In emergency rooms, speed is of the essence. According to the regulations on emergency care, emergency staff must assess within ten minutes how urgently patients need to be treated. Especially in phases of high stress, this decision is a challenge under time pressure. Although the emergency services are increasingly transmitting digital protocols, it is difficult to take into account all the information recorded in them.
The researchers in the project are developing an assistance system to support and optimise the initial medical assessment in the emergency room. It analyses data collected by the ambulance service. In doing so, it identifies relevant information and suggests a prioritisation of emergencies with a comprehensible rationale. The hybrid AI assistance system is composed of an expert knowledge-based and a data-driven component. The former offers high precision and reliability and is controlled in a rule-based manner. The data-based approach increases coverage and assurance of results and is trained using machine learning.
The innovative approach lies in the AI-based exploitation of data at the interface of ambulance service and emergency department for a more objective prioritisation of emergencies. A transparent presentation of decisive factors supports a trusting interaction of humans with the AI system.
Partners
DNC Information Management GmbH, Hannover Städtische Kliniken Mönchengladbach GmbH, Mönchengladbach bcmed GmbH, Ulm
