Dr. rer. nat. Lea Eckhart

Member of the "Multi-Omics Data" group, Institute of Medical Bioinformatics, UMG

I completed my PhD in 2025 at Saarland University on the topic of trustworthy machine learning methods for personalised cancer treatment. Since then, I have been working as a postdoctoral researcher at the Chair of "AI and Multi-Omics Data", which forms part of the Institute of Medical Bioinformatics at Göttingen University Medical Centre.

My research continues to focus on the development of trustworthy machine learning models for medical applications. To ensure that we can trust the predictions made by artificial intelligence in research, drug development and patient treatment, criteria such as reliability, interpretability and robustness play a central role alongside predictive accuracy. Unfortunately, these factors are often neglected or pitted against one another during model development. I am therefore developing new methods that treat "trustworthiness" as a multi-faceted concept and fulfil as many of the above-mentioned criteria as possible. In addition to oncological issues, I am also working on predicting antibiotic resistance based on routine clinical data from bacterial and fungal infections.