• 한국병원경영학회지
• /
• 제17권3호
• /
• pp.57-82
• /
• 2012

The primary purpose of this study is to examine consumers'probing actions to see what information sources consumers search for medical information when there are diverse medical service information channels, and classify consumers by information source. Its secondary purpose is to understand trust of information and attitude toward information by consumer type, value of medical service, satisfaction with medical service, and word-of-mouth intention. This study will concretely identify information utilization patterns of medical consumers, and explain the unique characteristics and behavior of segmented types of medical consumers. The significance of this study lies in the search for ways to establish information channels trusted by consumers for building an efficient medical service market in the future. The results of this study show that consumers were classified by the latent class analysis(LCA) into 5 types: low-level information seekers, word-of-mouth information seekers, mass media information seekers, digital information seekers and diverse information seekers. The reliability of information sources by type of medical consumer was statistically significant, and in the analysis of differences in consumer attitude, there was a statistically significant difference in cognitive responses. The value of medical service was statistically significant in health recovery and medical service word-of-mouth intention.

• 한국빅데이터학회지
• /
• 제6권1호
• /
• pp.51-62
• /
• 2021

의료 인공지능 분야에서 의사의 판단에 도움을 줄 수 있는 질환 예측 및 분류 알고리즘에 대해선 많은 연구가 이뤄져왔지만, 의료 소비자의 정보 획득과 판단에 도움을 줄 수 있는 인공지능에 대해선 상대적으로 관심이 적다. 네이버 지식인에 지난 1년 간 자신의 증상엔 어떤 병원을 가야할 지 질문하는 질문 건수만 해도 15만 건이 넘는다는 사실은 의료소비자들에게 적합한 의료정보의 제공이 필요하다는 반증이기도 하다. 따라서 본 연구에선 의료소비자들이 자신의 증상에 대한 진료과목을 선택하는데 도움을 줄 수 있도록 네이버 지식인에서 환자들이 직접 서술한 증상 텍스트를 수집하여 8개 진료과목을 분류하는 분류모델을 구축했다. 우선 환자의 주관이 개입된 데이터의 타당성과 객관성을 확보하기 위해 객관적 증상 텍스트(서울응급의료 정보센터에서 정리한 진료과목 별 주요 질환 증상)와 주관적 증상 텍스트(지식인 데이터) 간 유사도 측정을 수행하였다. 유사도 측정 결과, 두 텍스트가 동일한 진료과목의 증상일 경우 상이한 진료과목의 증상 텍스트에 비해 상대적으로 높은 유사성을 가진다는 것을 입증했다. 상기 절차를 따라 타당성을 확보한 주관적 증상 텍스트를 대상으로 릿지회귀모델을 사용하여 분류모델을 구축한 결과 0.73의 정확도를 확보할 수 있었다.

• Genomics & Informatics
• /
• 제12권4호
• /
• pp.151-155
• /
• 2014

In November 2013, the US Food and Drug Administration (FDA) sent a warning letter to 23andMe, Inc. and ordered the company to discontinue marketing of the 23andMe Personal Genome Service (PGS) until it receives FDA marketing authorization for the device. The FDA considers the PGS as an unclassified medical device, which requires premarket approval or de novo classification. Opponents of the FDA's action expressed their concerns, saying that the FDA is overcautious and paternalistic, which violates consumers' rights and might stifle the consumer genomics field itself, and insisted that the agency should not restrict direct-to-consumer (DTC) genomic testing without empirical evidence of harm. Proponents support the agency's action as protection of consumers from potentially invalid and almost useless information. This action was also significant, since it reflected the FDA's attitude towards medical application of next-generation sequencing techniques. In this review, we followed up on the FDA-23andMe incident and evaluated the problems and prospects for DTC genetic testing.

• International Journal of Knowledge Content Development & Technology
• /
• 제7권1호
• /
• pp.101-120
• /
• 2017

Healthcare professionals have edited many health questions (HQs) and their answers for healthcare consumers on the Internet. The HQs provide both readable and reliable health information, and hence retrieval of those HQs that are relevant to a given question is essential for health education and promotion through the Internet. However, retrieval of relevant HQs needs to be based on the recognition of the intention of each HQ, which is difficult to be done by predefining syntactic and semantic rules. We thus model the intention recognition problem as a text classification problem, and develop two techniques to improve a learning-based text classifier for the problem. The two techniques improve the classifier by location-based and area-based feature weightings, respectively. Experimental results show that, the two techniques can work together to significantly improve a Support Vector Machine classifier in both the recognition of HQ intentions and the retrieval of relevant HQs.

• 방사선산업학회지
• /
• 제9권1호
• /
• pp.29-35
• /
• 2015

Radiation technology is the one for developing new products or processes by applying radiation or for creating new functions in industry, research and medical fields, and its application is increasing consistently. For securing an advanced technology competitiveness, it is required to create a new added value by information consumer through providing an efficient system for supporting information, which is the infrastructure for research and development, contributed to its collection, analysis and use with a rapidity and structure in addition to some direct research and development. Provision of the management structure for information resources is especially crucial for efficient operating the system for supporting information in radiation technology, and then a standard classification structure of information must be first developed as the system for supporting information will be constructed. The standard classification structure has been analyzed by reviewing the definition of information resources in radiation technology, and those classification structures in similar systems operated by institute in radiation and other scientific fields. And, a draft version of the standard classification structure has been then provided as 7 large, 25 medium and 71 small classifications, respectively. The standard classification structure in radiation technology will be developed in 2015 through reviewing this draft version and experts' opinion. Finally, developed classification structure will be applied to the system for supporting information by considering the plan for constructing this system and database, and requirements for designing the system. Furthermore, this structure will be designed in the system for searching information by working to the individual need of information consumers.

• 한국산학기술학회논문지
• /
• 제19권11호
• /
• pp.730-737
• /
• 2018

행복한 삶의 질을 목적으로 하는 의료소비자가 증가하면서 웹에 분산되어 있는 블로그의 의료 정보를 바탕으로 신뢰성 있는 의료 시설을 선택하고 고품질의 의료 서비스를 받음으로서, 시간과 비용을 절약할 수 있는 O2O 의료 마케팅 시장이 활성화 되고 있다. 인터넷, 모바일, SNS 등에서 증가하는 비정형 텍스트 데이터는 전문 의료 지식 이외에 작성자의 관심, 선호, 예상 등을 직간접적으로 반영하고 있기 때문에 의료정보의 신뢰성을 담보하기 어렵다. 본 연구에서는 빅데이터 및 MLP를 사용하여 의료정보 블로그를 분류 (의료블로그, 광고블로그)함으로서 사용자에게 보다 고품질의 의료정보 서비스를 제공하는 블로그 판단 시스템을 제안한다. 제안된 빅데이터 및 머신러닝 기술을 통해 인터넷상에 존재하는 국내의 다수 의료정보 블로그를 종합, 분석한 후 질환별 개인 맞춤형 건강정보 추천 시스템을 개발한다. 이를 통하여 사용자는 자신의 건강문제를 지속적으로 점검하고 가장 적절한 조치를 취함으로서 자신의 건강 상태를 유지하는 것이 가능할 것으로 기대된다.

• 지능정보연구
• /
• 제28권1호
• /
• pp.217-242
• /
• 2022

AI 기술이 결합된 지능형 제품은 기술적 차별화를 실현하며 시장 경쟁력을 높일 수 있는 잠재성을 지닌다. 하지만 시장 수용도를 극대화 할 수 있는 AI 기반의 신제품 개발 방법론은 부재하다. 본 연구는 AI 기반의 지능형 제품 개발에 대한 방법론으로서 KANO-QFD 통합 모델을 제안한다. 실증적인 분석을 위한 구체적 사례로 탈모 예측 및 치료 기기에 대한 소비자 요구조건(Customer Requirements)의 유형을 분류하고, 이를 구현하기 위한 기술적 요구사항(Engineering Characteristics)의 상대적 중요도 및 우선순위를 도출하여 지능형 메디컬 신제품 개발의 방향을 제시하였다. 소비자 130명을 대상으로 실시한 설문조사 분석 결과, KANO 카테고리 중 매력적 품질(Attractive Quality) 요소로 미래 탈모 진행 상황에 대한 정확한 예측, 미래 탈모 모습 및 치료 후 개선된 미래 모습을 실물화하여 스마트폰으로 보고, 세련된 디자인, 레이저와 LED 빛 복합 에너지를 이용한 치료 등이 도출되었다. QFD의 품질의 집(House of Quality)을 기반으로 분석한 결과, 탈모 진단 및 예측을 위한 학습 데이터, 두피 스캔용 Micro 카메라 해상도, 탈모 유형 분류 모델, 맞춤화를 위한 개인별 계정 관리, 탈모 진행상황 진단 모델 순으로 상대적 중요도 및 우선순위가 도출되었다. 본 연구는 기존에 선행되지 않았던 AI 기반의 지능형 메디컬 제품 개발에 대한 방향을 제시하였다는 면에서 의의를 지닌다.

• 지역사회간호학회지
• /
• 제6권2호
• /
• pp.259-274
• /
• 1995

The study is to grasp the problems related to operation of Maternity clinic of public health centers in seoul and needs for public health of community in relation to consumers and providers in order to improve efficiency of community public health for mothers and children. Four pregnancy woman, who receive medical care at the maternity clinic of M public health centers in seoul and understand the purpose of this study, and one nurse who works at the were the objects of this field study. Participating observation and intensive interviews were conducted to collect data. All of them were performed as necessary from time to time since December, 1994, and not during a specific period. Through an data analysis in the order of sector analysis and classification analysis, the data were classified into specific patterns and the results are the following; 1. All of the subjects were using both private hospitals and public clinics, but managing activities prior to delivery were not carried out in accordence with theories for those activities. 2. The subjects showed two types of response to utilizing maternity clinic. they answered that the advantages of the clinic were 'short waiting time for medical treatment', 'medical treatment by female doctors' and 'economical benefit.' Meanwhile, they gave negative response to the problems of 'non-implementation of delivery' 'uncleanness and insufficient facilities', 'limited time of treatment', 'lack of expertise' and 'want of public health education for materity.' 3. Problems related to operation of maternity clinic were 'lack of experts', 'irrational facility structure' and 'absolutely lack budget'. In terms of the status of managing the subjects, 'programs only aimed at attaining the central-government-assigned objects' and 'limited management before and after delivery by non-implementing delivery' were pointed out to be problems. Regarding public health education before delivery and PR relations, 'superficial public health education for maternity' and 'absence of PR programs' were named. In planning and evaluation, 'absence of autonomous planning and evaluation by the clinic itself' was a major problem in operating the clinic. 4. 'Substantial health education and PR', 'supplementation of facilities and eqipment', 'development' and supply of demanded service by the subjects', 'implementation of autonomous programs', and 'reinforcement of supplementary education' were presented as alternatives for efficient opration of maternity clinics.