Files
Abstract
A clinical question is a question that a health care provider may have, during a patient encounter in a clinical setting. This thesis describes the design and implementation of a text classification system to automatically classify a clinical question into various categories based on a hierarchical taxonomy designed by researchers. The system implements natural language processing and machine learning based techniques to automatically classify a clinical question. This question classification system would be integrated into an Evidence-Based Point-of-Care clinical decision support system providing concise, practical, readily accessible information from various resources to facilitate fast and accurate decision making. The system would analyze clinical questions on both the syntactic and semantic level (extraction of noun phrases and nouns, identifying them like disease/syndrome using ontology). This study presents an initial prototype and the long term goal of the project is to classify all types of clinical questions with good results.