Abstract: An electronic medical record (EMR) analysis machine automatically clusters electronic medical records to produce an initial EMR analysis model and to identify high-value EMR documents such that human analysts can focus effort on labeling only high-value EMR documents to iteratively and extremely efficiently train an EMR analysis model. High-value sample EMR documents are identified as those whose membership in one or more clusters is most ambiguous, i.e., nearest the cluster boundary.

Abstract: A content provider manager has been develop for use in an information services such as a portal or desktop application to provide for “pluggable” content that may be modified simply through changes to the set of content provider components encoded in a repository therefor. Content providers served to clients (e.g., browsers) by an information service are dynamically loaded and instantiated within the execution environment of the information service in correspondence with changes in the repository. In some configurations, a single repository provides a mechanism for additions to, removals from and/or changes in the set of content providing components served by multiple information service installations. Although the techniques described are more generally applicable, they are particularly useful in implementations of dynamic content applications, including user customizable web portal and personalized desktop, e.g.