오늘날 많은 비용이 국가 의료보장체계의 유지를 위협하고 있다. 국가 질병 통제 및 방지 센터의 감사체계를 동반한 건강관리 역학성에 대한 연구에도 불구하고, 시간 한계, 표본 한계, 대상 질병 한계에 대한 제약이 여전히 존재하고 있다. 이러한 배경에서, 방대한 양의 전수 데이터를 활용하여, 많은 기술들이 건강의 선제적 예측이나 그 대상 질병을 확장하는 분야에 충분하게 적용되고 있다. 우리는 국민건강보험의 구조적 데이터와 소셜네트워크서비스의 비구조적 데이터를 활용하여 질병을 예측하는 모형을 설계하였다. 이 모형은 건강예보서비스를 제공함으로써, 국민건강을 증진시키고 사회적 혜택을 극대화할 수 있다. 또한, 빅데이터 분석에 근거하여, 건강보험비용의 갑작스러운 증가를 감소시키거나 적시적인 질병발생을 예측할 수도 있다. 관련된 의료 예측 사례를 살펴보았고, 제안된 모형의 검증을 위하여 시범과제를 통한 실험을 수행하였다.
오늘날 많은 비용이 국가 의료보장체계의 유지를 위협하고 있다. 국가 질병 통제 및 방지 센터의 감사체계를 동반한 건강관리 역학성에 대한 연구에도 불구하고, 시간 한계, 표본 한계, 대상 질병 한계에 대한 제약이 여전히 존재하고 있다. 이러한 배경에서, 방대한 양의 전수 데이터를 활용하여, 많은 기술들이 건강의 선제적 예측이나 그 대상 질병을 확장하는 분야에 충분하게 적용되고 있다. 우리는 국민건강보험의 구조적 데이터와 소셜네트워크서비스의 비구조적 데이터를 활용하여 질병을 예측하는 모형을 설계하였다. 이 모형은 건강예보서비스를 제공함으로써, 국민건강을 증진시키고 사회적 혜택을 극대화할 수 있다. 또한, 빅데이터 분석에 근거하여, 건강보험비용의 갑작스러운 증가를 감소시키거나 적시적인 질병발생을 예측할 수도 있다. 관련된 의료 예측 사례를 살펴보았고, 제안된 모형의 검증을 위하여 시범과제를 통한 실험을 수행하였다.
Lots of costs threaten the sustainability of the national health-guarantee system. Despite research by the national center for disease control and prevention on health care dynamics with its auditing systems, there are still restrictions of time limitation, sample limitation, and, target diseases li...
Lots of costs threaten the sustainability of the national health-guarantee system. Despite research by the national center for disease control and prevention on health care dynamics with its auditing systems, there are still restrictions of time limitation, sample limitation, and, target diseases limitation. Against this backdrop, using huge volume of total data, many technologies could be fully adopted to the preliminary forecasting and its target-disease expanding of health. With structured data from the national health insurance and unstructured data from the social network service, we attempted to design a model to predict disease. The model can enhance national health and maximize social benefit by providing a health warning service. Also, the model can reduce the advent increase of national health cost and predict timely disease occurrence based on Big Data analysis. We researched related medical prediction cases and performed an experiment with a pilot project so as to verify the proposed model.
Lots of costs threaten the sustainability of the national health-guarantee system. Despite research by the national center for disease control and prevention on health care dynamics with its auditing systems, there are still restrictions of time limitation, sample limitation, and, target diseases limitation. Against this backdrop, using huge volume of total data, many technologies could be fully adopted to the preliminary forecasting and its target-disease expanding of health. With structured data from the national health insurance and unstructured data from the social network service, we attempted to design a model to predict disease. The model can enhance national health and maximize social benefit by providing a health warning service. Also, the model can reduce the advent increase of national health cost and predict timely disease occurrence based on Big Data analysis. We researched related medical prediction cases and performed an experiment with a pilot project so as to verify the proposed model.
* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.
제안 방법
We proposed a health warning model for customer relationship management (HWM-CRM) using Big Data. After researching related cases of health prediction involving Big Data analysis, we performed a pilot experiment and verified the results. In order to accelerate this model, we will develop a service for nation-wide health promotion.
4) that provides influenza activity estimates for more than 25 countries. By aggregating Google search queries, the service attempts to make accurate predictions about flu activity.
In this process, we conducted a time series prediction and performed risk modeling. In the time series prediction, we designed an auto-regressive moving average model and predicted treatment information.
We performed an experiment to verify our HWM-CRM model. The experiment involved four major processes; target disease selection, knowledge implementation, collection/ mining, and prediction analysis.
This attempt is dependent on structured operational data with referring to unstructured social data with more developed Big Data technology. The model would certainly overcome existing limitations of epidemiological survey method only on the basis of operational National Health Insurance databases, and then improve the accuracy or speed of disease prediction by use of total data on the basis of Big Data analysis technologies. We performed an experiment to verify our HWM-CRM model.
The model supports macroscopic medical trends for the nation and individually customized medical information for each citizen. The service develops a disease prediction model and provides health warnings by monitoring danger signs. For the service, both the database for national health insurance and social media information are integrated.
The model would certainly overcome existing limitations of epidemiological survey method only on the basis of operational National Health Insurance databases, and then improve the accuracy or speed of disease prediction by use of total data on the basis of Big Data analysis technologies. We performed an experiment to verify our HWM-CRM model. The experiment involved four major processes; target disease selection, knowledge implementation, collection/ mining, and prediction analysis.
대상 데이터
We use several technologies to predict diseases on the basis of Big Data analysis, while focusing on personally customized analysis from the viewpoint of customer relationship management (CRM) [5-7]. The model handles two dimensional Big Data; one is the huge volume of citizen data from national health insurance and the other is the huge volume of crawled social network service data. The model supports macroscopic medical trends for the nation and individually customized medical information for each citizen.
이론/모형
With 6 target diseases, we established the knowledge classification system. The knowledge classification was performed with the mapping method of vocabulary modeling.
참고문헌 (9)
F. M. Rafiei, S. M. Manzari, and S. Bostanian, "Financial health prediction models using artificial neural networks, genetic algorithm and multivariate discriminant analysis: Iranian evidence," Expert Systems with Applications, vol. 38, no. 8, pp. 10210-1021, Aug. 2011.
S. P. Borgatti, and X. Li. "On social network analysis in a supply chain context," Journal of Supply Chain Management, vol. 45, no. 2, pp. 5-22, Mar. 2009.
R. Agrawal, and R. Srikant, "Fast algorithms for mining association rules," in Proceeding of the International Conference on Very Large Data Bases, Santiago, Chile, pp. 487-499, 1994.
M. W. Berry, S. T. Dumais, and G. W. O'Brien, "Using linear algebra for intelligent information retrieval," SIAM Review, vol. 37, no. 4, pp. 573-595, Dec. 1995.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.