Publications by authors named "Katharina Rausch"
Article Synopsis
- The study investigates survival analysis methods for lung cancer using data from the Schleswig-Holstein Cancer Registry, comparing traditional Cox regression with newer machine learning methods such as Random Survival Forests and neural networks.
- Results indicate that the Cox Proportional Hazard model performs best when using the cancer stage classification, while the Random Survival Forests excel when considering additional tumor characteristics like size and metastasis.
- The findings highlight the importance of these models for providing insights into patient survival, aiding physicians in making better treatment decisions, and ultimately enhancing patient outcomes.
Background: Generating synthetic patient data is crucial for medical research, but common approaches build up on black-box models which do not allow for expert verification or intervention. We propose a highly available method which enables synthetic data generation from real patient records in a privacy preserving and compliant fashion, is interpretable and allows for expert intervention.
Methods: Our approach ties together two established tools in medical informatics, namely OMOP as a data standard for electronic health records and Synthea as a data synthetization method.