19.12.2025

A joint project by Deutsche Telekom, Fraunhofer IAIS and Merheim Hospital is developing AI agents to support doctors and nurses in hospital trauma rooms. By structuring spoken medical information in real time, the system aims to reduce workload, support clinical decision-making and improve documentation during the acute care of critically injured patients.

Illustration of a trauma room scenario showing doctors and nurses treating a patient; Copyright: Fraunhofer IAIS, GPT-5

AI agents are designed to support trauma teams by structuring critical information and assisting clinical workflows during emergency care.

Products and exhibitors related to this topic

Exhibitors and products related to this topic can be found in the database of MEDICA:

More topic-related exciting news from the editors of MEDICA-tradefair.com

In hospital emergency departments, trauma rooms are environments where every second counts. Up to ten doctors and nurses work simultaneously to stabilize critically injured patients. Against this background, Deutsche Telekom, the Fraunhofer Institute for Intelligent Analysis and Information Systems (IAIS), and Merheim Hospital of Kliniken der Stadt Köln are developing an AIbased real-time display system. According to the Fraunhofer IAIS, the solution is designed to capture spoken communication and organize medical information according to defined priorities.

An AI agent listens to conversations among the trauma team, extracts relevant details and continuously updates a structured overview. At the same time, all data are recorded for treatment documentation, supporting both clinical workflows and quality assurance.

Reducing pressure on medical teams

In trauma rooms, essential information is exchanged verbally during handover from emergency services, throughout treatment and when patients are transferred to intensive care units or operating rooms. Diagnostics and therapy take place in parallel, leaving little time for manual documentation.

The AI system automatically records and analyzes conversations in real time, enriches the information and presents it in a structured visual format. This is intended to support doctors and nurses, reduce the risk of errors and improve transparency in highly dynamic situations.

ABCDE protocol as clinical backbone

Trauma care follows the ABCDE protocol, which prioritizes life-threatening conditions:

Airway
Breathing
Circulation
Disability
Exposure

The AI agent identifies mentioned findings, measures and decisions and assigns them to the appropriate category. If, for example, a doctor reports a “coarse bubbling sound” during breathing, the system links this information to the relevant ABCDE category and displays the current status using a trafficlight logic. The data are then automatically transferred into documentation and quality management forms.

Secure cloud-edge infrastructure

The project is part of the European IPCEI-CIS funding program and focuses on secure cloud-edge computing in healthcare. The system can operate locally in hospitals without an internet connection or via the Open Telekom Cloud, ensuring compliance with European data protection standards.

“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,” says Stefan Rüping, head of department at the Fraunhofer IAIS.

Jerome Defosse, MD, Kliniken der Stadt Köln, adds: “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.”
A fully operational prototype is expected to be available in hospitals by summer 2026.

MEDICA-tradefair.com; Source: Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS

More about the Fraunhofer IAIS at: www.iais.fraunhofer.de/en