될 데이터를 좀 더 효율적으로 관리할 수 있는 EMR의 필요성이 대두되고 있다. 본 논문은 현재 IT트렌드의 흐름을 살펴보고 의료 정보 기술과 접목한 새로운 차세대 EMR 기술을 분석하고 그 발전 방향을 제시하고자 한다.

• Information Systems Review
• /
• v.15 no.2
• /
• pp.41-58
• /
• 2013

The purpose of the present study is to theoretically assess IT Implementation Model of Cooper and Zmud (1990) in a hospital IS use context. A case study was applied to analogical study by interview from several end-users of the information systems at a university hospital. This study presented an EMR(Electronic Medical Record) systems how is initially implemented at an initial stage, continually adopted, adapted, accepted at an adoption stage, and finally rountinized and infused into an organization. Our study also elaborated IT Implementation Model as defining EMR development and its impact on nature of IS use in a hospital. This case study explained the characteristics of EMR and hospital organization context conceptually.

• Journal of Oral Medicine and Pain
• /
• v.34 no.1
• /
• pp.63-79
• /
• 2009

While previous epidemiological studies on temporomandibular disorders (TMD) have been based on a given health center or population sample, no study has been performed on general population of Korea, especially concerning about treatment pattern such as clinician’s specialty involved in TMD treatment, types and amount of prescription medication and cost. This study aimed to investigate magnitude of health visits and treatment patterns for Korean patients with TMD through the computerized database of Health Insurance Review and Assessment Service (HIRAS). Inclusion criteria were all patients registered on the HIRAS database over 3 years' period from 2003 to 2005 and the medical records of patients with TMD as a main diagnosis were extracted. Information collected was as follows; distribution related to gender, age and region and type of hospital the patients visited, treatment duration, clinicians' specialty involved in treatment, cost, types of prescription medication and surgical treatment. The results of this study indicated that 0.15% of the population yearly sought TMD treatment, presenting with increase of incidence over the three years. Most of TMD patients were women (99.8%) and the biggest age group was second and third decades and decreased with age. Seoul and Kyeonggi province presented with higher incidence of TMD compared to the other regions of Korea, which seems to be related with magnitude of population. 56% of TMD patients visited primary care sector and the numbers of treatment visits was the highest in dental clinic (38.4%), followed by orthopedics (28%) and ENT (13.6%) clinics in order. Duration of prescription medication was the longest for anti-inflammatory analgesics, followed by antipsychotic drugs and muscle relaxants. Inpatient care related to TMD was primarily performed in dental hospital compared to medical hospital. Medical database of HIRAS provided comprehensive and vast information on epidemiologic characteristics and treatment patterns for patients seeking TMD treatment, which can be more reliable data to expect medical demand for TMD in condition that accurate diagnosis and standardized treatment is delivered in clinical settings.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.2
• /
• pp.27-34
• /
• 2010

Recently, lots of internet service companies provide on-line health diagnosis systems. But general persons not having expert knowledge are difficult to use, because most of the health diagnosis systems present prescriptions or dietetic treatments for diseases based on western medicine. In this paper, a self health diagnosis system of oriental medicine coinciding with physical characteristics of Korean using fuzzy ART algorithm, is proposed. In the proposed system, three high rank of diseases having high similarity values are derived by comparing symptoms presented by a user with learned symptoms of specific diseases based on treatment records using neural networks. And also the proposed system shows overall symptoms and folk remedies for the three high rank of diseases. Database on diseases and symptoms is built by several oriental medicine books and then verified by a medical specialist of oriental medicine. The proposed self health diagnosis system of oriental medicine showed better performance than conventional health diagnosis systems by means of learning diseases and symptoms using treatment records.