Talk by Prof. Dr. Anne-Christin Hauschild

On Wednesday, April 26th 2023, Prof. Dr. Anne-Christin Hauschild will told a talk as part of our “Distinguished Speaker Series” about the topic of “Challenges in Biomedical Data Science: Of Data Sparsity, Privacy and a Lack of Trust in Al for Clinical Decision Support”.


Machine learning has been successfully applied in many areas of biomedical research. However, many challenges remain that hinder a transfer towards clinical practice. In particular, limited sample size and systematic biases of single cohorts lead to data sparsity, heterogeneity of medical registry and omics data. Moreover, a lack of interpretable and reliable predictions result in a lack of trust in otherwise highly accurate models. The Hauschild lab is addressing these challenges with different computational architectures and algorithms such as federated learning for global model generation, transfer learning to overcome small sample size issues and heterogenious data integration, as well as model and prediction interpretability by explainable artificial intelligence methods.