智慧型互動病症推論引擎

An Intelligent and Interactive Healthcare Inference Engine

呂芃萱(Peng-Hsuan Lu)

指導教授 ： 陳建錦

國立臺灣大學/管理學院/資訊管理學研究所/碩士(2014年)

https://doi.org/10.6342/NTU.2014.10554

摘要

網際網路的普及以及近年來大眾對於健康議題的重視，使得健康相關的網站及系統逐漸的普遍。在本篇研究中，我們實作出一個健康照護搜尋引擎，希望能提供使用者完整、有效率的疾病診斷服務，我們應用一個創新的權重模型，其涵蓋獨特性及主要性兩種特性，並設定了三個參數來探討考量身體階層後的影響力。最後，我們以三百多個實際案例來做測試，實驗結果顯示考慮不同身體階層能讓系統的準確率明顯提升，而系統也表現了良好的診斷疾病效能。

關鍵字

健康照護 ； 搜尋引擎 ； 權重模型

並列摘要

Accessing the Internet and emphasizing health are two of the most popular trends in recent years. Several health websites or systems were being constructed one after another. In this paper, we implemented a healthcare inference engine for supporting users who has concerns about their own physical conditions. Our research applied a novel weighting model which based on two features of weight which were uniqueness and dominance. Moreover, three parameters were assigned to measure the effect from adding the hierarchy levels of body parts into our methods. In sum, great improvement could be seen after applying body parts hierarchy levels and this healthcare inference engine could performed successfully in real cases.

並列關鍵字

healthcare ； inference engine ； weighting model

參考文獻

1. Fox, S., The Social Life of Health Information - 2011, in Pew Research Center’s Internet & American Life Project 2011.

2. Zickuhr, K., Generations 2010. Pew Internet & American Life Project, 2010. 16: p.11.

3. Fox, S. and M. Duggan, Health Online - 2013, in Pew Research Center’s Internet & American Life Project 2013.

4. Zhang, Y. A review of search interfaces in consumer health websites. in Workshop on Human-Computer Interaction and Information Retrieval. 2011.

5. Luo, G. and C. Tang. On iterative intelligent medical search. in Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval. 2008. ACM.