A distributed environment for the integration of multiple high-performance decision support systems into clinical workflow

摘要: Current studies conclude that clinical decision support systems can help reduce serious medical errors. The importance of Causal Probabilistic Networks (CPNs) for constructing such is already well-known. However, the computational complexity probabilistic inference, which results in unacceptably high response times, hinder acceptance and integration into clinician workflow. This paper investigates optimization parallelization potential complex CPN-based evaluates implementing a parallel, performance version an existing system concerning proper antibiotic treatment therapy. Furthermore, it discusses distributed computing techniques making multiple available at time location making, by exploiting resources residing inside, as well outside hospital walls optimally.