Prospect of Artificial Intelligence Based on Electronic Medical Records

Lee Suehyun,Kim Hun-Sung 한국지질동맥경화학회 2021 지질·동맥경화학회지 Vol.10 No.3

With the advent of the big data era, the interest of the international community is focusing on increasing the utilization of medical big data. Many hospitals are attempting to increase the efficiency of their operations and patient management by adopting artificial intelligence (AI) technology that enables the use of electronic medical record (EMR) data. EMR includes information about a patient's health history, such as diagnoses, medicines, tests, allergies, immunizations, treatment plans, personalized medical care, and improvement of medical quality and safety. EMR data can also be used for AI-based new drug development. In particular, it is effective to develop AI that can predict the occurrence of specific diseases or provide individualized customized treatments by classifying the individualized characteristics of patients. In order to improve performance of artificial intelligence research using EMR data, standardization and refinement of data are essential. In addition, since EMR data deal with sensitive personal information of patients, it is also vital to protect the patient's privacy. There are already various supports for the use of EMR data in the Korean government, and researchers are encouraged to be proactive.

경영학 수업에서의 문제기반학습(PBL) 적용 실행연구: 마케팅 교과목을 중심으로

이수현(Lee, Suehyun) 한국열린교육학회 2019 열린교육연구 Vol.27 No.4

본 연구에서는 마케팅 PBL 수업프로그램을 개발하고, <소비자 행동>, <마케팅 원론>, <마케팅 커뮤니케이션> 등 3개 교과목 적용과정에서의 4년간의 실행연구(action research)를 통해 개선, 완성하였다. 완성된 프로그램은 3가지 특징을 갖는다. 첫째, 마케팅 교과목의 학습 내용이 많은 편임을 고려하여, ‘강의 중심 학습’과 ‘문제기반학습’을 적절히 조합하였다. 둘째, 문제기반학습은 2개의 연계된 PBL 문제(모듈)로 구성하되, 팀별로 선택 가능한 하위 문제들을 제시함으로써 팀 간의 협동학습이 원활히 이루어지도록 하였다. 셋째, 효과적인 온라인 팀미팅 방법, 아이디에이션 도구 활용방법 등 팀 프로젝트 운영 에 도움을 주는 강의와 스마트 워크플레이스 구현을 위한 아이디에이션 세션을 제공함으로써 팀 프로젝트 협동학습이 원활히 이루어지도록 하였다. 완성된 PBL 수업프로그램은 강의평가 결과가 두 학기 연속단과대학 1위일 정도로 수강생 만족도가 매우 높은 것으로 나타났다. In this study, Marketing PBL instruction programs were developed, improved and completed through four years of action research in the application process of three subjects: Consumer Behavior, Principles of Marketing, and Marketing Communication. The completed program has three characteristics; First, lecture-based learning and problem-based learning are appropriately combined in consideration of the fact that there is usually a lot of learning content in marketing courses. Second, problem-based learning is composed of two linked PBL problems (modules), but the cooperative learning between teams is facilitated by presenting diverse sub-problems that can be selected for each team. Third, cooperative learning for team projects was facilitated by providing lectures to help improve team project management such as effective online team meeting methods and the use of ideation tools, and by providing ideation sessions to implement a smart workplace. The satisfaction level of students of PBL classes was very high: The lecture evaluations of the final two PBL classes – 2nd semester in 2018 and 1st semester in 2019 – were ranked first place among all courses provided by the School of Business.

삶의 중요한 일부로서의 스마트폰: 직장인·대학생 대상 설문조사와 여자대학생 대상 현장연구

이용숙(Lee, Yongsook),이수현(Lee, Suehyun) 서울대학교 비교문화연구소 2019 비교문화연구 Vol.25 No.1

이 연구에서는 대학생과 20~40대 직장인 500명의 스마트폰사용을 설문조사를 통해 연령대별/성별로 살펴본 후, 여자대학생에 중점을 두어 스마트폰이 어떻게 이들의 삶의 중요한 일부가 되고 있는지 논의했다. 연구자 2명과 연구보조원 36명이 자신과 주변인의 스마트폰 사용방식을 참여관찰하고, 80여 명과의 심층면담과 4회의 FGI를 실시했다. 스마트폰과 가장 밀착된 삶을 사는 것으로 나타난 여자대학생들은 57%가 하루 5시간 이상 스마트폰을 사용했다. 스마트폰사용으로 소요시간이 늘어난 활동은 취미생활, 쇼핑/관련정보검색, SNS, 사진찍기 등이고, 줄어든 활동은 혼자서 생각하기, 독서, 가족/친구와 함께하기, 교육/학습활동 등이다. 이들은 스마트폰을 ‘필수품’으로 여기고, ‘친구’, ‘일상/생활’, ‘또 하나의 나’ 등의 의미를 부여했다. 한편 이들은 ‘무의식적’으로나 ‘재미/현실도피’를 위해 스마트폰을 과다사용한다고 느꼈으며, SNS에 게시할만한 사진을 찍고 친구의 게시물에 반응을 보여야 하며 연락에 즉시 답해야 한다는 스트레스를 받았다. 스마트폰의 편의성/휴대성/즉각성은 사용자의 삶을 스마트폰 중심으로 개편시키고 있었다. This study examined the smartphone usage of college students and workers in their 20s, 30s and 40s. We discussed how smartphones are becoming an important part of their lives, focusing on female college students who tend to spend the most time on smartphones. For that purpose, three types of studies were conducted: 1) A questionnaire survey with 500 participants, 2) participant observation by two researchers and 36 research assistants who focused on their own smartphone usage as well as the smartphone usage of their friends/family members and 3) in-depth interviews with 80 college students and 4 focus group interviews at a coed university. The research found that female college students tend to use their smartphones much more than male college students and workers. Indeed, 57% of female college students used smartphones more than five hours a day. Activities that showed an increase in terms of time consumption due to smartphone usage were 1) hobbies, 2) shopping, 3) social media, 4) taking pictures and 5) travelling/searching for travel-related information. Using smartphones led to less time spent on the following activities: 1) thinking alone, 2) reading, 3) spending time with family or friends and 4) education/learning activities. College students felt anxious without their smartphones and considered them a necessity. Moreover, many gave meaning and value to their smartphones labelling them a ‘friend’, an ‘everyday life companion’, and ‘another self’. At the same time, however, students were found to be stressed because of their excessive use of smartphones. They felt that they were spending too much time on their smartphones either ‘unconsciously’, ‘for fun’ or ‘for escape.’ In particular, ‘SNS applications’, often used for ‘killing time’, and ‘communication applications’, which put students under pressure for ‘immediate reply’, were the top two causes of smartphone-related stress. This study found that the convenience, mobility and the spontaneity of smartphones deeply influenced the lifestyles of their users. Socio-structural causes of the excessive use of smartphones were further discussed in the study.

소셜 네트워크 서비스의 데이터를 활용한 약물재창출 단서 추출 파이프라인 연구

이원균 ( Wongyun Lee ),이승희 ( Seunghee Lee ),김종엽 ( Jong-yeup Kim ),이수현 ( Suehyun Lee ) 한국보건정보통계학회 2023 보건정보통계학회지 Vol.48 No.2

Objectives: In this study, we intend to propose a network analysis-based pipeline for drug repositioning using social network service data. Methods: We collected and analyzed 778 final posts on Cozaar-tab, a representative antihypertensive drug, from posts (2008-2022) of Naver Cafe, the largest social channel in Korea. For the analysis, we defined three filter dictionaries of the Cozaar-tab based on WHO-ART, an international classification system for drug side effects, and completed a network map by visualizing the extracted keywords. Results: We discussed to prepare evidence for drug repositioning from Cozaar-tab’s unexpected keyword ‘drowsiness’ to sleep inducing agent. Conclusions: Although this process is a narrow pipeline performance for a specific drug, it is expected to contribute to laying the foundation for data-based drug repositioning by supplementing it through clinical off-label review, additional data acquisition, and network analysis advancement in the future.

Polypharmacy and Elevated Risk of Severe Adverse Events in Older Adults Based on the Korea Institute of Drug Safety and Risk Management-Korea Adverse Event Reporting System Database

Kim Grace Juyun,Lee Ji Sung,Jang Sujung,Lee Seonghui,Jeon Seongwoo,Lee Suehyun,Kim Ju Han,Lee Kye Hwa 대한의학회 2024 Journal of Korean medical science Vol.39 No.28

Background: Older adults are at a higher risk of severe adverse drug events (ADEs) because of multimorbidity, polypharmacy, and lower physiological function. This study aimed to determine whether polypharmacy, defined as the use of ≥ 5 active drug ingredients, was associated with severe ADEs in this population. Methods: We used ADE reports from the Korea Institute of Drug Safety and Risk Management-Korea Adverse Event Reporting System Database, a national spontaneous ADE report system, from 2012 to 2021 to examine and compare the strength of association between polypharmacy and severe ADEs in older adults (≥ 65 years) and younger adults (20–64 years) using disproportionality analysis. Results: We found a significant association between severe ADEs of cardiac and renal/ urinary Medical Dictionary for Regulatory Activities System Organ Classes (MedDRA SOC) with polypharmacy in older adults. Regarding individual-level ADEs included in these MedDRA SOCs, acute cardiac arrest and renal failure were more significantly associated with polypharmacy in older adults compared with younger adults. Conclusion: The addition of new drugs to the regimens of older adults warrants close monitoring of renal and cardiac symptoms.

Patient Drug Database: 환자 생성 건강 데이터를 활용한 환자 주도적 약물 부작용 탐색을 위한 데이터베이스 구축

이상민 ( Sang Min Lee ),이수현 ( Suehyun Lee ),김종엽 ( Jong Yeup Kim ) 한국보건정보통계학회 2021 보건정보통계학회지 Vol.46 No.3

Objectives: This study focuses on building a database for patient-led search on drug side effects using basic drug information, drug analysis results information, patient information, and patient-generated health data (PGHD). Methods: After collecting data from the Health Insurance Review and Assessment Institute, the Korean Pharmaceutical Information Center, the Ministry of Food and Drug Safety, and the Korean Pharmaceutical Association, basic drug information was created. By utilizing the Korea Average Event Reporting System (KAERS) side effect report data provided by the Korea Drug Safety Administration and MetaLAB, a drug side effect detection algorithm applied on the Konyang university hospital’s real data, we designed and built a database using Oracle DB, which contains a table of patient information and PGHD. For drug information, a total of 49,553 drugs were mapped, and drug analysis results used KAERS and MetaLAB. Results: Based on the collected drug information, a total of 15 tables containing basic drug information (7 tables), drug analysis results (2 tables), patient information (1 table), and patient generation information (5 tables) were created using EDI codes, following mapping and normalization. Basic drug information included 49,553 EDI and 2,099 ATC codes. Drug analysis results included 2,046 KAERS ATC codes, 1,701 WHOART-ARRN (PT) that the result of 33 WHOART-SEQ (IT), 15,861 MetaLABEDI codes, and 101ATC codes. TheADR results were constructed using 62 DRUG_IDs and 73 MedDRA_PTI_IDs. Conclusions: The Patient Drug Database (PD2B) in this study was employed to allow patients to voluntarily report on their perception and drug side effects through application tools, which can provide quick measures against drug side effects and assist in the discovery of new ones.

소셜 네트워크 서비스 데이터에서 Bi-LSTM 기반 약물 부작용 게시물 탐지 모델 연구

이충천 ( Chung-chun Lee ),이승희 ( Seunghee Lee ),송미화 ( Mi-hwa Song ),이수현 ( Suehyun Lee ) 한국정보처리학회 2022 한국정보처리학회 학술대회논문집 Vol.29 No.1

본 연구에서는 소셜 네트워크 서비스(Social Network Service, SNS) 데이터로부터 약물 부작용 게시글을 추출하기 위한 순환 신경망(Recurrent Neural Network, RNN) 기반 분류 모델을 제안한다. 먼저, 처방 빈도가 높으며 게시글을 많이 확보할 수 있는 케토프로펜 약물에 대하여 국내 최대 소셜 네트워크 플랫폼인 네이버 블로그와 카페의 게시글(2005 년~2020 년)을 확보하고 최종 3,828 건을 분석하였다. 결과적으로 케토프로펜에 대한 3 종(약물, 부작용, 불용어)의 렉시콘을 정의하였으며 이를 기반으로 Bi-LSTM 분류모델 기준 87%의 정확도를 얻었다. 본 연구에서 제안하는 모델은 SNS 데이터가 약물 부작용 정보 획득을 위한 기존 (전자의무기록, 자발적 약물 부작용 보고 시스템 등) 자료원에 대한 보완적 정보원이 되며, 개발된 Bi-LSTM 분류모델을 통해 약물 부작용 게시글 추출의 편리성을 제공할 것으로 기대된다.

Re-reading of Winston Churchill’s Postwar Speech “The Sinews of Peace” (1946)

Jie, SueHyun(지수현),Lee, SangChul(이상철) 한국수사학회 2019 수사학 Vol.0 No.34

이 논문은 윈스턴 처칠이 1946년 미국 미주리 주 풀턴(Fulton)시에서 행한 일명 ‘철의 장막’(Iron Curtain) 연설을 재분석하였다. 첫째, 기존 연구는 ‘철의 장막’이라는 메타포(metaphor)에 중점적으로 이루어졌으나 이 논문에서는 처칠이 연설의 제목을 공식적으로 천명한 ‘평화의 근육’(Sinews of Peace) 메타포를 분석하였다. 또한 처칠이 연설에서 활용한 종교적 메타포인 ‘바벨탑’(Tower of Babel)과 ‘평화의 사원’(Temple of Peace)에 대해 레토릭 평론 관점에서 재분석하였다. 처칠은 수사학적으로 이러한 메타포를 통해 당시 정치•사회적 상황을 재창조하거나 재설정하려고 노력하였으며, 이 논문에서는 그러한 정치•사회적 상황에서 청중인 시민들이 인지적으로 처칠의 관점을 수용하는 과정을 살펴보며 메타포의 기능과 역할에 관해 논의하였다. 둘째, 이 논문은 처칠이 여러 번 강조한 ‘영어권 사람들(English Speaking People)의 단합’과 ‘형제 연합’(fraternal association)에 대한 관용구를 분석하였다. 이 관용구는 현장 청중들인 미국 시민들에게 효과적인 문구라고 보았지만, 처칠 이 원하던 공산국가들과 대항하는 민주국가들의 연합과 국제연합(United Nations)을 강조하는 관점에서 본다면, 영어가 모국어가 아닌 다른 국가의 청중들을 도외시하는 단점을 갖고 있다고 지적하였다. 셋째, 일부 기존의 연구는 이 연설을 誇示연설(epideictic) 장르로 분석하며 정치적인 면에서 단기적으로 비효과적이라고 평가하였으나, 이 논문에서는 審議연설(deliberative) 장르의 특성을 검토하였다. 심의연설 장르로서 이 연설은 청중들에게 심의관 역할을 맡도록 하며, 공동체의 유용성(expediency)을 위해 미래의 정책(policy) 방향을 결정하도록 촉구하는 효율적인 심의연설로 평가하였다.

Pre-trained Model for brain tumor prediction

Kyoungsu Oh,Seok-hwan Kang,Suehyun Lee,Hyekyung Woo,Youngho Lee 한국차세대컴퓨팅학회 2023 한국차세대컴퓨팅학회 학술대회 Vol.2023 No.12

Medical images constitute a substantial portion of all medical data, but various issues arise, including noise and judgment-related problems. Therefore, recent research has actively explored deep learning applications, such as noise removal and disease classification based on medical images. In particular, brain tumors are typically diagnosed using MRI, and early detection is crucial. In this study, the classification of MRI images for brain tumor patients was conducted by improving MRI noise and utilizing a pre-trained CNN model.

시판 후 약물감시를 위한 자료원별 약물 부작용 분석 방법 및 연구 동향

신현아 ( Hyunah Shin ),박성현 ( Seonghyeon Park ),이수현 ( Suehyun Lee ) 한국보건정보통계학회 2022 보건정보통계학회지 Vol.47 No.7

In this study, we summarized analysis methodologies for each of five sources that electronic medical records, claim data, spontaneous reporting system data, social media data, and knowledge base for pharmacovigilance and research trends. We used PubMed from 2016.01.01. to 2020.12.31. for reviewing, and as a result, spontaneous reporting system data tended to be used the most, followed by electronic medical records. As for the analysis methods, data mining was applied the most, followed by traditional statistical analysis. We need an appropriate research design, because each data source has different characteristics and analysis methods applied depending on the subject.