2020
DOI: 10.1186/s13326-020-00231-z
|View full text |Cite
|
Sign up to set email alerts
|

Natural language processing algorithms for mapping clinical text fragments onto ontology concepts: a systematic review and recommendations for future studies

Abstract: Background Free-text descriptions in electronic health records (EHRs) can be of interest for clinical research and care optimization. However, free text cannot be readily interpreted by a computer and, therefore, has limited value. Natural Language Processing (NLP) algorithms can make free text machine-interpretable by attaching ontology concepts to it. However, implementations of NLP algorithms are not evaluated consistently. Therefore, the objective of this study was to review the current met… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
26
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 52 publications
(26 citation statements)
references
References 93 publications
0
26
0
Order By: Relevance
“…The success of AI/ML in the image analysis domain can be attributed to the wide availability of high quality, comprehensive, and extensively annotated datasets. In other domains, such as NLP processing of electronic health records, there is an absence of publically available annotated datasets which can be used to develop and validate NLP systems ( Kersloot et al, 2020 ). Due to this, there is limited information about the accuracy of NLP healthcare data analysis systems within the literature and it is difficult to compare the existing systems within the research ( Kersloot et al, 2020 ).…”
Section: Discussion and Future Researchmentioning
confidence: 99%
See 1 more Smart Citation
“…The success of AI/ML in the image analysis domain can be attributed to the wide availability of high quality, comprehensive, and extensively annotated datasets. In other domains, such as NLP processing of electronic health records, there is an absence of publically available annotated datasets which can be used to develop and validate NLP systems ( Kersloot et al, 2020 ). Due to this, there is limited information about the accuracy of NLP healthcare data analysis systems within the literature and it is difficult to compare the existing systems within the research ( Kersloot et al, 2020 ).…”
Section: Discussion and Future Researchmentioning
confidence: 99%
“…In other domains, such as NLP processing of electronic health records, there is an absence of publically available annotated datasets which can be used to develop and validate NLP systems ( Kersloot et al, 2020 ). Due to this, there is limited information about the accuracy of NLP healthcare data analysis systems within the literature and it is difficult to compare the existing systems within the research ( Kersloot et al, 2020 ). The development of publicly available challenge NLP healthcare datasets and better metrics for analyzing the accuracy of such systems is an area which should be worked on by researchers in the future.…”
Section: Discussion and Future Researchmentioning
confidence: 99%
“…Sun et al present the architecture of their semantic processing approach where data is transmitted through the semantic layer with clinical ontologies inside (Sun et al 2015). Most solutions for data interoperability are based on ontologies (Sun et al 2015;Roberts and Demner-Fushman 2016;Freedman et al 2020;Kersloot et al 2020). Moreover, Kersloot et al (2020) show the statistics for mapping clinical text fragments to ontology concepts that are described in reviewed papers.…”
Section: Related Workmentioning
confidence: 99%
“…Most solutions for data interoperability are based on ontologies (Sun et al 2015;Roberts and Demner-Fushman 2016;Freedman et al 2020;Kersloot et al 2020). Moreover, Kersloot et al (2020) show the statistics for mapping clinical text fragments to ontology concepts that are described in reviewed papers. They conclude that 88% of the studies do not present any validation.…”
Section: Related Workmentioning
confidence: 99%
“…Over the last few years, researchers working in clinical medicine have adopted artificial intelligence and deep learning techniques such as Natural Language Processing (NLP). Due to this, electronic health records have become unique data sources because they contain free text annotations that can inform NLP models for a variety of tasks [1][2][3][4][5][6][7] (e.g., risk prediction). On the other hand, public health research appears not to have benefited from NLP algorithms, despite the fact that this research field also has large data sources of text, such as reports and policy briefs 8 .…”
Section: Introductionmentioning
confidence: 99%