Artificial intelligence (AI) techniques typically require large data sets, also called "big data". Biomedical data sets, on the other hand, often only comprise a relatively small number of observations. These "small data" applications may seem more manageable at first glance, but they make it much more difficult to use data-hungry artificial intelligence approaches. The new Collaborative Research Centre „Small Data“ is developing methods for using artificial intelligence techniques and modelling to discover complex patterns even in such relatively small data sets. This requires a highly interdisciplinary approach that combines expertise from computer science, mathematics, statistics, medicine and systems modelling - and establishes a shared language among researchers from the different disciplines.
The German Research Foundation (DFG) is funding the new Collaborative Research Centre (CRC) 1597 "Small Data" with over 11 million euros until June 2027. If continuation applications are successful, the new CRC could run for a total of twelve years. The spokesperson is Prof. Dr. Harald Binder, Professor of Medical Biometry and Statistics at the Medical Faculty of the University of Freiburg and the Medical Centre and member of the Cluster of Excellence CIBSS – Centre for Integrative Biological Signalling Studies.
“An essential strategy for tackling small data challenges is to incorporate domain knowledge in the form of models,” Binder explains. “This is also relevant in CIBSS, where signaling knowledge might, for example, be represented via differential equations. The newly developed methods will therefore also be useful for other initiatives in Freiburg.”
The new Collaborative Research Centre will start in October 2023. 29 scientists from all participating disciplines will lead its diverse sub-projects over the next four years. The SMART Research Training Group, which offers positions for 31 doctoral students, is also part of the CRC. "We will make AI techniques that are already very successful for big data usable for much more challenging small data applications in medicine," says Binder.
Binder's research interests include integrative statistical modelling of molecular measurements together with clinical features, techniques for clinical registries and routine data with complex time structures, and machine learning approaches for biomedical data with a limited number of observations. Binder is also director of the Institute of Medical Biometry and Statistics (IMBI) at the Medical Centre of the University of Freiburg.
CIBSS Profile of Prof. Dr. Harald Binder
Website of the Collaborative Research Centre (CRC) 1597 "Small Data"