Data Privacy

Today I presented a poster at the GMDS 2023 congress in Heilbronn Germany. The poster was about using Named Entity Recognition (NER) and Language Models (LLMs) to enhance the de-identification of semi-structured Electronic Medical Record (EMR) data. In essence we used open-source LLMs to augment our de-identification pippeline for semi-structured EMR data. The LLMs were used to identify entities that were not covered by the NER model we used. Since all of this had to be done on-site (on-premise) and with limited resources, you can probably imagine that the results were’nt stellar....

This article from the german Ärzteblatt describes a recent survey reveals that 50% of Germans are open to donating their health data for research purposes. This data could significantly advance studies on chronic and rare diseases, providing valuable insights for the medical community. While this is a promising result, it is important to note that the data must be handled responsibly and with the utmost care to protect the privacy of the donors....