Informace o projektu

Anotace je dostupná pouze v anglickém jazyce.

The proposed project is the first to automatically analyze large databases of electronic health records (EHRs) in Czech and Polish using deep learning and text data mining. Building on recent advances in natural language processing, it tackles the hybrid code of medical text - a combination of fully formed sentences, Latin words and abbreviations, and numerical values - in order to extract, analyze, and visualize previously unseen medical information. Patient data are anonymized.