About our research group/lab
Our research
Improving Interoperability of Data
Multi-center studies are severely hampered by the fact that each database has a different database structure and uses different terminology systems. In an ideal world, a harmonized approach would be available by which results from different databases could be combined to answer research questions. A common data model and standardized analytical tools should become a de facto standard. Our group, therefore, collaborates closely with the Observational Health Data Sciences and Informatics (OHDSI) initiative (www.ohdsi.org) that is responsible for the development of the OMOP-CDM, and leads its European Chapter (www.ohdsi-europe.org) to support adoption of the OMOP-CDM in Europe.
Enabling Data-driven Healthcare
The Health Data Science group aims to develop analytical methods and tools to enable data-driven healthcare. We apply advanced machine learning and statistical methods to develop and validate clinical prediction models at scale in distributed data networks. Methodological research in the field of predictive analytics, data characterisation, and causal inference is an important focus of the group.
Open Science and FAIR
The group is developing open source pipelines and only performs open science, and fully endorses the Findable, Accessible, Interoperable, and Re-usable (FAIR) principles in its work. A good example is the influencial European Health Data and Evidence Network (EHDEN, www.ehden.eu) project, coordinated by Dr. Rijnbeek, that is implementing the FAIR principles in a large federated data network.
Natural Language Processing
Many health-record databases contain large amounts of unstructured, textual data. We develop and apply natural language processing techniques to extract information from medical texts across different European languages to improve prediction models. This work is led by Dr. Jan Kors.
More information can be found at www.healthdatascience.nl.
Multi-center studies are severely hampered by the fact that each database has a different database structure and uses different terminology systems. In an ideal world, a harmonized approach would be available by which results from different databases could be combined to answer research questions. A common data model and standardized analytical tools should become a de facto standard. Our group, therefore, collaborates closely with the Observational Health Data Sciences and Informatics (OHDSI) initiative (www.ohdsi.org) that is responsible for the development of the OMOP-CDM, and leads its European Chapter (www.ohdsi-europe.org) to support adoption of the OMOP-CDM in Europe.
Enabling Data-driven Healthcare
The Health Data Science group aims to develop analytical methods and tools to enable data-driven healthcare. We apply advanced machine learning and statistical methods to develop and validate clinical prediction models at scale in distributed data networks. Methodological research in the field of predictive analytics, data characterisation, and causal inference is an important focus of the group.
Open Science and FAIR
The group is developing open source pipelines and only performs open science, and fully endorses the Findable, Accessible, Interoperable, and Re-usable (FAIR) principles in its work. A good example is the influencial European Health Data and Evidence Network (EHDEN, www.ehden.eu) project, coordinated by Dr. Rijnbeek, that is implementing the FAIR principles in a large federated data network.
Natural Language Processing
Many health-record databases contain large amounts of unstructured, textual data. We develop and apply natural language processing techniques to extract information from medical texts across different European languages to improve prediction models. This work is led by Dr. Jan Kors.
More information can be found at www.healthdatascience.nl.
Our projects
European Health Data and Evidence Network (EHDEN, www.ehden.eu). The EHDEN project aspires to be the trusted observational research ecosystem to enable better health decisions, outcomes and care. Its mission is to provide a new paradigm for the discovery and analysis of health data in Europe, by building a large-scale, federated network of data sources standardized to a common data model
Observational Health Data Sciences and Informatics (or OHDSI, pronounced "Odyssey") program is a multi-stakeholder, interdisciplinary collaborative to bring out the value of health data through large-scale analytics. All solutions are open-source www.ohdsi.org. The HDS group is leading the European OHDSI Community (www.ohdsi-europe.org).
The group collaborating with the European Medicines Agency (EMA) in establishing a European framework and research network for the conduct of multicentre cohort studies on the use of medicines in COVID-19 patients. This EMA-funded project, includes data sources from eight European countries standardised to the OMOP-Common Data Model and is contracted to IQVIA as the coordinating partner.
Observational Health Data Sciences and Informatics (or OHDSI, pronounced "Odyssey") program is a multi-stakeholder, interdisciplinary collaborative to bring out the value of health data through large-scale analytics. All solutions are open-source www.ohdsi.org. The HDS group is leading the European OHDSI Community (www.ohdsi-europe.org).
The group collaborating with the European Medicines Agency (EMA) in establishing a European framework and research network for the conduct of multicentre cohort studies on the use of medicines in COVID-19 patients. This EMA-funded project, includes data sources from eight European countries standardised to the OMOP-Common Data Model and is contracted to IQVIA as the coordinating partner.
Key Publications
- Reps JM, Rijnbeek PR, Ryan PB. Supplementing claims data analysis using self-reported data to develop a probabilistic phenotype model for current smoking status. J Biomed Infirm. 2019;97:102264. doi:10.1016/j.jbi.2019.103264
- Reps JM, Rijnbeek PR, Ryan PB. Identifying the DEAD: Development and validation of a patient-level model to predict death status in population-level claims cata. Drug Saf. 2019: epub: 2019/05/06. doi: 10.1007/s40264-019-00827-0
- Reps JM, Schuemie MJ, Suchard MA, Ryan PB, Rijnbeek PR. Design and implementation of a standardized framework to generate and evaluate patient-level prediction models using observational healthcare data. J Am Med Inform Assoc. 2018. Epub 2018/05/03. doi: 10.1093/jamia/ocy032. PubMed PMID: 29718407
- Hripcsak G, Duke JD, Shah NH, Reich CG, Huser V, Schuemie MJ, Suchard MA, Park RW, Wong IC, Rijnbeek PR, van der Lei J, Pratt N, Norén GN, Li YC, Stang PE, Madigan D, Ryan PB Observational Health Data Sciences and Informatics (OHDSI): Opportunities for Observational Researchers. Stud Health Technol Inform. 2015;(216):574–8
Collaborations
Research Suite.
Funding & Grants
The European Health Data & Evidence Network (www.ehden.eu) has received funding from the Innovative Medicines Initiative 2 Joint Undertaking (JU) under grant agreement No 806968. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and EFPIA.
Career opportunities
The Health Data Science group is growing and regularly has open positions for Postdocs, PhDs, and Master Students. Please contact us for more information.
We are always open for collaborations with Academia and Industry, do not hesitate to discuss the opportunities with us.
Contact us
Please contact us by email: healthdatascience@erasmusmc.nl.
