支援大數據深度學習建模分析之具可靠性智慧服務倉儲平台設計

朱正忠 ； 許哲銓 ； 張志宏 ； 洪哲倫 ； 王冠智

《TANET2017 臺灣網際網路研討會》 2017年 (2017/10) Pp. 1717-1721

https://doi.org/10.6728/TANET.201710.0304

摘要

慢性病管理是各國醫療照護人員面臨最昂貴、增長最快且最棘手的問題。健康照護數據不具有互通特性，也缺乏數據標準，使得專家和數據科學家難以從中提取有意義的資訊。對龐大的醫療數據庫，進行深度學習分析，可提前診斷並改善醫療結果，協助醫療人員精確地對疾病作出診斷。採用預測性，預防性，個性化和參與性的P4 medical model，於疾病初期辨識出病癥，並在疾病擴展之前進行治療，幫助患者改善日常行為及健康狀況。在此篇論文中提出了一個有效且可靠的支援大數據深度學習建模分析之智慧服務倉儲平台，其中服務框架及中介層，以維護智慧醫療保健系統的服務品質，及分析和設計用來預測導致糖尿病和腎臟病的風險因素的數學模型， 向病患提供照護之建議。最終以醫院端資料驗證此服務平台的可用性與有效性。

關鍵字

大數據 ； 可靠系統 ； 深度學習 ； 建模 ； 微服務

並列摘要

Chronic disease management is the most expensive, fastest growing and most difficult problem for medical care workers in various countries. Health care data do not have interoperability characteristics, but also the lack of data standards, making it difficult for information scientists and data scientists to extract meaningful information. Through deep learning analysis a large medical database, can diagnose and improve medical results in advance, to help medical personnel to accurately diagnose the disease. The use of P4 medical models predictive, preventative, personalized and participatory identifies disease at the beginning of the disease and is treated prior to disease progression to help patients improve their daily behavior and health status. In this paper, an effective and reliable intelligent service warehousing platform, which is a service framework and a middle layer, is designed to maintain the quality of service of the intelligent health care system and to analyze and design to predict the risk factors that contribute to diabetes and kidney disease. Mathematical model, to provide care to the patient's advice. At the end we verified the availability and effectiveness of this service platform from the hospital-side data.

並列關鍵字

Big Data ； Dependable System ； Deep learning ； Modeling ； Microservices