Towards Automated Anamnesis Summarization: BERT-based Models for Symptom Extraction
Abstract
Professionals in modern healthcare systems are increasingly burdened by documentation workloads. Documentation of the initial patient anamnesis is particularly relevant, forming the basis of successful further diagnostic measures. However, manually prepared notes are inherently unstructured and often incomplete. In this paper, we investigate the potential of modern NLP techniques to support doctors in this matter. We present a dataset of German patient monologues, and formulate a well-defined information extraction task under the constraints of real-world utility and practicality. In addition, we propose BERT-based models in order to solve said task. We can demonstrate promising performance of the models in both symptom identification and symptom attribute extraction, significantly outperforming simpler baselines.
Cite
@article{arxiv.2011.01696,
title = {Towards Automated Anamnesis Summarization: BERT-based Models for Symptom Extraction},
author = {Anton Schäfer and Nils Blach and Oliver Rausch and Maximilian Warm and Nils Krüger},
journal= {arXiv preprint arXiv:2011.01696},
year = {2020}
}
Comments
Machine Learning for Health (ML4H) at NeurIPS 2020 - Extended Abstract