Research

Noel’s research interests focus on developing and applying machine learning methods that yield models with meaningful capacity for data-driven clinical insight (Cosgriff et al., 2019).

In particular, he intends to (1) optimize for real-world contexts (Lekadir et al., 2025) with clinically-informed (Cosgriff et al., 2019) models that remain stable under data variations (Freiesleben and Grote, 2023) and (2) advance from prediction towards deepening understanding (Craver, 2006) of health and disease, discovering avenues for actionable interventions through the integration of concepts from causal inference (Pearl, 2009; Schölkopf, 2022; Sanchez et al., 2022).

Highlights¹

Noel has contributed to various research projects, working with Prof. Dr. Dr. Felix Balzer (Director, Institute of Medical Informatics, Charité Berlin), Prof. Dr. Stefan Haufe (Professor, Research Group for Uncertainty, Inverse Modeling and Machine Learning, Technical University of Berlin), Prof. Dr. Roland Eils (Founding Director, Center for Digital Health, Berlin Institute of Health, Charité Berlin), and Dr. Benjamin Wild (Group Leader, Research Group for Artificial Intelligence in the Life Sciences, Center for Digital Health, Berlin Institute of Health, Charité Berlin).

In his bachelor thesis at the Charité Berlin and Technical University of Berlin (2024), Noel developed a proof-of-concept electronic health record (EHR) data processing pipeline. The objective was to streamline the use of quality-assessed EHR data for real world evidence studies and to build the foundation for the Charité Outcomes Research Repository (CORR). As a demonstration, established clinical risk scores were derived and extensively validated.

In Kronenberg et al. (2024), Noel co-led a study that identified multimorbidity clusters in intensive care unit (ICU) patients. These clusters were independently associated with mortality and enhanced the predictive performance of a widely used clinical risk score. He presented the work as a poster at the Congress of the German Interdisciplinary Association for Intensive Care and Emergency Medicine (DIVI).

Noel has also contributed to several projects exploring the use of large language models (LLMs) in medicine. In Hegselmann et al. (2025), general-purpose LLMs were evaluated for encoding EHR data in clinical prediction tasks, demonstrating performance on par with or superior to specialized models. In a separate study (von Wedel et al., 2024), the team investigated affiliation bias in LLM-assisted peer review of medical abstracts.

Additional work includes outcomes research in ICU patients. For instance, von Wedel et al. (2025) examined mortality differences between female and male patients at comparable thresholds of mechanical power.

For a complete list of publications, please see Noel’s Google Scholar profile.