Sameh Khattab

Sameh Khattab

PhD Student, NLP

Institute for AI in Medicine, Germany

Sameh studied Data Science at the Silesian University of Technology and is currently pursuing his PhD at IKIM, where his research focuses on generative AI for healthcare applications. Before joining IKIM, he gained industry experience as a Software Engineer in multiple companies. At IKIM, Sameh conducts research on large language models, information retrieval, and agentic AI systems. He also contributes to the DevOps team by developing and optimizing MLOps pipelines that connect research with real-world deployments, working towards building scalable and reliable AI systems that support IKIM’s mission of translating machine learning into meaningful clinical impact.

Publications

2026

Large language models enable prognostic stratification of cancer patients using real-world clinical notes Niklas Kiermeyer, Tim Lenfers, Amin Dada, Julian Friedrich, Sameh Khattab, Eric Knop, Jan Egger, Markus Pauly, Andreas Jung, Grégoire Montavon, Jens T. Siveke, Marcel Wiesweg, Stefan Kasper, Ulf Peter Neumann, Frederick Klauschen, Sylvia Hartmann, Martin Schuler, Philipp Keyl, Jens Kleesiek, Julius Keyl PLOS Digital Health Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why Osman Alperen Çinar-Koraş, Marie Bauer, Sameh Khattab, Merlin Engelke, Moon-Sung Kim, Stephan Settelmeier, Shigeyasu Sugawara, Fabian Freisleben, Felix Nensa, Jens Kleesiek arXiv Automated Tumor International Classification of Diseases Coding of Real-World Pathology Reports Using Self-Hosted Large Language Models Kamyar Arzideh, René Hosch, Amin Turki, Bahadir Eryilmaz, Mikel Bahn, Henning Schäfer, Ahmad Idrissi-Yaghir, Sameh Khattab, Amin Dada, Hideo A. Baba, Dirk Schadendorf, Martin Schuler, Jens Kleesiek, Sylvia Hartmann, Felix Nensa, Julius Keyl JCO Clinical Cancer Informatics AIANO: Enhancing Information Retrieval with AI-Augmented Annotation Sameh Khattab, Marie Bauer, Lukas Heine, Till Rostalski, Jens Kleesiek, Julian Friedrich arXiv Less Finetuning, Better Retrieval: Rethinking LLM Adaptation for Biomedical Retrievers via Synthetic Data and Model Merging Sameh Khattab, Jean-Philippe Corbeil, Osman Alperen Koraş, Amin Dada, Julian Friedrich, François Beaulieu, Paul Vozila, Jens Kleesiek arXiv

2025

Performing the HINTS-exam using a mixed-reality head-mounted display in patients with acute vestibular syndrome: a feasibility study Nadia Sadok, Gijs Luijten, Fin Hendrik Bahnsen, Christina Gsaxner, Lorenz Peters, Theda Eichler, Theresa Rombach, Stephan Lang, Sameh Khattab, Jens Kleesiek, Dagny Holle, Moritz Meyer, Jan Egger Frontiers in Neurology