NotesFAQContact Us
Search Tips
ERIC Number: ED459839
Record Type: RIE
Publication Date: 2001-Jun
Pages: 12
Abstractor: N/A
PERSIVAL, a System for Personalized Search and Summarization over Multimedia Healthcare Information.
McKeown, Kathleen R.; Chang, Shih-Fu; Cimino, James; Feiner, Steven K.; Friedman, Carol; Gravano, Luis; Hatzivassiloglou, Vasileios; Johnson, Steven; Jordan, Desmond A.; Klavans, Judith L.; Kushniruk, Andre; Patel, Vimla; Teufel, Simone
This paper reports on the ongoing development of PERSIVAL (Personalized Retrieval and Summarization of Image, Video, and Language), a system designed to provide personalized access to a distributed digital library of medical literature and consumer health information. The goal for PERSIVAL is to tailor search, presentation, and summarization of online multimedia information to the end user, whether patient or healthcare provider. PERSIVAL utilizes the online patient records at New York Presbyterian Hospital as a sophisticated, pre-existing user model that can aid in predicting user interests. For the healthcare provider, the approach facilitates finding literature relevant to the specific patient under care; for the healthcare consumer, the approach facilitates finding and understanding information relevant to his or her medical situation. This paper presents the system's architecture and then discusses the components that are being developed. These include a user query component, which allows inference of meaningful questions given the clinical context, providing relevant information from the context for search; search over heterogeneous, distributed sources, re-ranking results by matching against the patient record; presentation of results to highlight information that is relevant to the patient, including summarization of textual and video resources along with definitions of unfamiliar terms; and interaction with the results through a highly interactive, multimodal, Web-based thin-client architecture. The researchers have begun preliminary experiments with end users that can provide specific information on how to personalize search and summarization. (Contains 33 references.) (AEF)
Association for Computing Machinery, 1515 Broadway, New York NY 10036. Tel: 800-342-6626 (Toll Free); Tel: 212-626-0500; e-mail: For full text:
Publication Type: Reports - Descriptive; Speeches/Meeting Papers
Education Level: N/A
Audience: N/A
Language: English
Sponsor: National Science Foundation, Arlington, VA.
Authoring Institution: N/A
Note: In: Proceedings of the ACM/IEEE-CS Joint Conference on Digital Libraries (1st, Roanoke, Virginia, June 24-28, 2001). For entire proceedings, see IR 058 348. Figure may not reproduce well.