In this project, we will develop adaptive models for the diagnosis of various diseases in the intensive care unit. These models are intended to help inexperienced medical professionals to understand the complex processes, e.g., in the case of a blood poisoning (sepsis). The system is supposed to be able to predict various pathologies by means of instructive models and current measurement data. A major challenge in medicine is machine learning with small amounts of data (low-data problem), since the generation of data is very expensive. For this reason, we aim at developing so-called Medical-Insilico-Methods for a model-based computer-assisted drug optimization in cooperation with physicians. Such procedures reduce the number of laboratory tests required and could make drug development more cost-effective.
© ISEK at RWTH Aachen