• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1667-1676
• /
• 2006

다른 산업과 달리 병원/의료 산업에서는 건강 보험료 심사 평가라는 독특한 검증 과정이 필수적으로 있게 된다. 건강 보험료 심사 평가는 병원의 수익 문제 뿐 아니라 적정한 진료행위를 하는 병원이라는 이미지와도 맞물려 매우 중요한 분야이며, 특히 대형 종합병원일수록 이 부분에 많은 심사관련 인력들을 투입하여, 병원의 수익과 명예를 위해서 업무를 수행하고 있다. 본 논문은 이러한 건강보험료 청구 심사 과정에서, 사전에 수많은 진료 청구 건 중 심사 평가에서 삭감이 될 수 있는 진료 청구 건을 데이터 마이닝을 통해서 발견하여, 사전의 대비를 철저히 하고자 하는 한 국내의 대형 종합병원의 사례를 소개하고자 한다. 데이터 마이닝을 적용함에 있어, 주요한 문제점 중의 하나는 바로 지도학습 기법을 적용하기에 곤란한 데이터 불균형 문제가 발생하는 것이다. 이런 불균형 문제를 해소하고, 비교 조건 중에 가장 효율적인 삭감 예상 진료 건 탐지 모형을 만들어 내기 위하여 데이터 불균형 문제의 기본 해법인 과, Sampling 오분류 비용의 다양하고 혼합적인 적용을 통하여, 적합한 조건을 가지는 의사결정 나무 모형을 도출하였다.

• Health Policy and Management
• /
• v.34 no.2
• /
• pp.163-177
• /
• 2024

Background: This study aims to examine changes in fraudulent claim counts and total reimbursements before and after enhancements in counterfeit claim controls and monitoring of provider claim patterns under the "Proactive self-audit pilot program of fraudulent claims." Methods: This study used the claims data and hospital information (July 2021-February 2022) of the Health Insurance Review and Assessment Service. The data was collected from 1,129 hospitals assigned to the pilot program, selected from the providers who filed a claim for reimbursement for intravenous injections. Paired and independent t-tests, along with regression analysis, were utilized to analyze changing patterns and factors influencing claim behaviors. Results: This program led to a reduction in the number of fraudulent claims and the total amount of reimbursements across all levels of hospitals in the experimental groups (except for physicians below 40 years old). In the control group, general hospitals and hospitals demonstrated some significant decreases based on the duration since opening, while clinics showed significant reductions in specified subjects. Additionally, a notable increase was observed among male physicians over the age of 50 years. Overall, claims and reimbursements significantly declined after the intervention. Furthermore, a positive correlation was found between hospital opening duration and claim numbers, suggesting longer-established hospitals were more likely to file claims. Conclusion: The results indicate that the pilot program successfully encouraged providers to autonomously minimize fraudulent claims. Therefore, it is advised to extend further support, including promotional activities, training, seminars, and continuous monitoring, to nonparticipating hospitals to facilitate independent improvements in their claim practices.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2023

Research using AI and big data is also being actively conducted in the health and medical fields such as disease diagnosis and treatment. Most of the existing research data used cohort data from research institutes or some patient data. In this paper, the difference in the prediction rate of survival and the factors affecting survival between breast cancer patients in their 40~50s and other age groups was revealed using health insurance review claim data held by the HIRA. As a result, the accuracy of predicting patients' survival was 0.93 on average in their 40~50s, higher than 0.86 in their 60~80s. In terms of that factor, the number of treatments was high for those in their 40~50s, and age was high for those in their 60~80s. Performance comparison with previous studies, the average precision was 0.90, which was higher than 0.81 of the existing paper. As a result of performance comparison by applied algorithm, the overall average precision of Decision Tree, Random Forest, and Gradient Boosting was 0.90, and the recall was 1.0, and the precision of multi-layer perceptrons was 0.89, and the recall was 1.0. I hope that more research will be conducted using machine learning automation(Auto ML) tools for non-professionals to enhance the use of the value for health insurance review claim data held by the HIRA.

• Journal of Digital Convergence
• /
• v.11 no.9
• /
• pp.289-299
• /
• 2013

The aim of this study was to enhance the NHI claims data-based tuberculosis classification rule of KCDC(Korea centers for disease control & prevention) for an effective TB surveillance system. 8,118 cases, 10% samples of 81,199 TB cases from NHI claims data during 2009, were subject to the Medical Record Survey about whether they are real TB patients. The final study population was 7,132 cases whose medical records were surveyed. The decision tree model was evaluated as the most superior TB patients detection model. This model required the main independent variables of age, the number of anti-tuberculosis drugs, types of medical institution, tuberculosis tests, prescription days, types of TB. This model had sensitivity of 90.6%, PPV of 96.1%, and correct classification rate of 93.8%, which was better than KCDC's TB detection model with two or more NHI claims for TB and TB drugs(sensitivity of 82.6%, PPV of 95%, and correct classification rate of 80%).

• 대한예방의학회:학술대회논문집
• /
• 1999.10a
• /
• pp.27-28
• /
• 1999

• 한국노년학
• /
• v.29 no.2
• /
• pp.645-656
• /
• 2009

The purpose of this study was to address the current status of hospital-based home care(HBHC). We analyzed the data on HBHC from national electronic data information of Health Insurance Review Agency. Beside, we surveyed 75 hospital-based home care agency. In 2006, 20,343 elderly(64.0% from all HBHC user) used 333,889 visits(76.8%from all visits). Medical diagnosis was composed of circulatory disease including cerebrovascular diseases 41.3%, endocrine system disease including Diabetes mellitus 10.4%, neoplasm 9.7%. Some of subjects used HBHC in excess of maximum covered 8 visits a month by National Health Insurance, decubitus 7.0%, the cancer 5.4%, the diabetes 2.5%, the hypertension 1.1%, and the stroke 0.9%. This results will contribute to expand the coverage of hospital-based home care by National Health Insurance. There was distribution difference in medical diagnosis and nursing intervention between HBHC and Public health center-based home care(PBHC) subjects. Therefore, HBHC subjects had more severe medical diagnosis, and were intervened more injections, examinations, than PBHC subjects. These differences must be considered to set up functional role among the three types of home visit care.

• Journal of Digital Convergence
• /
• v.16 no.12
• /
• pp.533-540
• /
• 2018

The purpose of this study was to use the data from the Health Insurance Review and Assessment Service to analyze the disagreement in disease coding given by different medical institutions on the same disease of the same patient and provide basic data that could help improve the quality of national public health statistics. 9,976,826 patients' data records from the Health Insurance Review and Assessment Service-National Patient Sample (HIRA-NPS) of 2014 were analyzed. The disagreement in disease coding differed by movement paths for medical institutions; the disagreement rate tended to increase when moving from a medical institution other than public health centers to a public health center and decrease remarkably when moving from a specialized general hospital to another. Therefore, this analysis of disagreement in disease coding among medical institutions suggests the need to supplement the system so that domestic medical institutions can realize consistent disease coding.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2008.10a
• /
• pp.342-345
• /
• 2008

산재 발생 시 산재근로자는 근로복지공단을 통해서 각종 급여를 받게 된다. 본 논문은 심사 과정과 급여지급 후에 부정수급으로 판명된 산재 청구 건을 데이터 마이닝을 통해서 분석하여 부정수급의 유형을 발견하고자 한다. 이 연구에서는 서울관내 4개 지사에서 8년 동안(2000년$\sim$2007년)의 총 61,536명의 최초요양 신청을 한 산재근로자 자료를 대상으로 하였고, 종속변수에 영향을 미치는 8개의 독립변수를 선택해서 사용한다. 데이터 마이닝을 적용함에 있어서 가장 효율적인 허위 부정 탐지 모델을 만들기 위해 의사결정나무분석(Decision Tree)과 로지스틱 회귀분석(Logistic Regresion)등의 다양한 기법을 적용하여 결과를 비교분석 하고, 오분류 비용을 적용하여, 최적의 분류결정 값을 가지는 모델을 도출한다. 분석결과, 로지스틱 회귀분석이 산재보험 부정수급 유형 발견에 보다 효과적인 모델로 판명되었다. 또한 판별점(Cut-Off) 0.01로 했을 때 4개변수(요양기간, 업종형태, 의료기관, 재해발생형태)가 부정수급에 탐지하는데 영향력이 큰 변수로 선정되었다.

• Health Policy and Management
• /
• v.34 no.1
• /
• pp.38-47
• /
• 2024

Background: Korea's population of children and adolescents has decreased by 2.88 million over the past decade and is expected to decline further due to the unprecedented low birth rate. In the fee-for-service compensation system, the decline in the pediatric population relates directly to the profit decrease in the pediatric clinics. This study analyzed whether the worsening profits of pediatric clinics impacted their closure. Methods: We built annual data for pediatric and other department clinics (internal medicine, otolaryngology, and family medicine) using the status of medical institute and health insurance claims data from 2012 to 2022. Then, we analyzed whether institutional variables such as annual profit and regional variables (Herfindahl-Hirschman index, the number of clinics per 100,000, etc.) affected the closure of clinics. The methods used in this study are descriptive statistics and chi-square analysis. Odds ratios for each variable were estimated by generalized estimating equations (GEE). Results: The closure rate of pediatric clinics was 2.66%-7.04% in 2012-2022, which was consistently higher than those of internal medicine, otolaryngology, and family medicine clinics. The profit gap per institution between the pediatric and the other clinics grew from 126 million won in 2012 to 245 million won in 2019. In the GEE analysis, profit decrease compared to the previous year with lower profit was the main factor that increased the closure of pediatric and other department clinics. After adjusting profit-related variables, the decrease in the pediatric population itself did not relate to the closure of pediatric clinics. The number of pediatric clinics or monopolies also did not affect the closure of pediatric clinics. Conclusion: The worsening profit is the crucial factor for the closure of pediatric clinics, while the pediatric population is decreasing. For this reason, it is necessary to actively seek ways to maintain a stable treatment system for children and adolescents.

• The Inventors News
• /
• no.53
• /
• pp.1-16
• /
• 2006

'여성기업지원에 관한 법률' 개정 한 목소리/발행인 칼럼/'제4회 여성발명경진대회' 수준 높아졌다/심사착수 예정시기 직접 통지 서비스 실시/특허청.한국기계연구원, 업무협약체결/낙도어린이들에게 꿈과 희망 심어주는 초청 행사 가져/특허청 팀장 선발 방식 변화 통한 팀제 강화/디자인 권리화 지원사업 실시한다/'DMB 특허품과 지재권전략 세미나'/'2006 독일 국제발명품 전시회' 회원 4명 수상/고성능 하이브리드 보호복, 출원 증가/'이달의 기능 한국인' 박순복 씨 선정/모방상표, 더 이상 등록 받을 수 없다/국내제약업계, 유사브랜드 너무많아/'2006 여성 재활용 발명경진대회' 개최/순수 한방재료로 만든 헤어 클리닉 화제/발명자에게 편리한 특허제도 마련/차로 마시는 '허브 추출물'로 살충제 만들어/종이컵에도 웰빙 바람이 불고 있다/특허공보 통해 '나의 발명' 확인가능/지역특산품도 지리적 표시로 보호 받는다/한미약품,'비만치료제 특허권 분재' 연승/국내특허, 해외에서 신속하게 심사 처리/'스판덱스 특허소송'에서 일본업체 패소/아모레, 다국적 화장품회사 로레알에 승소/제7차 한국.유럽 특허청장 회담 개최/고부가가치 창출하는 단백질 의약품 개발 필요/한방 진료에도 변화의 새바람 분다/에너지 절감'기능성 유리' 출원 급증/역사 속의 발명품/하루 10분 발명교실/특허Q&A/세상을 밝히는 여성들의 발명 아이디어/'특허넷' 정부기관 최초 CMMI 레벨4인증 획득/'해외지재권 보호 가이드북' 제작배포하다/아이디어 착상 및 발명 기법/고정관념을 깨트려 블루오션을 장악하라/에반스의 증기제분기/50년 후엔 동물과도 대화할 수 있다/첩보용 도구 전달 '발명팀' 실제 존재/중소기업 위한'2006 특허유통 페스티벌' 개최/출원료.심사청구료 반환제도 도입, 시행/'지재권 e-러닝 콘텐츠' 전 세계특허청 교육 자료로 활용/대한변리사회, 미 특허법 세미나 개최/한국여성발명협회 회원사 발명품 가이드