Page 22 - AIH-1-1

Artificial Intelligence in Health

REVIEW ARTICLE
Natural language processing in electronic health

records: A review

Prachi Gurav *
1,2
1 Department of Decision Science and Information Systems, Indian Institute of Management,
Mumbai, India
2 Department of Computer Engineering, St. John College of Engineering and Management, Palghar,
Maharashtra, India

Abstract
The two fundamental tasks that a physician performs during every interaction
with a patient are reading and updating electronic health records (EHRs). Reading
the records is necessary to gain better knowledge of a patient’s health status while
updating the records is essential for creating a database for future information
extraction. If a patient’s history consists of only a few records, manual reading is the
best approach. However, this method may lead to overlooking important aspects of
the patient’s health, which could be detrimental. Therefore, automation is required
to extract important information. Natural language processing (NLP) facilitates
information extraction and operates on seven different levels. In our review, we aimed
to understand how NLP levels assist in extracting information. We examined articles
published in PubMed and, after critical evaluation, selected 65 out of 382 identified
articles that met the inclusion criteria for the final review. Among these, 47 articles
were included in the final review. We found a higher number of articles on the lexical
(7), semantic (30), and morphological (4) levels, while fewer articles focused on the
*Corresponding author: phonetic (1), syntactic (2), discourse (2), and pragmatic (1) levels. This distribution
Prachi Gurav
(prachigurav19@gmail.com) underscores the current emphasis within the literature on the specific aspects of NLP.
In conclusion, our review underscores the critical role played by NLP in extracting
Citation: Gurav P, 2024, Natural
language processing in electronic information from EHR, shedding light on the varied levels at which this technology
health records: A review. Artif Intell operates.
Health, 1(1): 16-31.
https://doi.org/10.36922/aih.2147
Keywords: Electronic health records; Natural language processing; Natural language
Received: October 31, 2023
processing levels
Accepted: January 8, 2024
Published Online: January 10, 2024
Copyright: © 2024 Author(s). 1. Introduction
This is an Open-Access article
distributed under the terms of the The utilization of patient records in healthcare procedures has a longstanding history,
Creative Commons Attribution
License, permitting distribution, spanning from ancient times to the present day. These patient records serve multiple
and reproduction in any medium, purposes, primarily functioning as aids to physicians’ memory recall and serving as
provided the original work is
properly cited. essential references for other healthcare professionals involved in the patient’s medical
journey. Another imperative for diligently documenting the healthcare process of a
Publisher’s Note: AccScience
Publishing remains neutral with patient lies in legal mandates, as stipulated by law in many countries.
regard to jurisdictional claims in
published maps and institutional Patient records encompass various nomenclatures, including patient records, health
affiliations. records, case sheets, and case histories. In the realm of paper-based documentation,

Volume 1 Issue 1 (2024) 16 https://doi.org/10.36922/aih.2147