Dr. Matthijs S. Berends works as a medical epidemiologist/microbiologist the University Medical Center Groningen (UMCG) and Certe Foundation. He is an expert on microbial epidemiology and data science. With a background in Medical Biology, Medical Microbiology and Clinical Epidemiology, he wrote his PhD thesis “A New Instrument for Microbial Epidemiology” (DOI 10.33612/diss.177417131) on the novel development of a data-analytical method for antimicrobial resistance (AMR) data analysis: the AMR package for R (https://amr-for-r.org). It has since become a new standard in the field; cited over 75 times, downloaded more than 150,000 times, translated to 28 languages, used in over 175 countries, and adopted by national health institutes and international research groups across the globe. For this development, the University of Groningen rewarded him with the Open Research Award. The preprint about the method was in the ResearchGate top 10 weekly most read preprints ever and is according to Altmetrics in the 97th percentile of most popular research ever measured. It was published in the Journal of Statistical Software (IF 22.1), which at that time held the #1 journal impact ranking in Statistics and Probability (Mathematics), and in Statistics, Probability & Uncertainty (Decision Sciences), and in Software (Computer Science).

Dr. Berends' recent work bridges clinical microbiology with artificial intelligence, with a particular emphasis on applying natural language processing (NLP) to large-scale electronic health records for infectious disease detection and applying machine learning models. His collaborative research includes the development of AI models using various architectures to identify early signs of infectious disease in primary care settings, published in Nature Digital Medicine (2025). His expertise in applying transformer-based models to Dutch general practice data has led to the creation of validated NLP tools for COVID-19 detection (J Med Internet Res, 2023), and large-scale cohort analyses of long COVID risk factors and outcomes (Int J Infect Dis, 2025). These studies exemplify his ongoing commitment to translating complex AI methodologies into clinically actionable tools, particularly in antimicrobial resistance surveillance and infection prevention. As Head of the Epidemiology & Data Science Unit at UMCG, he continues to lead innovative research on integrating AI into microbiological diagnostics and public health infrastructure, while supervising 4 PhD students.