Virtual Intelligent Agents to Train Abilities of Diagnosis in Psychology and Psychiatry

Abstract

The diagnostic interview in Mental Health Sciences involves a series of abilities that require sound training. This training should be provided under guidance from a professor in controlled settings that mimic real-life situations as closely as possible, but in the initial stages the interaction with real patients should be avoided. Precisely, the objective of this study was to develop a system constructed with artificial intelligence and 3D design applications that creates an environment in which the trainee can interact with a group of simulated patients. These virtual patients are realistic objects that can interact in real-time with the user using a series of parameters that define their verbal, emotional and motor responses. From them the trainee must obtain the data needed to make an accurate diagnosis. The high level of flexibility and interactivity increases the trainees’ sensation of participating in the simulated situation, leading an improving of the learning of the skills required.