Student's Corner

PhD student Jannis Guski presents his latest paper in which he applies causal machine learning techniques to analyze whether real-world patient data hint at an increased risk of neurodegeneration caused by SARS-CoV-2 infections. The work was conducted as part of the EU project COMMUTE.

Lennart Carstens-Behrens shares some insights into his work on the estimation of causal effects that lifestyle factors might have on the risk of Parkinson's disease.

India Mähler presents her master's thesis, which she recently defended as part of the applied mathematics degree program at Koblenz University of Applied Sciences. Her thesis was supervised by Prof. Dr. Holger Fröhlich and Prof. Dr. Armin Fiedler.

Jonas Elmer describes how he used generative adversarial networks to generate synthetic data for minorities in clinical cohorts in his recently submitted Bachelor's thesis.

Marjan Niazpoor explains how suitable bioassays for the validation of structured biomedical hypotheses can be identified with the aid of Knowledge Graphs and Large Language Models, the topic of her recently submitted master's thesis.

Leonie Fohler presents her master's thesis, which she recently defended as part of the applied mathematics degree program at Koblenz University of Applied Sciences. Her thesis was supervised by Prof. Dr. Holger Fröhlich and Prof. Dr. Michael Kinder.

Master's student Johanna Driever talks about her latest paper in which she used Domain Adaptation to generalize Machine Learning predictions across EHR datasets from different healthcare systems.

Endri Gupta presents her Master's thesis which explores the integration of artificial intelligence, knowledge graphs, and biomedical evidence to support clinical decision-making in the presence of co-morbidities.

Astha Anand explains how she developed and evaluated an expert question answering system in the domain of agricultural pest control for her Master's thesis.

Avani Bhat shares a digest of her Master's thesis about a layered validation strategy to ensure that both curated and automated graphs reflect trustworthy biological knowledge.