• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.934-941
• /
• 2018

There are some limits on cost and efficiency for large amount of data in RDBMS, and NoSQL is starting to gain popularity. In medical institutions, data forms are different between organizations, and that makes difficulty for interoperability between organizations. In this paper we focused on performance issues between RDMBS and NoSQL in medical documents. We had built two different environment and had experiment comparative analysis of NoSQL with RDBMS based on medical data. We used medical HL7 FHIR as a medical data standard. Also YCSB benchmark tool was used for performance comparison. Experiments shows that NoSQL has better performance in large amounts of medical data processing systems that have over 10,000~100,000 records.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.269-270
• /
• 2023

본 논문에서는 구글 클라우드에 1차적으로 저장된 Healthcare API 서비스의 FHIR 객체들을 Big Query 서비스로 전환하고 질의를 작성하여 결과를 확인하는 과정을 설명한다. 이 과정에서 IAM을 위한 Big Query 테이블로의 입력 권한 부여 과정과 중첩된 필드들을 포함하고 있는 FHIR 객체의 명세과정이 핵심적인 단계가 되고 있으며 위 서비스들의 연계에 의해 대용량의 의료정보들이 구글 클라우드 상에 저장되고 사전분석되어 추가적인 정밀 분석을 위한 기저 자료를 제공할 수 있다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.356-357
• /
• 2023

본 논문에서는 구글 클라우드의 Healthcare API의 의료정보 표준에 따라 정의된 객체들을 저장하는 과정을 수행하고 활용방안을 설계한다. 클라우드에서 프로젝트 생성, API 활용 설정, 인증, 데이터 셋 생성 등의 과정을 거쳐 cloud shell을 통해 curl 명령을 수행함으로써 Json으로 표현된 의료자원들에 대해 CRUD 연산을 수행할 수 있다. 무결성 체크 과정에서 기본 객체의 id 필드 명세가 중요하며 데이터 저장시 객체에 구글 클라우드의 특정한 request 속성추가가 필요하다.

• 정보과학회지
• /
• 제33권3호
• /
• pp.67-72
• /
• 2015

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.164-172
• /
• 2020

The interest and importance of the convergence services for healthcare expand more and more as the average life expectancy increases. Convergence of ICT and healthcare technology unfold efficient and quick health services. Recently, healthcare services provide to clients with apps over web. On-demand wireless data broadcast supports any number of clients to access their desired data items dynamically by responding the needs for data items from the clients. In this paper, we propose an on-demand system to broadcast FHIR bundles for efficient healthcare services. We use time-parameterized replacing policy for renewing the bundle items on the wireless broadcast channel. The policy lets the on-demand broadcasting dynamic by controlling the time duration for the bundles to reside over the wireless channel. With simulation studies using an implemented testbed, we evaluate the performances of the proposed system in access time and tuning time. For evaluation, we compare the time-parameterized replacing policy of the proposed system with regular-number replacing policy. The proposed time-parameterized replacing policy shows shorter access time than the regular-number replacing policy because the policy responds more actively and dynamically to the change of the needs of the clients for FHIR bundles.

• 전기학회논문지
• /
• 제67권7호
• /
• pp.969-975
• /
• 2018

The purpose of this study is to develop a healthcare service based on standard protocol and information communication technology for mother's sustainable postpartum care. The developed service was consisted of a client area where mothers measure, manage and transmit their vital signs using their own smartphone and personal health devices, and a server area that manages and shares with the received mother's vital signs and the results of examination results and personal health records. The client area collects vital signs through the IEEE 11073 Personal Health Device (PHD) using the m-health application of the previous study and Continua Health alliance certified personal health devices and transfers to Health Level Seven (HL7) V2.4, Continuity of Care Record (CCR) and Continuity of Care Document (CCD). The server area consists of a mobile web that manages and shares the HL7 Fast Healthcare Interoperability Resources (FHIR)-compliant personal health records to ensure interoperability of examination results, and a mobile web where the postpartum caregiver enters and manages the results of the mother's examination results and provides it to the mother. In this way, the healthcare service of this study securing continued exchanges between the mother and postpartum caregiver improves the quality of life of the mother not only to satisfy the needs of the mother who was discharged but also through self-management and postpartum. In the future, we will conduct a study applying mothers and postpartum caregiver after approval of a clinical trail at a university hospital to evaluate developed healthcare services.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.705-706
• /
• 2024

본 논문에서는 pdf 파일 형태로 주어진 119 구조대원 현장지침을 Open AI의 Llama index에 학습시켜 대화형 모델을 만들고 응급현장에서 발생할 수 있는 질의들을 쿼리 엔진에 제시하고 그 결과의 타당성을 확인한다. 기존 지식모델에서 학습된 내용과 추가된 정보에서 추론된 결과들이 제시되고 있으나 안정적인 사용을 위해서는 필요한 정보들만 요약하는 전처리 과정에 대한 설계가 필요하며 FHIR에 기반한 환자 정보 분석 모델과 결합된다.