Three-Branch BERT-Based Text Classification Network for Gastroscopy Diagnosis Text

During a hospital visit, a significant volume of Gastroscopy Diagnostic Text (GDT) data are produced, representing the unstructured gastric medical records of patients undergoing gastroscopy. As such, GDTs play a crucial role in evaluating the patient’s health, shaping treatment plans, and schedulin...

Full description

Saved in:
Bibliographic Details
Published in:International journal of crowd science Vol. 8; no. 1; pp. 56 - 63
Main Authors: Wang, Zhichao, Zheng, Xiangwei, Zhang, Jinsong, Zhang, Mingzhe
Format: Journal Article
Language:English
Published: Tsinghua University Press 01.03.2024
Subjects:
bidirectional encoder representations from transformers (bert)
gastroscopy diagnostic text
text classification
ISSN:2398-7294, 2398-7294
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:During a hospital visit, a significant volume of Gastroscopy Diagnostic Text (GDT) data are produced, representing the unstructured gastric medical records of patients undergoing gastroscopy. As such, GDTs play a crucial role in evaluating the patient’s health, shaping treatment plans, and scheduling follow-up visits. However, given the free-text nature of GDTs, which lack a formal structure, physicians often find it challenging to extract meaningful insights from them. Furthermore, while deep learning has made significant strides in the medical domain, to our knowledge, there are not any readily available text-based pre-trained models tailored for GDT classification and analysis. To address this gap, we introduce a Bidirectional Encoder Representations from Transformers (BERT) based three-branch classification network tailored for GDTs. We leverage the robust representation capabilities of the BERT pre-trained model to deeply encode the texts. A unique three-branch decoder structure is employed to pinpoint lesion sites and determine cancer stages. Experimental outcomes validate the efficacy of our approach in GDT classification, with a precision of 0.993 and a recall of 0.784 in the early cancer category. In pinpointing cancer lesion sites, the weighted F1 score achieved was 0.849.
ISSN:2398-7294
2398-7294
DOI:10.26599/IJCS.2023.9100031