The “FAIrPaCT” research network is funded by the BMBF as part of the National Decade Against Cancer and aims to develop a software system that can individually predict the probability of success of pancreatic cancer therapies. This should increase the chances of effective treatment. In addition, factors could be identified that positively influence the effectiveness of treatment procedures. These factors in turn provide information on which molecular mechanisms control a therapy. Insights that could lead to improved drugs and personalised treatment strategies. It would be a major step forward in the fight against pancreatic cancer, which is considered one of the deadliest types of cancer. Only seven to eight percent of those affected survive the first five years after diagnosis. The tumours are often detected late and form metastases at an early stage, even in distant parts of the body.
FAIrPaCT” stands for “Framework for federated artificial intelligence to optimize the treatment of pancreatic cancer”. The system that the researchers want to develop is based on what is known as federated or distributed artificial intelligence. This is an algorithm that enables machine learning with data sources from different locations. In addition, the data is not stored centrally, but on different devices and can be accessed flexibly. FAIrPaCT researchers can therefore analyze data across institutes without storing it centrally. This ensures a higher level of data protection, which is particularly important for patient data. “FAIrPaCT” uses three of the largest, most informative data sets of patients with pancreatic cancer in Germany. These are clinical patient data and molecular data from removed cancer cells. These data were collected in the clinics of the network: at the University Medical Center Göttingen, the University Hospital Giessen and Marburg and the Rechts der Isar Hospital of the Technical University of Munich. The quantity and diversity of the data is unique in Germany.