Saved in:
Bibliographic Details
Main Authors: Guellil, Imane, Andres, Salomé, Anand, Atul, Guthrie, Bruce, Zhang, Huayu, Hasan, Abul, Wu, Honghan, Alex, Beatrice
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.14900
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911010676277248
author Guellil, Imane
Andres, Salomé
Anand, Atul
Guthrie, Bruce
Zhang, Huayu
Hasan, Abul
Wu, Honghan
Alex, Beatrice
author_facet Guellil, Imane
Andres, Salomé
Anand, Atul
Guthrie, Bruce
Zhang, Huayu
Hasan, Abul
Wu, Honghan
Alex, Beatrice
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14900
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adverse Event Extraction from Discharge Summaries: A New Dataset, Annotation Scheme, and Initial Findings
Guellil, Imane
Andres, Salomé
Anand, Atul
Guthrie, Bruce
Zhang, Huayu
Hasan, Abul
Wu, Honghan
Alex, Beatrice
Computation and Language
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.
title Adverse Event Extraction from Discharge Summaries: A New Dataset, Annotation Scheme, and Initial Findings
topic Computation and Language
url https://arxiv.org/abs/2506.14900