Utilizing big data to build personalized technology and system of diagnosis and treatment in traditional Chinese medicine.

Abstract

In September 2008, a special issue was published by Nature devoted to big data storage, management, and analysis, and it signified the coming of the era of big data [1,2]. Later, more reports and special issues on big data were published by Science [3]. In China, big data is becoming a hot topic. Headed by Guojie Li, an academician from the Chinese Academy of Engineering, a task force on big data was created in October 2012 by the China Computer Federation in Dalian, China [4]. In March 2013, the National Natural Science Foundation of China held the 89th Shuangqing Forum on “Challenging the Scientific Issues of Big Data Technology and Application” in Shanghai. In 2009, a few weeks before the influenza A (H1N1) outbreak, an engineer from Google published a paper that stunned the public. In the article, the author identified the combinations of the 45 most common search terms and fed them into a specific mathematical model. The author compared a list of 50 million most common terms searched by Americans, such as “drugs for cough and fever,” with the U.S. Centers for Disease Control and Prevention (CDC) data on the spread of seasonal influenza from 2003 to 2008. The prediction of a flu pandemic was strongly (97%) correlated with that revealed by CDC figures. The article predicted the flu not only at the national level but also at the regional and even state level. Furthermore, the prediction was near real-time, unlike the figures of the CDC, which were unavailable until one or two weeks after the flu broke out [5,6]. Many other instances signal the emergence of big data. The use of big data slowly triggers a huge transformation in our times. What are big data then? No consensus on its definition has been achieved so far. According to “Mining the Big Data,” the annual ACM SIGKDD (Association for Computing Machinery’s Special Interest Group on Knowledge Discovery and Data Mining) conference held in August 2012, big data should be larger than what 10 servers can store in terms of storage capacity. Data similar to that must be processed online as one computer’s memory is unable to handle the data. From the perspective of data analysis, some experts argue that big data is so complicated that most methods available are unable to process them and frameworks, such as Hadoop, should be used to handle them. National Science Foundation summarizes the definition of big data as “large, diverse, complex, longitudinal, and/ or distributed data sets generated from instruments, sensors, Internet transactions, email, video, click streams, and/or all other digital sources available today and in the future” [7]. However, in their book on big data, Mayer-Schonberger and Cukier (2013) proposed that, from the perspective of exploitation, the tasks of big data could only be accomplished on the basis of massive data rather than on small data. Therefore, big data is a resource for humans to obtain new knowledge and create new value, as well as a way for markets, organizational structures, and relations between governments and citizenry to transform [8]. Therefore, big data is not only huge in volume and complex in structure but also dynamic and rich in useful value. Today, information resources with a potential nature of big data can be found everywhere. Most of these resources are stored in the form of paper or analog information. With the wide use of digitization, networks, and Internet of Things (IOT), these data can be largely activated once digitized and transformed into something with considerable innovative value. In the same vein, data can grow into big data that can boost traditional Chinese medicine (TCM) development and enhance health services generated. These data come from EDITORIAL