Search

This paper briefly describes four cognitively-related aspects of modeling a virtual patient: interoception, decision-making, natural language processing and learning. These phenomena are treated within the Maryland Virtual Patient simulation and training environment.

The patient authoring interface for each disease in the Maryland Virtual Patient simulation environment reveals the conceptual substrate of the disease model. Revealing the disease model to the community both explains how the interactive simulations work and invites collaboration from the wider community.

The Maryland Virtual Patient (MVP) Project seeks to create realistically functioning virtual humans endowed with automatic physiological and cognitive function that can be used in the training of medical personnel. Physiologically, the state of an MVP changes in response to internal pathophysiological stimuli and external stimuli, the latter initiated by either by the patient or the trainee. Cognitively, the MVP can communicate with trainees about current symptoms, lifestyle, history, adherence to prescribed treatments, etc. We will demonstrate simulation in the MVP environment using the example of patients suffering from gastroesophageal reflux disease (GERD).