AG Vieluf
-
The AI-based Telemonitoring research group focusses on the integration of artificial intelligence (AI) with clinical practice. As telemedicine continues to evolve, the amount of valuable patient data has significantly increased, opening new opportunities for AI-driven insights to enhance patient care. Our research aims to leverage these data streams, combining cutting-edge AI techniques with clinical expertise.
Our team focuses on applications in cardiology but also collaborates across multiple disciplines, including neurology, psychology, sport science, bioinformatics, statistics, and computer science. This interdisciplinary approach enables us to conduct both foundational and applied research, focusing on the practical application of AI in real-world clinical settings.
Key research areas include:
- AI for Wearables: Utilizing machine learning to analyze data from wearable devices, providing predictive insights for the early detection and management of cardiovascular and neurological diseases.
- Multimodal ML for Medicine: Using machine learning to analyze clinical data of different modalities including electronic health records (EHRs), medical imaging, wearable sensors, and genomic data.
- Cardiovascular Image Analysis: Developing AI models to improve the accuracy and efficiency of cardiovascular imaging, supporting precise diagnostics and personalized treatment plans.
- Explainable AI in Clinical Practice: Advancing explainable AI techniques to ensure that machine learning models provide transparent, interpretable results that clinicians can trust and apply in decision making.
We specialize in using a variety of advanced machine learning methods, with a strong emphasis on explainability and reproducibility ensuring that our methodologies can be easily replicated and scaled for use in different clinical environments. Our research aims at integrating AI tools seamlessly into clinical workflows, offering user-friendly solutions that align with the needs of healthcare providers and patients.
-
Goelz, Christian, Solveig Vieluf, and Hendrik Ballhausen. "A Secure Median Implementation for the Federated Secure Computing Architecture." Applied Sciences 14.17 (2024): 7891.
Vieluf, Solveig, et al. "Developing a deep canonical correlation-based technique for seizure prediction." Expert Systems with Applications 234 (2023): 120986.
Vieluf, Solveig, et al. "Development of a Multivariable Seizure Likelihood Assessment Based on Clinical Information and Short Autonomic Activity Recordings for Children With Epilepsy." Pediatric Neurology 148 (2023): 118-127.
Goelz, Christian, et al. "Classification of age groups and task conditions provides additional evidence for differences in electrophysiological correlates of inhibitory control across the lifespan." Brain Informatics 10.1 (2023): 11.
Böttcher, Sebastian, Vieluf, Solveig, et al. "Data quality evaluation in wearable monitoring." Scientific reports 12.1 (2022): 21412.
Vieluf, Solveig, et al. "Twenty‐four‐hour patterns in electrodermal activity recordings of patients with and without epileptic seizures." Epilepsia 62.4 (2021): 960-972.
-
Prof. Dr. Solveig Vieluf
AG Leiter
RüäqilxD;eÖliäfwvimsfulD_avfiuyziu miChristian Gölz
PhD Candidate
Hzplcblgu Xüiäßv;im ful+vfiuyziu-miCaren Strote
PhD Candidate
ygpiuscbpübividm ful_vfi:uyziuD miFabian Zheng
PhD Candidate
RzfukliwgjlgSutLziuxvimYsfulh:vfiuyziusmiValentine Ojonugwa Idakwo
PhD Candidate
qgäiublui Slmgoéüvim dfulGvfDiuWyziusmiPaulina Moehrle
MD Candidate (currently abroad)
Qasrina Shafei
research assistants
WTfpeOüzgvimvimsfulGvfiuyziuemiAbdul Baig
research assistants
Fjmfä Aglxvimeful_vfiuyziu mi