Bryan P. Bergeron

Learn More
Serious games are being actively explored as supplements to and, in some cases, replacement for traditional didactic lectures and computer-based instruction in venues ranging from medicine to the military. As part of an intelligent tutoring system (ITS) for nuclear event first responders, we designed and evaluated two serious games that were integrated with(More)
Really simple syndication (RSS) feeds and aggregators are indispensable tools for clinicians who need to stay abreast of the latest clinical research, public health publications, and economic factors that might affect their practice. RSS enables clinicians with a compatible browser, such as Mozilla Firefox, or other desktop aggregator, to view headlines and(More)
Recent performance breakthroughs in affordable, large vocabulary, speaker independent voice recognition systems have rekindled widespread interest in using voice recognition technology to enhance the palatability and effectiveness of clinician-mediated computing. However, even if industry fully addresses the formidable hardware requirements, less than(More)
HeartLab and EkgLab are two simulation-based programs designed to teach medical students the essentials of the auscultatory cardiac examination and of electrocardiogram interpretation, respectively. The issues considered throughout the development of these projects, namely implementation language selection, program architecture, simulation design, patient(More)
Investment in information technology accounts for an increasingly large component of the cost of modern health care. In most businesses, a quantitative return on investment analysis forms the basis for decisions regarding technology investment. As a whole, the medical community lags behind in the quantitative analysis of the benefits of information(More)
The Internet is not only changing the face of computing but is redefining the manner in which medical information is stored, manipulated, and disseminated. However, before patients and clinicians can come to trust the Internet as much as traditional paper medical records, the issue of data security must be adequately addressed. Every clinician who works(More)
For neural networks to develop good internal representations for pattern mapping, noise in the training set data must be controlled. Because of the many difficulties associated with manually validating training data, we have focused on using decision table techniques as a practical, domain-independent means of optimizing training set formulation. Decision(More)
In computer-based medical education, there is frequently a need to present students with pictorial data representative of the natural variation associated with disease presentations as well as the progression of disease within an individual. Because of the difficulty in acquiring such data, image acquisition is often the most resource-intensive phase of(More)