This paper presents a decentralized safety concept for networked intensive care setups, for which a decentralized network of sensors and actuators is realized by embedded microcontroller nodes. It is evaluated for up to eleven medical devices in5 a setup for automated acute respiratory distress syndrome (ARDS) therapy. In this contribution we highlight a blood pump supervision as exemplary safety measure, which allows a reliable bubble detection in an extracorporeal blood circulation. The10 approach is validated with data of animal experiments including 35 bubbles with a size between 0.05 and 0.3 ml. All 18 bubbles with a size down to 0.15 ml are successfully detected. By using hidden Markov models as statistical method the number of15 necessary sensors can be reduced by two pressure sensors.