This study explores the use of AI-based simulations to support healthcare staff in complex decision-making scenarios. The aim is to improve workflow efficiency and to develop preventive strategies that strengthen the ability of clinical staff to manage emergencies safely. In doing so, the study seeks to enhance patient safety while reducing staff workload. The findings will contribute to sustainable solutions for key healthcare challenges such as workforce shortages, increasing workload, and mai
Conditions
Interventions
Group 1: The intervention group in this study consists of participants who receive a KI-supported debriefing—that is, a debriefing automatically generated by a Large Language Model (LLM) based on comm
Sponsors
Helios Universitätsklinikum Wuppertal
Eligibility
Sex/Gender
All
Inclusion criteria
Inclusion criteria: Written informed consent Medical students from the 6th semester onward from Germany, Austria, and Switzerland Healthcare professionals from the pediatric department Compliance with and consent to the technical requirements (e.g., wearable device, audio recording)
Exclusion criteria
Exclusion criteria: Missing informed consent Technically unusable data (e.g., corrupted or failed recordings) Participant withdrawal from the study
Design outcomes
Primary
| Measure | Time frame |
|---|---|
| Development and Evaluation of an AI-Based Feedback System Using Communication and Stress Data to Complement Traditional Debriefings; Integration of Physiological Parameters (HRV/EDA) to Analyze Individual Stress Responses. | — |
Secondary
| Measure | Time frame |
|---|---|
| Development and Evaluation of an AI-Based Feedback System Using Communication and Stress Data to Complement Traditional Debriefings. Integration of Physiological Parameters (HRV/EDA) to Analyze Individual Stress Responses. | — |
Countries
Germany
Contacts
Public ContactKai Oliver Hensel
Helios Universitätsklinikum Wuppertal
Outcome results
None listed