# Deeper Clinical Document Understanding Using Relation Extraction

arXiv: https://arxiv.org/abs/2112.13259 · HTML: https://mlsanity.com/paper/2112.13259/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 25 Dec 2021.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [SciFive: a text-to-text transformer model for biomedical literature](https://mlsanity.com/paper/2106.03598/) (2021)
- [Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders](https://mlsanity.com/paper/2010.03851/) (2020)
- [Spark NLP: Natural Language Understanding at Scale](https://mlsanity.com/paper/2101.10848/) (2021)
- [A Silver Standard Corpus of Human Phenotype-Gene Relations](https://mlsanity.com/paper/1903.10728/) (2019)
- [Clinical Relation Extraction Using Transformer-based Models](https://mlsanity.com/paper/2107.08957/) (2021)
- [Relation Extraction from Biomedical and Clinical Text: Unified Multitask Learning Framework](https://mlsanity.com/paper/2009.09509/) (2020)
- [Deeper Task-Specificity Improves Joint Entity and Relation Extraction](https://mlsanity.com/paper/2002.06424/) (2020)
- [Improving Clinical Document Understanding on COVID-19 Research with Spark NLP](https://mlsanity.com/paper/2012.04005/) (2020)
- [Relation extraction between the clinical entities based on the shortest dependency path based LSTM](https://mlsanity.com/paper/1903.09941/) (2019)
- [BiOnt: Deep Learning using Multiple Biomedical Ontologies for Relation Extraction](https://mlsanity.com/paper/2001.07139/) (2020)
- [Robustly Pre-trained Neural Model for Direct Temporal Relation Extraction](https://mlsanity.com/paper/2004.06216/) (2020)

## Built on by (most cited first, 7 of 7)

- [A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers](https://mlsanity.com/paper/2306.02051/) (2023)
- [Analysing zero-shot temporal relation extraction on clinical notes using temporal consistency](https://mlsanity.com/paper/2406.11486/) (2024)
- [Temporal Relation Extraction in Clinical Texts: A Span-based Graph Transformer Approach](https://mlsanity.com/paper/2503.18085/) (2025)
- [Mining Adverse Drug Reactions from Unstructured Mediums at Scale](https://mlsanity.com/paper/2201.01405/) (2022)
- [Understanding COVID-19 News Coverage using Medical NLP](https://mlsanity.com/paper/2203.10338/) (2022)
- [Beyond Negation Detection: Comprehensive Assertion Detection Models for Clinical NLP](https://mlsanity.com/paper/2503.17425/) (2025)
- [ADEQA: A Question Answer based approach for joint ADE-Suspect Extraction using Sequence-To-Sequence Transformers](https://mlsanity.com/paper/2412.15510/) (2024)

## Abstract (arXiv)

The surging amount of biomedical literature & digital clinical records presents a growing need for text mining techniques that can not only identify but also semantically relate entities in unstructured data. In this paper we propose a text mining framework comprising of Named Entity Recognition (NER) and Relation Extraction (RE) models, which expands on previous work in three main ways. First, we introduce two new RE model architectures -- an accuracy-optimized one based on BioBERT and a speed-optimized one utilizing crafted features over a Fully Connected Neural Network (FCNN). Second, we evaluate both models on public benchmark datasets and obtain new state-of-the-art F1 scores on the 2012 i2b2 Clinical Temporal Relations challenge (F1 of 73.6, +1.2% over the previous SOTA), the 2010 i2b2 Clinical Relations challenge (F1 of 69.1, +1.2%), the 2019 Phenotype-Gene Relations dataset (F1 of 87.9, +8.5%), the 2012 Adverse Drug Events Drug-Reaction dataset (F1 of 90.0, +6.3%), and the 2018 n2c2 Posology Relations dataset (F1 of 96.7, +0.6%). Third, we show two practical applications of this framework -- for building a biomedical knowledge graph and for improving the accuracy of mapping entities to clinical codes. The system is built using the Spark NLP library which provides a production-grade, natively scalable, hardware-optimized, trainable & tunable NLP framework.