MedTem2.0: Prompt-based Temporal Classification of Treatment Events from Discharge Summaries

Research output: Contribution to conferencePaperpeer-review

Abstract

Discharge summaries are comprehensive medical records that encompass vital information about a patient's hospital stay. A crucial aspect of discharge summaries is the temporal information of treatments administered throughout the patient's illness. With an extensive volume of clinical documents, manually extracting and compiling a patient's medication list can be laborious, time-consuming, and susceptible to errors. The objective of this paper is to build upon the recent development on clinical NLP by temporally classifying treatments in clinical texts, specifically determining whether a treatment was administered between the time of admission and discharge from the hospital. State-of-the-art NLP methods including prompt-based learning on Generative Pre-trained Transformers (GPTs) models and fine-tuning on pre-trained language models (PLMs) such as BERT were used to classify temporal relations between treatments and hospitalisation periods in discharge summaries. Fine-tuning with the BERT model achieved an F1 score of 92.45% and a balanced accuracy of 77.56%, while prompt learning using the T5 model and mixed templates resulted in an F1 score of 90.89% and a balanced accuracy of 72.07%. Our codes and data are available at https://github.com/HECTA-UoM/MedTem.

Original languageEnglish
Pages160-183
Number of pages24
DOIs
Publication statusPublished - 2023
EventProceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop) - Toronto, Canada
Duration: 1 Jul 20231 Jul 2023

Conference

ConferenceProceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
Period1/07/231/07/23

Fingerprint

Dive into the research topics of 'MedTem2.0: Prompt-based Temporal Classification of Treatment Events from Discharge Summaries'. Together they form a unique fingerprint.

Cite this