AN INTELLIGENT INTERACTIVE SYSTEM FOR DELIVERING INDIVIDUALIZED INFORMATION TO PATIENTS

This paper is a report on the first phase of a long-term, interdiscipl inary project whose goal is to increase the overall effectiveness of p hysicians' time, and thus the quality of health care, by improving the information exchange between physicians and patients in clinical sett ings. We are focusing on patients with long-term and chronic condition s, initially on migraine patients, who require periodic interaction wi th their physicians for effective management of their condition. We ar e using medical informatics to focus on the information needs of patie nts, as well as of physicians, and to address problems of information exchange. This requires understanding patients' concerns to design an appropriate system, and using state-of-the-art artificial intelligence techniques to build an interactive explanation system. In contrast to many other knowledge-based systems, our system's design is based on e mpirical data on actual information needs. We used ethnographic techni ques to observe explanations actually given in clinic settings, and to conduct interviews with migraine sufferers and physicians. Our system has an extensive knowledge base that contains both general medical te rminology and specific knowledge about migraine, such as common trigge r factors and symptoms of migraine, the common therapies, and the most common effects and side effects of those therapies. The system consis ts of two main components: (a) an interactive history-taking module th at collects information from patients prior to each visit, builds a pa tient model, and summarizes the patients' status for their physicians; and (b) an intelligent explanation module that produces an interactiv e information sheet containing explanations in everyday language that are tailored to individual patients, and responds intelligently to fol low-up questions about topics covered in the information sheet.