Smart recommendation services in support of patient empowerment and personalized medicine

Medicine is undergoing a revolution that is transforming the nature of healthcare from reactive to preventive. The changes are catalyzed by a new systems approach to disease which focuses on integrated diagnosis, treatment and prevention of disease in individuals. This will replace our current mode of medicine over the coming years with a personalized predictive treatment. While the goal is clear, the path is fraught with challenges. The p-medicine EU project aspires to create an infrastructure that will facilitate this translation from current medical practice to personalized medicine. This Chapter focus on current research activities related to the design and implementation of an intelligent patient empowerment platform and its services. The focus of our work concerns the nature of the interaction between health institutions and individuals, particularly the communicative relation between physicians and patients, the ways of exchanging information, the nature of the information itself and the information assimilation capabilities of the patients. Our practical focus is the domain of cancer patients, whether in normal treatment or participating in clinical trials. The ultimate objective is to implement a smart environment (recommender system) able to act as a decision support infrastructure to support the communication, interaction and information delivery process form the doctor to the patient. A prerequisite of personalized delivery of information and intelligent guidance of the patient into his/her treatment plans is our ability to develop an appropriate and accurate profile of the user. In the p-medicine project we focus on modeling and profiling the psycho-cognitive capabilities of the patient based on questionnaires and other information features and behaviors extracted from a personal health record of the patient. In this chapter we will provide a systematic review of user profiling techniques and approaches and present our results in developing a psycho-cognitive profile of the user/patient. Subsequently we will describe the details and challenges of implementing the recommendation system and services using a combination of methods to counter-balance the intrinsic weaknesses in various algorithmic approaches. We will review solutions that have combined demographic user classes and content-based filters using implicit behavior and explicit preferences, collaborative filtering and demographic or collaborative filtering and knowledge-based filters. Finally, our approach will be fully described, which uses an adaptive user interface for the presentation of the e-consent, an ontology and a semantic web rule language to formally describe patient choices, and a reasoning engine to handle access and personalized delivery of pertinent disease related information.