# BCSLinker: automatic method for constructing a knowledge graph of venous thromboembolism based on joint learning

## TL;DR

This paper introduces BCSLinker, a deep learning method to build a more accurate knowledge graph for venous thromboembolism from medical records, improving diagnosis and treatment support.

## Contribution

BCSLinker is a novel joint extraction model that reduces error propagation and redundant information in constructing venous thromboembolism knowledge graphs.

## Key findings

- BCSLinker achieved an F1 score of 86.9% on electronic medical records, outperforming other joint extraction models.
- The model uses a Biaffine Common-Sequence Self-Attention module to extract entities and relations simultaneously, reducing error propagation.
- A question-answering system was developed using the constructed VTE knowledge graph for clinical support.

## Abstract

Venous thromboembolism (VTE) is characterized by high morbidity, mortality, and complex treatment. A VTE knowledge graph (VTEKG) can effectively integrate VTE-related medical knowledge and offer an intuitive description and analysis of the relations between medical entities. However, current methods for constructing knowledge graphs typically suffer from error propagation and redundant information.

In this study, we propose a deep learning-based joint extraction model, Biaffine Common-Sequence Self-Attention Linker (BCSLinker), for Chinese electronic medical records to address the issues mentioned above, which often occur when constructing a VTEKG. First, the Biaffine Common-Sequence Self-Attention (BCsSa) module is employed to create global matrices and extract entities and relations simultaneously, mitigating error propagation. Second, the multi-label cross-entropy loss is utilized to diminish the impact of redundant information and enhance information extraction.

We used the electronic medical record data of VTE patients from a tertiary hospital, achieving an F1 score of 86.9% on BCSLinker. It outperforms the other joint entity and relation extraction models discussed in this study. In addition, we developed a question-answering system based on the VTEKG as a structured data source.

This study has constructed a more accurate and comprehensive VTEKG that can provide reference for diagnosing, evaluating, and treating VTE as well as supporting patient self-care, which is of considerable clinical value.