As a major contributor and user of healthcare knowledge, the healthcare enterprise requires intelligent knowledge management strategies to effectively exploit expert-quality healthcare knowledge. In this paper, we discuss a novel knowledge acquisition and representation strategy using healthcare scenarios. This strategy is complemented with an ontology- or thesaurus-based input standardization mechanism to limit the diverse nature of the healthcare experts’ input. We also present in detail an algorithm for healthcare knowledge crystallization that, in addition to simulating the process of annealing, employs the notion of nucleation and growth on healthcare knowledge. The crystallized knowledge potentially undergoes a repair process that employs analogical reasoning to identify less useful knowledge and transform them, with the aid of more established knowledge, into useful ones. We conclude by asserting that the strategies presented do provide an all-rounded approach in our efforts to bring quality healthcare knowledge and services to the masses.
Clinical Pathways (CP) stipulate an evidence-based patient care workflow for a specific disease within a localized setting. We present an ontology-based approach for computerizing CP so that they can be executed at the point-of-care. We present our CP modeling approach that features the integration of multiple localized CP to realize a unified disease-specific CP. The execution of the ontological CP model is achieved by our property abstraction method that assigns functional behaviors to existing semantic properties to facilitate their execution. Using our methods we have developed a prostate cancer management system.
Clinical practice guidelines (CPG) are instrumental in standardizing the quality and delivery of care across different practitioners, departments and institutions. Health practitioners will use current best evidence to validate or supplement their understanding of CPG. This study investigates the potential of supplementing computerized CPG with relevant best evidence sourced from reliable medical literature repositories. A web-enabled Best-evidence Retrieval and Delivery (BiRD) system facilitates autonomous retrieval of pertinent medical literature with respect to user-specified content from a GEM-encoded CPG. A multilevel literature search strategy categorizes the search towards predefined clinical query intentions, and subsequently filters insignificant medical terms. The resultant is a highly focused medical literature search query that is objectively derived from CPG content. The technical architecture comprises existing medical language processing tools and vocabularies, together with newly developed tools to automatically generate optimum search queries, retrieve medical articles from MEDLINE, and embed the articles within XML-based CPG.