Acquiring patient data by an intelligent interface agent with medicine-related common sense reasoning

The first process in medical diagnosis is gathering useful patient data fro m physical examination. How to capture proper and correct morbidity during a consultation is a very difficult task. It usually takes many years of cli nical training and practice for a physician to successfully do this. This p aper proposes an intelligent interface agent to alleviate the problem. It i ncludes an hypermedia human-machine interface, a medicine-related common se nse and past Q&A scenarios repository, and a data analyst. The hypermedia i nterface provides a friendly human body image for easy patient data input. The data analyst, with the help of medicine-related common sense and past Q &A scenarios, supports the determination of proficiency level of the user; verification of completeness, consistency, and rationality of the input dat a; and generation of complete patient data. Knowing the proficiency level o f a user facilitates the system in soliciting relevant patient's data. Veri fication of the input data against the common sense allows the system to gu arantee their validity. Generation of complete patient data is carried out by hypothesizing a major disease using the common sense, followed by produc ing more diseases through the interaction of the involved systems, and comp leted by adding those symptoms that are decided to be significant in the di scovered diseases into the patient record. The intelligent symptoms thus ca n correctly gather high-quality patient data from all user levels. (C) 1999 Elsevier Science Ltd. All rights reserved.