Automated generation of discharge summaries: leveraging large language models with clinical data.

This study explores the use of open-source large language models (LLMs) to automate generation of German discharge summaries from structured clinical data. The structured data used to produce AI-generated summaries were manually extracted from electronic health records (EHRs) by a trained medical professional. By leveraging structured documentation collected for research and quality management, the goal is to assist physicians with editable draft summaries.

Efficient synthesis of organosoluble 6-azido-6-deoxy-2,3-O-trimethylsilyl cellulose for click reactions.

Huisgen cycloaddition has proven to be a powerful tool for the derivatization of cellulose, but the choice of reaction partners is limited by the solubility of the cellulose derivative. In this report, we show the efficient synthesis of an azide-bearing, organosoluble cellulose derivative via the 6-bromo-6-deoxy-2,3-O-trimethylsilyl cellulose (Br-TMSC) obtained through a novel one-pot reaction. It opens the possibility to perform the copper(I)-catalyzed azide-alkyne cycloaddition (CuAAC) under moisture free conditions.