Copyright © 2010-2014, CILMI project.
Last updates: January 2014.
The term Lifestyle management infrastructure refers to a wide range of ICT technologies (from sensors to middleware, data management, security and privacy, and human-computer interaction) that support humans improve their wellness and health. According to Egger, Binns and Rossner (2008) Lifestyle Medicine (LM) is defined as the application of environmental, behavioural, medical and motivational principles to the management of lifestyle related health problems in the clinical setting.LM is becoming the preferred modality for not only the prevention but the treatment of most chronic diseases, including type-2 diabetes, coronary heart disease, hypertension, obesity, insulin resistance syndrome, osteoporosis and many types of cancer. While LM remains primarily a clinical discipline, (pervasive) ICT provides opportunities in terms of detecting lifestyle habits and correlating them with health or unhealthy patterns, so that people (and patients in particular) can be informed on what they can or need to do to reduce their health risk level. There are three types of tools in this context: (1) lifestyle sensors, which include various ways of measuring nutrition and food intake, activity levels, fitness, stress anxiety, depression, sexual health, sleep, skin care, smoking patterns, and a range of other behaviours, emotions, and problems (see www.australianlifestylemedicineassociation.net.au and www.lifestylemedicine.org); (2) data analysis tools that process lifestyle information and detect potentially harmful patterns; and (3) lifestyle middleware tools that connect LM components and enable an integrated management of all processes and data, including support for privacy.
One of the most interesting research opportunities in lifestyle management infrastructure is to extend business intelligence and computational intelligence techniques can be developed and applied on this data. Types of data range from simpler (numeric, char) to complex (digital images, process data, spatiotemporal data, etc.). Issues as warehousing such complex data that frequently presents temporal variations, and several well-known data quality problems as noise, outliers, null values can be addressed by those techniques. Besides, data mining tasks, as classification, regression and clustering can be performed to find interesting patterns that can improve the procedures executed in LM. In addition, the perception of user (patient or citizen) trust in LM systems may importantly influence acceptance of such technology, since sensitive data in sensitive (often shared) settings is obtained and analyzed.
Together, the above provides a strong case for the necessity to bring together researcher in (i) data collection software infrastructures, including lifestyle sensors (University of Trento, UniTn), (ii) data analysis (Pontifical Catholic University of Rio Grande do Sul, PUCRS), and (iii) issues of trust and privacy in health and lifestyle management (Newcastle University, UNEW). The objective of this project is for these three partners to bring together these three research areas in a synergetic whole. The project there asks for exchange opportunities for early and senior researchers, for research as well as teaching exchanges. This aims at providing mobility and professional experience to the individuals concerned. Equally important, it provides the three research groups the opportunity to broaden their research perspective, drawing on the complementary research foci of the project partners. The teaching exchanges are an important element of broadening the impact of exchange program to all group and department members of the partners.