The summer school introduces advanced methods of managing and analysing medical data from health care and medical research. It includes an introductory course to introduce the programming language Python, and basic statistics which is crucial in data science and for data analytics. The main course consists of two distinct themes: “OMOP for Real World Evidence generation” and “Introduction to Machine Learning” as an essential pillar of the development of AI systems in clinically associated settings. OMOP is short for “Observational Medical Outcomes Partnership”. It refers to a common data model used in clinical data analysis to standardize and unify health data from heterogeneous sources. OMOP enables the integration of data from different sources, such as electronic health records (EHRs) and surveys, to be transformed into a standardized format and further processed. In addition to OMOP, other interoperability standards such as SNOMED-CT, LOINC, FHIR and openEHR will be explained and applied in interactive sessions. In the second theme, central concepts of machine learning with a focus on classification and regression models of supervised learning are presented and applied using Python and relevant libraries such as scikit-learn. A special focus will be on the validation of the developed prediction models.
The summer school is therefore an excellent opportunity to familiarize yourself with common interoperability standards in healthcare and medical secondary data-based research. Further, advanced data analysis techniques with a focus on machine learning as an important set of methods for the development of AI systems will be taught.
More detailed information will be available on this website soon.
