Towards Automated Anamnesis Summarization: BERT-based Models for Symptom Extraction
This addresses the workload of healthcare professionals by providing a tool for structured documentation, though it is incremental as it applies existing NLP methods to a new domain-specific dataset.
The paper tackles the problem of automating symptom extraction from patient anamnesis to reduce documentation burdens in healthcare, achieving promising performance in symptom identification and attribute extraction with BERT-based models that significantly outperform simpler baselines.
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.