SNOBERT: A Benchmark for clinical notes entity linking in the SNOMED CT clinical terminology

Mikhail Kulyabin, Gleb Sokolov, Aleksandr Galaida, Andreas Maier, Tomas Arias-Vergara
5/25/2024
cs.CLcs.LG

No official code found. Best implementation: MikhailKulyabin/SNOBERT (13 stars, MIT, last commit 2024-05-30).

Abstract

The extraction and analysis of insights from medical data, primarily stored in free-text formats by healthcare workers, presents significant challenges due to its unstructured nature. Medical coding, a crucial process in healthcare, remains minimally automated due to the complexity of medical ontologies and restricted access to medical texts for training Natural Language Processing models. In this paper, we proposed a method, "SNOBERT," of linking text spans in clinical notes to specific concepts in the SNOMED CT using BERT-based models. The method consists of two stages: candidate selection and candidate matching. The models were trained on one of the largest publicly available dataset of labeled clinical notes. SNOBERT outperforms other classical methods based on deep learning, as confirmed by the results of a challenge in which it was applied.

View on arXivView PDF

Code Implementations(1)

MikhailKulyabin/SNOBERTCommunity100%
MIT

A Benchmark for clinical notes entity linking in the SNOMED CT clinical terminology

133Python, MakefileMay 23, 20242 years agoMIT

Similar Papers

ClinLinker: Medical Entity Linking of Clinical Concept Mentions in Spanish

83% match2024

Deep Learning for Medical Text Processing: BERT Model Fine-Tuning and Comparative Study

83% match2024

Automated SNOMED CT Concept Annotation in Clinical Text Using Bi-GRU Neural Networks

82% match2025

SNOMED CT-powered Knowledge Graphs for Structured Clinical Data and Diagnostic Reasoning

82% match2025

Semantic Analysis of SNOMED CT Concept Co-occurrences in Clinical Documentation using MIMIC-IV

80% match2025

Biomedical Entity Linking for Dutch: Fine-tuning a Self-alignment BERT Model on an Automatically Generated Wikipedia Corpus

80% match1 repo32024

Cite this paper

@article{kulyabin2024snobert,
  title  = {SNOBERT: A Benchmark for clinical notes entity linking in the SNOMED CT clinical terminology},
  author = {Mikhail Kulyabin and Gleb Sokolov and Aleksandr Galaida and Andreas Maier and Tomas Arias-Vergara},
  year   = {2024},
  eprint = {2405.16115},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.16115v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.16115.svg)](https://codeofpaper.com/paper/2405.16115)

Discussion