Dictionaries are rich sources of detailed semantic information, but in order to use the information for natural language processing, it must be organized systematically.

Objective Early detection of Heart Failure (HF) could mitigate the enormous individual and societal burden from this disease. Clinical detection is based, in part, on recognition of the multiple signs and symptoms comprising the Framingham HF diagnostic criteria that are typically documented, but not necessarily synthesized, by primary care physicians well before more specific diagnostic studies are done. We developed a natural language processing (NLP) procedure to identify Framingham HF signs and symptoms among primary care patients, using electronic health record (EHR) clinical notes, as a prelude to pattern analysis and clinical decision support for early detection of HF. Design We developed a hybrid NLP pipeline that performs two levels of analysis: (1) At the criteria mention level, a rule-based NLP system is constructed to annotate all affirmative and negative mentions of Framingham criteria. (2) At the encounter level, we construct a system to label encounters according to whether any Framingham criterion is asserted, denied, or unknown. Measurements Precision, recall, and F-score are used as performance metrics for criteria mention extraction and for encounter labeling. Results Our criteria mention extractions achieve a precision of 0.925, a recall of 0.896, and an F-score of 0.910. Encounter labeling achieves an F-score of 0.932. Conclusion Our system accurately identifies and labels affirmations and denials of Framingham diagnostic criteria in primary care clinical notes and may help in the attempt to improve the early detection of HF. With adaptation and tooling, our development methodology can be repeated in new problem settings.

Background The electronic health record contains a tremendous amount of data that if appropriately detected can lead to earlier identification of disease states such as heart failure (HF). Using a novel text and data analytic tool we explored the longitudinal EHR of over 50,000 primary care patients to identify the documentation of the signs and symptoms of HF in the years preceding its diagnosis. Methods and Results Retrospective analysis consisting of 4,644 incident HF cases and 45,981 group-matched controls. Documentation of Framingham HF signs and symptoms within encounter notes were carried out using a previously validated natural language processing procedure. A total of 892,805 affirmed criteria were documented over an average observation period of 3.4 years. Among eventual HF cases, 85% had at least one criterion within a year prior to their HF diagnosis (as did 55% of controls). Substantial variability in the prevalence of individual signs and symptoms were found in both cases and controls. Conclusions HF signs and symptoms are frequently documented in a primary care population as identified through automated text and data mining of EHRs. Their frequent identification demonstrates the rich data available within EHRs that will allow for future work on automated criterion identification to help develop predictive models for HF.

A fundamental aspect of knowledge management is capturing knowledge and expertise created by knowledge workers as they go about their work and making it available to a larger community of colleagues. Technology can support these goals, and knowledge portals have emerged as a key tool for supporting knowledge work. Knowledge portals are single-point-access software systems intended to provide easy and timely access to information and to support communities of knowledge workers who share common goals. In this paper we discuss knowledge portal applications we have developed in collaboration with IBM Global Services, mainly for internal use by Global Services practitioners. We describe the role knowledge portals play in supporting knowledge work tasks and the component technologies embedded in portals, such as the gathering of distributed document information, indexing and text search, and categorization; and we discuss new functionality for future inclusion in knowledge portals. We share our experience deploying and maintaining portals. Finally, we describe how we view the future of knowledge portals in an expanding knowledge workplace that supports mobility, collaboration, and increasingly automated project workflow. A ll human work, even the most physical labor, involves cognitive capabilities, but the hallmark of human work in the latter part of the twentieth century emphasizes knowledge work-solving problems and accomplishing goals by gathering, organizing, analyzing, creating, and synthesizing information and expertise. Knowledge work is performed by individuals who belong to communities of interest, where knowledge is shared and accumulated. Knowledge management (KM) refers to the methods and tools for capturing, storing, organizing, and making accessible knowledge and expertise within and across communities. Communities of interest may be scientific, academic, business-oriented, or government-based. We focus here on the corporate environment, since this is where KM is most self-consciously addressed, and where supporting technologies are expanding most rapidly. At the broadest level (to paraphrase Prusak 1), KM refers to all the tools, technologies, practices, and incentives deployed by an organization to "know what it knows" and to make this knowledge available to people who need to know it when they need to know it. At the individual or team level, the KM flow is a cycle in which solving a problem leads to new knowledge, initially tacit (that is, known but unexpressed), and then made explicit when experiences are documented, distributed, and shared (via databases, e-mail, or presentations). Once explicit, the knowledge is used by others for solving new problems. 2,3 The application of the explicit knowledge to a new problem creates new tacit knowledge, with the potential of initiating a new KM cycle. In this general cycle lie a host of technical, social, and humancomputer interaction issues. In this paper we focus on the technology and, specifically, on what have come to be called knowledge portals.

The experimental EPISTLE system is intended to provide "intelligent" functions for processing business correspondence and other texts in an office environment. This paper focuses on the initial objectives of the system: critiquing written material on points of grammar and style. The overall system is described, with some details ofthe implementation, the user interface, and the three levels of processing, especially the syntactic parsing of sentences with a computerized English grammar.The long-term objectives of the EPISTLE project are to provide office workers, particularly middle-level managers, with a variety of application packages to help them interact with natural language texts. Initially we are focusing on business letters and on the first of two classes of applications. This first class will provide services for the author, initially furnishing critiques of a draft of a letter or other text, and eventually helping him write an initial draft based on a terse statement of what he wants to say. The second class of applications will deal with incoming texts, synopsizing letter contents, highlighting portions known to be of interest, and automatically generating index terms based on conceptual or thematic characteristics rather than key words.In its current experimental form, the EPISTLE system addresses only the tasks of grammar and style checking of texts written in English. Grammar checking deals with such errors as lack of number agreement between subject and verb; style checking points out such