FACE
AI-Based Analysis of Long-Term ECGs – The evaluation of long-term ECG data is time-consuming and error-prone in medical practice, even though it is crucial for diagnosing cardiac arrhythmias such as atrial fibrillation. The FACE project is developing AI-based methods for the automated analysis of large volumes of ECG data to detect abnormalities more reliably and improve diagnostics. As part of this effort, various AI models are being trained, compared, and optimized for practical use. A particular focus is on privacy-friendly processing directly on-site (edge computing) as well as testing the technology in real-world medical application scenarios.
Project Description
AI-Based ECG Analysis for Cardiology (FACE) – The manual evaluation of long-term ECG recordings takes only a limited amount of time in medical practice, but involves enormous amounts of data: a 24-hour recording corresponds to over 100,000 heartbeats that must be assessed. Abnormalities such as atrial fibrillation, arrhythmias, or other irregularities can provide vital insights. Despite this importance, the error rate for conventional analysis averages about 25 percent.
The “FACE” project addresses this challenge by using artificial intelligence designed to analyze cardiac data automatically and reliably. The focus is on the development, evaluation, and optimization of various AI models trained on real ECG datasets to detect noise, classify arrhythmias, and deliver reliable analysis results in a fraction of the time. In addition to performance, special attention is being paid to a privacy-friendly edge architecture in which sensitive patient data is processed directly on-site without being transmitted to the cloud. Through collaboration with clinical partners, hospitals, and device manufacturers, the project aims to test the integration of AI analysis into everyday medical practice and conduct a feasibility study in a real-world clinical setting.
By utilizing structured data, comparative AI evaluations, and real-world testing, the project improves the reliability of long-term ECG diagnostics, reduces the workload on medical professionals, and simultaneously lays the foundation for future cloud-based and edge-optimized assistance solutions in cardiology.
Project Focus Areas
- AI-assisted ECG analysis: Development and training of AI models for the automated detection and classification of cardiac arrhythmias in long-term ECG data.
- Reliability and Quality Assurance: Systematic comparison and optimization of various AI methods to reduce misinterpretations and improve diagnostic accuracy.
- Privacy-friendly edge architecture: Processing sensitive patient data directly on-site without cloud transmission to meet data protection requirements and enable practical integration into everyday hospital and clinic operations.
Everything at a Glance
-
Duration
January 1, 2024 – December 31, 2026 (Ongoing) -
Research Area
AI and Medicine -
Funding
Funded by the former Federal Ministry for Economic Affairs and Climate Action (BMWK): €430,000
