Benjamin Skov Kaas-Hansen
Assistant lecturer
Section of Biostatistics
Øster Farimagsgade 5 opg. B
1014 København K
Benjamin is a hybrid medical doctor and data scientist with an MSc in epidemiology and biostatistics and a PhD in pharmacovigilance and health informatics from University of Copenhagen. He holds a position as research fellow at Dep. of Intensive Care at Copenhagen University Hospital - Rigshospitalet. His scientific interests include in causal inference, platform/adaptive trial design, Bayesian methods, machine learning, and data visualisation and standardisation; R fluent, proficient in Python and SQL, and learning Julia.
Primary fields of research
- Pharmacovigilance
- Causal inference and platform/adaptive trial design
- Data and text mining in electronic patient records
- Bayesian analysis and machine learning in epidemiology
- Data standardisation and visualisation
Selected publications
- Published
Language-agnostic pharmacovigilant text mining to elicit side effects from clinical notes and hospital medication records
Kaas-Hansen, Benjamin Skov, Placido, Davide, Rodrìguez, C. L., Thorsen-Meyer, H., Gentile, S., Nielsen, A. P., Brunak, Søren, Jürgens, Gesche & Andersen, Stig Ejdrup, 2022, Authorea, (Authorea Preprints).Research output: Working paper › Preprint › Research
- Published
Using Machine Learning to Identify Patients at High Risk of Inappropriate Drug Dosing in Periods with Renal Dysfunction
Kaas-Hansen, Benjamin Skov, Leal Rodríguez, C., Placido, Davide, Thorsen-Meyer, H., Nielsen, A. P., Dérian, N., Brunak, Søren & Andersen, Stig Ejdrup, 2022, In: Clinical Epidemiology. 14, p. 213-223 11 p.Research output: Contribution to journal › Journal article › peer-review
- Published
- Published
adaptr: an R package for simulating and comparing adaptive clinical trials
Granholm, A., Jensen, Aksel Karl Georg, Lange, Theis & Kaas-Hansen, Benjamin Skov, 2022, In: Journal of Open Source Software. 7, 72, 1 p., 4284.Research output: Contribution to journal › Journal article › peer-review
- Published
Dynamic and explainable machine learning prediction of mortality in patients in the intensive care unit: a retrospective study of high-frequency data in electronic patient records
Thorsen-Meyer, H., Nielsen, Annelaura Bach, Nielsen, A. P., Kaas-Hansen, Benjamin Skov, Toft, P., Schierbeck, J., Strøm, T., Chmura, Piotr Jaroslaw, Heimann, M., Dybdahl, L., Spangsege, L., Hulsen, P., Belling, K., Brunak, Søren & Perner, Anders, 2020, In: The Lancet Digital Health. 2, 4, p. e179–91 13 p.Research output: Contribution to journal › Journal article › peer-review
ID: 185059892
Most downloads
-
110
downloads
Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients
Research output: Contribution to journal › Journal article › peer-review
Published -
53
downloads
Dynamic and explainable machine learning prediction of mortality in patients in the intensive care unit: a retrospective study of high-frequency data in electronic patient records
Research output: Contribution to journal › Journal article › peer-review
Published -
42
downloads
Different Original and Biosimilar TNF Inhibitors Similarly Reduce Joint Destruction in Rheumatoid Arthritis-A Network Meta-Analysis of 36 Randomized Controlled Trials
Research output: Contribution to journal › Review › peer-review
Published