Internet as a knowledge base for medical diagnostic assistance

The paper addresses the determination of the context of medical analysis case studies. A model of context recognition was used to extract information from actual medical cases. The goal of the research was to examine a method for encapsulating a patient's medical history and current situation into keywords for the physician performing the analysis. The algorithm yielded good results in the analysis of the medical case studies and the model was able to determine the correct diagnosis in some of the cases. An advantage of the model is the use of the Internet as an existing database that is constantly updated for possible symptoms and diagnoses. The model can serve as a decision support system for a physician presented with a patient's medical record. The model can assist in identifying some of the key issues in a patient's medical records or can suggest a possible diagnosis. The model can therefore assist the physician in his review of a patient's medical records. (c) 2006 Elsevier Ltd. All rights reserved.