Wild-Health: From Quantified Self to Self-Understanding

作者：Li Yang; Guo Yike^*

来源：Future Generation Computer Systems-The International Journal of eScience, 2016, 56: 333-359.

DOI：10.1016/j.future.2015.08.008

• Wiki-Health
• Big Data Management
• Health sensor data management
• Self-Understanding
• Quantified-Self

Today, healthcare providers are experiencing explosive growth in data. Although the dramatic increase in the use of medical imaging technologies has been a major contributor to healthcare data growth in the past decade, more recently the rising adoption of sensing devices, enabling people to collect health-related data independently at any time or place is leading to a torrent of sensor data. The scale and richness of the sensor data currently being collected and analysed is rapidly growing. The key challenges that we will be facing are how to effectively manage and make use of this abundance of easily generated and diverse health data.
This paper explores the potential for sensors use in healthcare data acquisition and presents the next evolution in the on-going development of Wiki-Health, a big data service platform, designed to address the larger problem of explosive growth in healthcare information by providing a unified solution for collecting, storing, tagging, retrieving, searching and analysing personal health sensor data. Additionally, the platform is designed to allow users to reuse and remix data, along with analysis results and analysis models, to make health-related knowledge discovery more available to individual users including health professionals, patients or even individuals who desire to maintain an optimum level of personal health on a massive scale.
To tackle the challenge of efficiently managing the high volume and diversity of big data, Wiki-Health introduces a hybrid data storage model capable of storing structured, semi-structured and unstructured sensor data and sensor metadata separately. The design of such a hybrid model allows Wiki-Health to potentially handle heterogeneous formats of sensor data. In addition to its data management capabilities, we envision the potential for Wiki-Health as a system that also enables health sensor data monitoring and analysis, not only as a method of tracking existing health conditions but also as a means of encouraging a more pro-active approach to healthcare through early detection. To tackle the scalability and performance challenges of real-time analysis, the Analysis Tasks Allocation Scheme proposed in the research aids the management of data analysis tasks on a large scale and utilises the elastic nature of cloud infrastructure by considering the aspects of performance and cost.
To evaluate the proposed Wild-Health approach, we have developed an ECG-based health monitoring service on top of the Wiki-Health platform. The positive performance of the approach is supported by the results obtained in our experimental trials and shows significant potential for real-world applications.

• 出版日期2016-3