Procedural knowledge

2011 02 24 NYU CHIBI Yuval Shahar MD, PhD: Integrating Proc & Decl Clinical Guideline Knowledge

• Report rights infringement
• published: 16 Mar 2012
• views: 210

Clinical Guidelines are a major tool in improving the quality of medical care. However, most guidelines are in free text, not in a formal, executable format, and are not easily accessible to clinicians at the point of care. We have designed and implemented a Web-based, modular, distributed architecture, the Digital Electronic Guideline Library (DeGeL), which facilitates gradual conversion of clinical guidelines from text to a formal representation in chosen target guideline ontology. The architecture supports guideline classification, semantic markup, context-sensitive search, browsing, run-time application to a specific patient at the point of care, and retrospective quality assessment by a clinical organization. The DeGeL procedural-knowledge hybrid meta-ontology includes elements common to all guideline ontologies, such as semantic classification and domain knowledge; it also includes four content-representation formats: free text, semi-structured text, semi-formal representation, and a formal representation. These formats support increasingly sophisticated computational tasks. We have evaluated the accuracy and completeness of the specification of the semi-structured and semi-formal medical procedural knowledge by clinical editors, with encouraging results. Furthermore, the declarative knowledge embedded in the clinical guideline's formal representation can also be exploited to support the tasks of interpretation, summarization, visualization, explanation, temporal data mining, and interactive exploration, in a context-sensitive manner, of the patient's time-oriented raw data and the multiple levels of higher-level, interval-based concepts that can be abstracted from these data. The exploration can be performed for either a single patient record or for multiple records, thus supporting both individual-patient monitoring and clinical research. I will therefore breifly introduce the KNAVE-II and VISITORS tools for visual exploration of individual and multiple patient records, respectively, and some of the results of their evaluation. Finally, an integration of procedural and declarative guideline-based knowledge can be used for additional tasks, such as automated quality assessment. In this task, the degree to which the clinician adheres to the guideline, i.e., the match between the temporal pattern generated by the clinician's actions and the the pattern implied by a correct application of the guideline, is of prime interest. This partial match can be computed using fuzzy temporal logic, and can be shown to produce results similar to those of a medical domain expert.