Albert "Skip" Rizzo, PhD, a psychologist at University of Southern California, is working on a project that could possibly change the future of psychology training: creating virtual patients. He draws upon artificial intelligence research to design realistic-looking and –acting patients that will be used primarily in the training of new clinicians. By using principles from the Diagnostic and Statistical Manual of Mental Disorders (Fourth Edition) and input gathered from clinicians and users, the team is programming these AI patients to respond to questions with realistic answers that will help students to learn the right information from real patients. The “patients” are viewed on a computer screen or are projected onto a screen to be life-sized. The project team has already created two patient models, one is a treatment-resistant boy named Justin and the other is a girl programmed as the victim of a sexual assault named Justina. "I think at first people say, 'This is whacked,'" says Rizzo, "but all of a sudden when they get a legitimate answer to a question or two or three, they start acting like it's the real thing." He wants to someday create models of patients that represent all diagnoses in the manual of mental disorders and have students use them regularly as training tools. "Based on a person's training needs, you could then drag and drop any model onto a specific patient," he says.