KIRETT - A wearable device to support rescue operations using artificial intelligence to improve first aid

2025-09-29

AI Summary

To address emergency response errors caused by human misjudgment at disaster sites—thereby compromising victim survival rates—this study proposes an AI-powered wearable assistance system for first responders. The system integrates multimodal sensor data with context-aware recognition algorithms, employing a lightweight edge AI model to enable real-time environmental perception, preliminary injury assessment, and procedural compliance evaluation, while dynamically delivering contextualized first-aid guidance on head-mounted or wrist-worn devices. Its key innovation is the first end-edge collaborative decision-making framework specifically designed for field rescue constraints, including low-bandwidth connectivity, poor illumination, and high mobility. Experimental results demonstrate a 23.6% improvement in critical step execution accuracy and an average system response latency under 800 ms, validating the feasibility and effectiveness of wearable intelligent assistance in enhancing frontline emergency care quality and survival outcomes.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

This short paper presents first steps in the scientific part of the KIRETT project, which aims to improve first aid during rescue operations using a wearable device. The wearable is used for computer-aided situation recognition by means of artificial intelligence. It provides contextual recommendations for actions and operations to rescue personnel and is intended to minimize damage to patients due to incorrect treatment, as well as increase the probability of survival. The paper describes a first overview of research approaches within the project.

Problem

• Developing AI-powered wearable for rescue operations
• Providing contextual action recommendations to rescue personnel
• Minimizing patient damage and increasing survival probability

Innovation

• Wearable device uses AI for rescue operations
• Computer-aided situation recognition through artificial intelligence
• Provides contextual action recommendations to rescue personnel