EBH 2014 - AAAI Fall Symposium on Expanding the Boundaries of Health Informatics Using AI: Making Personalized and Participatory Medicine A Reality

The 20th century laid a foundation of evidence-based medicine that relied on populations and large groups of patients to derive generalized results and observations that were applied to (mostly passive) patients. Yet, the 21st century is shaping up as a time where the patient and personalized health data is the driver of health care innovation and delivery. This is a significant shift from the paradigm where physicians made patient treatment decisions based on their clinical experience and by evidence-based results derived from general population studies. The rise of novel methods and tools for collecting and storing large amounts of personalized health data (for example from various types of electronic health records and from new sensors) has made vast amounts of data available. Several projects have shown that sharing this data offers multiple advantages to both physicians and patients, enabling them to globally identify similar patient cases and discover successful therapies from other patients and physicians. Access to this information, from a multitude of data channels, allows for shared decision making that enables physicians to personalize care decisions and, at the same time, supports patients' engagement in their own care. This paradigm shift, termed participatory medicine, will eventually lead to improved patient outcomes and reduced healthcare costs but significant challenges must be addressed before its full promise is realized.
In addition to providing physicians with the necessary tools to effectively take advantage of available medical data, patients will need guidance so they can embrace their new roles as active participants in their care. The physician-patient relationship will transition from one- to two-way communication where patient treatment becomes a feedback rather then feed-forward process. Similarly, information technology will need to evolve to improve communication, collaboration, and teamwork between patients, their families, and care teams involving practitioners from different fields and specialties. All of these changes require novel solutions and the AI community is well positioned to provide both theoretical- and application-based methods and frameworks.
The goal of this symposium is to focus on creating and refining AI-based approaches that (1) help patients (and families) participate in the care process, (2) improve patient participation and (3) help physicians utilize this participation in order to provide high quality and efficient personalized care. The extraction, representation, and sharing of health data, patient preference solicitation, personalization of generic therapy plans, adaptation to care environments and available health expertise, care team coordination, and making medical information accessible to patients are some of the relevant problems in need of AI-based solutions.
Topics
This symposium focuses on AI-based methodological and application contributions in health informatics and its aim is to foster opportunities for collaborative research within a multidiscipline research community that offers expertise in medicine, bioinformatics, computer and information science. Topics of interest include but are not limited to the following:
Methods for knowledge extraction (leveraging social, population, clinical data) and personalization via intelligent predictive analytics
Design of integrated health information systems to accelerate the discovery of health knowledge, and the design of personalized care systems (including telehealth and ambient assisted living) to disseminate the discovered knowledge and enable patients to provide feedback to physicians about their ongoing care
Innovative use of social media for patients' education, empowerment and engagement
Supporting personalized care delivery by interdisciplinary health care teams by modeling patient-focused workflows and supporting their adaptation (setting, experience) and execution
Methods to improve randomized clinical trails or new paradigms for more effective organization and execution of bench-to-bedside processes
Decision support systems for eliciting patient preferences and for shared decision making by health care providers and patients