Deep learning in clinical natural language processing: a methodical review

By Stephen T Wu, Kirk Roberts, Surabhi Datta, Jingcheng Du, Zongcheng Ji, Yuqi Si, Sarvesh Soni, Qiong Wang, Qiang Wei, Yang Xiang and 2 more. J. Am. Medical Informatics Assoc., 2019

437 citations recorded by the source corpus.

OBJECTIVE This article methodically reviews the literature on deep learning (DL) for natural language processing (NLP) in the clinical domain, providing quantitative analysis to answer 3 research questions concerning methods, scope, and context of current research. MATERIALS AND METHODS We searched MEDLINE, EMBASE, Scopus, the Association for Computing Machinery Digital Library, and the Association for Computational Linguistics Anthology for articles using DL-based approaches to NLP problems in electronic health records. After screening 1,737 articles, we collected data on 25 variables across 212 papers. RESULTS DL in clinical NLP publications more than doubled each year, through 2018. Recurrent neural networks (60.8%) and word2vec embeddings (74.1%) were the most popular methods; the information extraction tasks of text classification, named entity recognition, and relation extraction were dominant (89.2%). However, there was a "long tail" of other methods and specific tasks. Most contributions were methodological variants or applications, but 20.8% were new methods of some kind. The earliest adopters were in the NLP community, but the medical informatics community was the most prolific. DISCUSSION Our analysis shows growing acceptance of deep learning as a baseline for NLP research, and of DL-based NLP in the medical community. A number of common associations were substantiated (eg, the preference of recurrent neural networks for sequence-labeling named entity recognition), while others were surprisingly nuanced (eg, the scarcity of French language clinical NLP with deep learning). CONCLUSION Deep learning has not yet fully penetrated clinical NLP and is growing rapidly. This review highlighted both the popular and unique trends in this active field.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/a2d2a482ccd62a705c8fafeb5f93bca33a4d796d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Large language models are few-shot clinical information extractors (2022, methodology): “Clinical text differs significantly from text typically utilized in general NLP, both in syntax and vocabulary (Wu et al., 2020).”
Language Models are Few-shot Learners for Prognostic Prediction (2023, background): “The pretraining corpus is also known as the knowledge source for LLMs. Clinical language is notably different from the standard NLP text in terms of vocabulary and syntax (Wu et al., 2019).”
esCorpius: A Massive Spanish Crawling Corpus (2022, background): “This situation has negative reper-cussions on the development of fair NLP technology for all [6], e.g. disparate access to clinical NLP for speakers of different languages [7].”
Natural Language Processing Advancements By Deep Learning: A Survey (2020, methodology): “Development of NLP methods is increasingly reliant on data-driven approaches which help with building more powerful and robust models [2]–[4].”