# Adverse Event Extraction from Discharge Summaries: A New Dataset, Annotation Scheme, and Initial Findings

arXiv: https://arxiv.org/abs/2506.14900 · HTML: https://mlsanity.com/paper/2506.14900/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 68 references that are in the map.
- First posted on arXiv 17 Jun 2025.

## Builds on (most cited first, 4 of 4)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Effective Transition-based Model for Discontinuous NER](https://mlsanity.com/paper/2004.13454/) (2020)
- [Extracting Adverse Drug Events from Clinical Notes](https://mlsanity.com/paper/2104.10791/) (2021)
- [MultiADE: A Multi-domain Benchmark for Adverse Drug Event Extraction](https://mlsanity.com/paper/2405.18015/) (2024)

## Built on by (most cited first, 2 of 2)

- [Event Extraction in Large Language Model](https://mlsanity.com/paper/2512.19537/) (2025)
- [Applicability Condition Extraction for Therapeutic Drug-Disease Relations](https://mlsanity.com/paper/2606.14031/) (2026)

## Abstract (arXiv)

In this work, we present a manually annotated corpus for Adverse Event (AE) extraction from discharge summaries of elderly patients, a population often underrepresented in clinical NLP resources. The dataset includes 14 clinically significant AEs-such as falls, delirium, and intracranial haemorrhage, along with contextual attributes like negation, diagnosis type, and in-hospital occurrence. Uniquely, the annotation schema supports both discontinuous and overlapping entities, addressing challenges rarely tackled in prior work. We evaluate multiple models using FlairNLP across three annotation granularities: fine-grained, coarse-grained, and coarse-grained with negation. While transformer-based models (e.g., BERT-cased) achieve strong performance on document-level coarse-grained extraction (F1 = 0.943), performance drops notably for fine-grained entity-level tasks (e.g., F1 = 0.675), particularly for rare events and complex attributes. These results demonstrate that despite high-level scores, significant challenges remain in detecting underrepresented AEs and capturing nuanced clinical language. Developed within a Trusted Research Environment (TRE), the dataset is available upon request via DataLoch and serves as a robust benchmark for evaluating AE extraction methods and supporting future cross-dataset generalisation.