Deutsche Telekom, the Fraunhofer Institute for Intelligent Analysis and Information Systems (IAIS), and Kliniken der Stadt Köln are working together to develop an artificial intelligence (AI) agent designed to support medical teams in emergency trauma rooms. The AI system is intended to help organize information by medical priorities and provide a framework for treatment documentation.
In hospital trauma rooms, where up to ten doctors and nurses may work together on critically injured patients, the partners are developing a real-time display system powered by AI. This system listens to team conversations during simulations, extracts relevant information, categorizes it according to medical priorities, and updates this data continuously. The aim is to reduce the workload for trauma teams, decrease errors, and improve patient outcomes.
The application can operate either on dedicated hospital servers or via cloud infrastructure, ensuring that all data remains within Europe in compliance with European data protection standards. Development of a prototype began in September as part of a one-year project using simulated trauma room scenarios. The core technology is based on a modular software toolkit for AI solutions.
The new AI tool is expected to record conversations automatically, analyze them in real time, enhance the extracted information, and present it visually in line with established protocols such as ABCDE—Airways, Breathing, Circulation, Disability (neurological status), and Exposure. For example, if a doctor notes a specific breathing sound during treatment, the AI will categorize this observation and display live status updates using an easy-to-read format. The agent also transfers relevant details into forms required for documentation and quality assurance.
This initiative is part of the European IPCEI-CIS funding program aimed at creating standardized cloud-edge infrastructure across Europe. The system is built for resilience; it can run both locally offline using specialized hardware like NVIDIA’s DGX Spark super-minicomputer or through Deutsche Telekom’s Open Telekom Cloud (OTC). Key components—including lightweight AI models and automated workflows—are designed for reuse in other similar infrastructures.
Stefan Rüping of Fraunhofer IAIS stated: “With the development of a versatile multi-agent framework and its adaptation to the demanding requirements of emergency medicine, we are laying the foundation for relieving medical teams during the treatment of critically injured patients. Key elements include a well-designed system architecture, the integration of trusted components for speech processing and data management, and edge capabilities that enable on-site operation.”
Jerome Defosse from Kliniken der Stadt Köln added: “By integrating medical expertise and realistic trauma room simulations, we are bridging the gap between research and practice, contributing to the potential for AI agents to bring tangible advancements to emergency care in the trauma room.”
Ferri Abolhassan from Deutsche Telekom commented: “AI is already saving lives today. Our AI agent for emergency medicine serves as a model for other industries as well. With this practical solution, we demonstrate the value of sovereign digital infrastructure for both the economy and the greater good.”
Additional advisory support comes from Bundeswehr Hospital Berlin and Florence Nightingale Hospital Düsseldorf. A fully operational prototype capable of offline use within hospitals is targeted for completion by summer 2026.
Thorsten Tjardes from Bundeswehr Hospital Berlin said: “For us, the resilience of the AI assistance system is the top priority – it must function with absolute reliability and security, both in the cloud and locally offline, to meet the rigorous demands of emergency medicine.”
Martin Pin from Florence Nightingale Krankenhaus Düsseldorf noted: “As an advisory partner, we contribute our expertise to ensure that this innovative AI technology is designed with practical applicability in mind, achieving the optimal balance between technical excellence and usability in clinical operations.”
The current project builds upon previous work funded by Germany’s Federal Ministry of Health under “TraumAInterfaces” with further support from IPCEI-CIS.
The AI Foundation Services platform enables secure access to open-source and commercial AI models operated by T-Systems in their own data centers under strict security standards.
IPCEI-CIS seeks to establish a unified European digital infrastructure through edge-cloud computing technologies involving industry leaders such as SAP, Siemens, Bosch, Telefónica, Orange, Airbus—and now Deutsche Telekom—collaborating across twelve EU member states.
T-Systems operates globally with over 26 countries represented by more than 26,000 employees generating annual revenues exceeding EUR 4 billion.
Fraunhofer IAIS has around 350 employees specializing in applied research on artificial intelligence across multiple locations in Germany.
Kliniken der Stadt Köln treats about 159,500 outpatients annually at three locations that will eventually be consolidated into one healthcare campus at Merheim; its Merheim Hospital manages approximately 600 trauma cases each year.
