WikiHealth - Big Data infrastructure for Social Wellbeing

WikiHealth draws inspiration from existing platforms such as PatientsLikeMe (www.patientslikeme.com), which reports more than 175,000 active users and 1000 conditions. These figures indicate that people are very interested in using data-sharing social platforms for healthcare to communicate with other people who have common needs and learn more about themselves.

WikiHealth will be a social platform for data-driven and context-specific discovery of citizen communities in the areas of health, fitness and well-being. WikiHealth will harness personalised and location-based information for health-related knowledge discovery available to individual users at a massive scale. WikiHealth is based on the concept of the wiki (or mass collaboration), according to which aggregated user-contributed content is collectively curated to produce unprecedented knowledge in a multi-perspective and socially engaging way.

Sensor Revolution

Mobile Phones are becoming increasingly successful in the area of health monitoring. They provide new ways to gather information, both manually and automatically, over wide areas. Many current phones have embedded a number of sensors such as microphone, camera, gyroscope, accelerometer, compass, proximity sensors, GPS and ambient light. The newer generation of professional medical sensors can easily connect to the smart phones and transfer the sensing results directly. This has brought a more efficient and convenient way of collecting information about persons health like blood pressure, oxygen saturation, blood glucose level, pulse, Electrocardiogram (ECG), Electroencephalogram(EEG) and electrocardiography (EKG).
healthsensors

Architecture of WikiHealth


architecture

Big Data Analysis

One of key researches for WikiHealth is to deliver novel algorithms for data-driven community discovery in large health datasets. Given time series coming from sensors in real time the developed algorithms should identify commonalities in the different users’ health and discover communities in which patients could benefit from exchanging information or comparing the effects of specific kinds of treatment. For example, an interesting work can be modelling sleep patterns for different people based on various parameters such as their life styles, activities, surrounding environment and so on. Students must have experience or strong interest in data mining, machine learning, and algorithms.

Big Data Explosion

Please refer any enquiries to:

yang.li09atsign imperial.ac.uk
Yang Li