Computing: report leaps geographical barriers but stumbles over gender.
Explore the source record for details and available documents.
Biomedical subjects
Publications and source records attributed to Kathleen McKeown.
Explore the source record for details and available documents.
We have developed a summarization system, TAS (Technical Article Summarizer), which, when provided with a patient record and journal articles returned by a search, automatically generates a summary that is tailored to the patient characteristics. We hypothesize that a personalized summary will allow a physician to more quickly find information relevant to patient care. In this paper, we present a user study in which subjects carried out a task under three different conditions: using search results only, using a generic summary and search results, and using a personalized summary with search results. Our study demonstrates that subjects do a better job on task completion with the personalized summary, and show a higher level of satisfaction, than under other conditions.
We report on an evaluation of MAGIC, a system that automatically generates briefings of patient status after coronary bypass surgery, completed in the Cardio Thoracic Intensive Care Unit at New York Presbyterian Hospital. Through enhancements in system design, robustness and speed, we compared information obtained by nurses against two briefings, one automatically generated by MAGIC and one provided by physicians upon the patient's arrival to the ICU. Our results show that MAGIC and the physician briefing provide a substantial increase in the amount of information than is available prior to the patient's arrival and that the information MAGIC provides is accurate. In many aspects, MAGIC out-performs the physician briefing; information is reported earlier and is always available. We conclude that MAGIC provides the CT ICU staff early on with a better assessment of the patient's status than in current practice and allows them to better prepare for the patient's arrival.
This paper describes the comparative evaluation of an experimental automated text summarization system, Centrifuser and three conventional search engines - Google, Yahoo and About.com. Centrifuser provides information to patients and families relevant to their questions about specific health conditions. It then produces a multidocument summary of articles retrieved by a standard search engine, tailored to the user's question. Subjects, consisting of friends or family of hospitalized patients, were asked to "think aloud" as they interacted with the four systems. The evaluation involved audio- and video recording of subject interactions with the interfaces in situ at a hospital. Results of the evaluation show that subjects found Centrifuser's summarization capability useful and easy to understand. In comparing Centrifuser to the three search engines, subjects' ratings varied; however, specific interface features were deemed useful across interfaces. We conclude with a discussion of the implications for engineering Web-based retrieval systems.