Reasoning and Risk Assessment based on Real-Time Physiological Simulations and Dependable Vital Parameter Monitoring

We present a novel approach for dependability analysis of medical devices. As focus, we considered vital pa- rameter monitoring. The basic strategy relies on using me- thods from system theory. For the first time not only the tech- nical device but also the patient is taken into consideration. Including the patient requires prediction of physiology which is achieved by a real-time physiological simulation in a conti- nuous time domain, whereby one of the main ingredients is a temporal reasoning element. The quality of the reasoning is expressed by a dependability analysis strategy. Thereby, ano- malies are expressed as differences between simulation and real world data. Deviations are detected for current and they are forecasted for future points in time. By this method, pa- tient specific differences in terms of physiological reactions are described, allowing early detection of critical states. The inter- play of the different elements and the consequences are ex- plained in a realistic model.