Skip to ContentSkip to Navigation
Rijksuniversiteit Groningenfounded in 1614  -  top 100 university
Over ons Praktische zaken Waar vindt u ons dr. R.S.N. (Rudolf) Fehrmann

Research interests

In addition to my medical training (MSc, 2006; MD/PhD, 2010), I received degrees in Mathematics and Computer Science (Propaedeutic exam, 1998) and Cognitive Science and Engineering (MSc, 2002). These opened a multidisciplinary toolbox that I use to answer complex research questions; this toolbox includes programming skills, machine learning, statistics, and biomedical knowledge. Early on in my career, I understood that the vast amount of publicly available data constitutes a gold mine. Constructing large-scale datasets from open data and performing advanced analyses can generate valuable new insights often missed by the researchers who originally collected the data. Therefore, I’m highly motivated to maximize and contribute to open data and public tools.

In 2013, I established an independent multidisciplinary research group at the UMCG. The group uses big-data approaches combined with machine learning (ML) to identify molecular, imaging, or clinicopathological patterns relevant to the pathophysiological behavior and treatment response of tumors. I’m known for stimulating students to acquire new skills outside of their ‘comfort zone’, to nurture the next generation of multidisciplinary researchers who can successfully bridge the gap between data science and biomedical research. I’m a team player who can collaborate extensively with clinicians, biologists, and data scientists in medical oncology and beyond.

I followed the residency program in Internal Medicine / Medical Oncology and now work as a board-certified internist and medical oncologist at the department of Medical Oncology at the UMCG, involved in care, teaching, and research. In addition, I am a tenure track adjunct professor in Artificial Intelligence Approaches for Precision Oncology.

Publicaties

Association of copy number alterations with the immune transcriptomic landscape in cancer

Cyclin E1 overexpression triggers interferon signaling and is associated with antitumor immunity in breast cancer

ESMO basic requirements for AI-based biomarkers in oncology (EBAI)

MYC controls STING levels to downregulate inflammatory signaling in breast cancer cells upon DNA damage

The ESMO-Magnitude of Clinical Benefit Scale (ESMO-MCBS) visualisation: picturing the evidence of clinical benefit of clinical trial data

Transcriptional pattern enriched for synaptic signaling is associated with shorter survival of patients with high-grade serous ovarian cancer

Upfront whole blood transcriptional patterns in patients receiving immune checkpoint inhibitors associate with clinical outcome

128P - Whole blood transcriptomics identifies transcriptional patterns linked to outcomes in patients receiving immune checkpoint inhibitors

Exploring combinations of dimensionality reduction, transfer learning, and regularization methods for predicting binary phenotypes with transcriptomic data

Functional ex vivo DNA fibre assay to measure replication dynamics in breast cancer tissue

Pers/media

AI may be key to streamline patient allocation to clinical trials

KWF-subsidie voor onderzoek naar werking immuuntherapie bij triple-negatieve borstkanker

UMCG krijgt miljoen euro voor onderzoek naar therapie bij agressieve borstkanker

UMCG krijgt miljoen euro voor onderzoek naar therapie bij agressieve borstkanker

Prangende vragen én antwoorden over artificial intelligence in de zorg

Artificial Intelligence in Medical Oncology

Interview on Artificial Intelligence in Medical Oncology

Vlog: YAG Interdisciplinary Project

Looking back: ECR Lunch on work / life balance

UMCG krijgt subsidie voor onderzoek naar kanker