Presentation
The Relevance and Hands-on Application of Biomedical Record Linkage in the Big Data Era
Biomedical Record Linkage is especially designed for linking data of patients in different data repositories. An important question in this context is whether singling-out is sufficient for identifying a patient. First, we will describe the relevance of record linkage in general and in our projects specifically. Then, it will be shown how record linkage can be applied in Python via the Splink package, which represents the state-of-the-art of dealing with big data using Spark. Finally, we exemplify the conceptual problem of identification and introduce the sortal concept, stemming from analytical philosophy
Speaker
Prof. Dr. Murat Sariyar
PhD and habilitation in Medical Informatics in the areas of Machine Learning and Record Linkage. Professor for Medical Informatics at the Applied University of Bern since 2016. His main domains of interest include precision medicine, statistical bioinformatics, data management for biomedical data, process mining, natural language processing, ontology development, anonymization, and identity.
