Tom Seinen, MSc

PhD Student

Email: This email address is being protected from spambots. You need JavaScript enabled to view it.

Social:linkedin logogithub logo researchgate logo










Tom obtained his BSc (2015) in Computer Science from Roosevelt University College, followed by an MSc (2017) in Bioinformatics from Leiden University and an MSc (2019) in Health Informatics from the Karolinska Institute, Stockholm. His thesis, conducted within the Computational Health Informatics Lab at the University of Oxford, focused on the risk prediction of patient deterioration in the clinical ward using ICU data and different machine learning methods. 

Currently, his studies in the Health Data Science group are focused on the incorporation of unstructured clinical text data in patient-level prediction models.


Seinen TM, Fridgeirsson E, Ioannou S, Jeannetot D, John LH, Kors JA, Markus AF, Pera V, Rekkas A, Williams RD, van Mulligen E, 2022. Use of unstructured text in prognostic clinical prediction models: a systematic review. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocac058

Seinen TM, Kors JA, van Mulligen EM, Fridgeirsson E, Rijnbeek PR, 2023. The added value of text from Dutch general practitioner notes in predictive modeling. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocad160





Tom M. Seinen, Erik M. van Mulligen, Jan A. Kors, Katia Verhamme, Peter R. Rijnbeek. Disambiguation of ICPC codes using free-text and active learning to improve concept mappingshttps://www.ohdsi.org/2022showcase-112/

Tom M. Seinen, Peter R. Rijnbeek. Vocabulary Versioning: Tracking Concepts over Time Software Demonstrationhttps://www.ohdsi.org/2022showcase-3/

Tom M. Seinen, Jan A. Kors, Erik M. van Mulligen, Peter R. Rijnbeek. Concept extraction from Dutch clinical texthttps://www.ohdsi-europe.org/images/symposium-2022/posters/Tom-Seinen_medspacy-dutch_2022symposium_-_OHDSI_Europe.pdf


Tom M. Seinen, Jan A. Kors, Erik M. van Mulligen, Peter R. Rijnbeek. Use of unstructured text data in electronic health records to improve patient-level prediction modelshttps://www.ohdsi.org/2020-global-symposium-showcase-58/