Cross-lingual Approaches for the Detection of Adverse Drug Reactions in German from a Patient's Perspective

TL;DR

This paper introduces the first German ADR detection corpus from patient forums, demonstrating preliminary zero- and few-shot classification experiments with multilingual models, and sharing resources for future research.

Contribution

It provides the first German ADR detection dataset from patient-generated content and explores multilingual zero- and few-shot learning methods for this task.

Findings

Achieved an F1-score of 37.52 with fine-tuned XLM-RoBERTa.

Created and shared a new German ADR detection dataset.

Highlighted challenges of class imbalance and topic variability.

Abstract

In this work, we present the first corpus for German Adverse Drug Reaction (ADR) detection in patient-generated content. The data consists of 4,169 binary annotated documents from a German patient forum, where users talk about health issues and get advice from medical doctors. As is common in social media data in this domain, the class labels of the corpus are very imbalanced. This and a high topic imbalance make it a very challenging dataset, since often, the same symptom can have several causes and is not always related to a medication intake. We aim to encourage further multi-lingual efforts in the domain of ADR detection and provide preliminary experiments for binary classification using different methods of zero- and few-shot learning based on a multi-lingual model. When fine-tuning XLM-RoBERTa first on English patient forum data and then on the new German data, we achieve an F1-score of 37.52 for the positive class. We make the dataset and models publicly available for the community.