The GeMTeX project of the Medical Informatics Initiative (MII) aims to create the largest corpus of medical texts in the German language. For this purpose, texts from routine clinical care (e.g. doctors’ letters and discharge summaries) are collected with the consent of the patients. These texts contain valuable information that can support medical research and care. If this information can be read by automated language processing programmes, the texts can also serve as the basis for machine learning models and Artificial Intelligence (AI). However, to unlock the full potential of the medical data they contain, these clinical texts must first be made machine-readable.
For this purpose, the Faculty of Medicine at the Leipzig University is looking for students of human medicine or dentistry from December 1st, 2025.
Interested in working with us?
Please send us until October 24, 2025 an email with the subject “GeMTeX Annotation” to info@smith.care.
GeMTeX is a project of the Medical Informatics Initiative and is funded by the German Federal Ministry of Education and Research until 2026. The aim of the Medical Informatics Initiative is to digitally network routine patient care data across Germany and make it available for medical research. This should enable diseases to be treated more quickly and effectively in the future. To this end, all German university medical institutions are working together with other research institutions, companies, health insurers and patient representatives in the four consortia DIFUTURE, HiGHmed, MIRACUM and SMITH on a cross-location infrastructure for health data. This infrastructure is being expanded through various projects and its functionality is being tested on the basis of use cases.