@inproceedings{lena-al-etal-2023-enriching,
title = "Enriching Electronic Health Record with Semantic Features {U}tilising{P}retrained Transformers",
author = "Lena Al, Mutair and
Eric, Atwell and
Nishant, Ravikumar",
editor = "Jyoti, D. Pawar and
Sobha, Lalitha Devi",
booktitle = "Proceedings of the 20th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2023",
address = "Goa University, Goa, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2023.icon-1.15",
pages = "151--161",
abstract = "Electronic Health Records (EHRs) have revolutionised healthcare by enhancing patient care and facilitating provider communication. Nevertheless, the efficient extraction of valuable information from EHRs poses challenges, primarily due to the overwhelming volume of unstructured data, the wide variability in data formats, and the lack of standardised labels. Leveraging deep learning and concept embeddings, we address the gap in context-aware systems for EHRs. The proposed solution was evaluated on the MIMIC III dataset and demonstrated superior performance compared to other methodologies. We addressed the positive impact of the latent feature combined with the note representation in four different settings. Model performance was evaluated using a case study conducted with BertScore, assessing precision, recall, and F1 scores. The model excels in Medical Natural Language Inference (MedNLI) with an 89.3{\%} accuracy, further boosted to 90.5{\%} through retraining the embeddings using International Classification of Diseases (ICD) codes, which we formally designate as ClinicNarrIR. The ClinicNarrIR was tested with 1000 randomly sampled notes, achieving an N DCG@10 score of approximately 0.54 with accuracy@10 of 0.85. The study also demonstrates a high correlation between the results produced by the proposed representation and medical coders. Notably, in all evaluation cases, the optimal base pretrained model that emerged was BlueBERT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lena-al-etal-2023-enriching">
<titleInfo>
<title>Enriching Electronic Health Record with Semantic Features UtilisingPretrained Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mutair</namePart>
<namePart type="family">Lena Al</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atwell</namePart>
<namePart type="family">Eric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ravikumar</namePart>
<namePart type="family">Nishant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">D</namePart>
<namePart type="given">Pawar</namePart>
<namePart type="family">Jyoti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lalitha</namePart>
<namePart type="given">Devi</namePart>
<namePart type="family">Sobha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Goa University, Goa, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Electronic Health Records (EHRs) have revolutionised healthcare by enhancing patient care and facilitating provider communication. Nevertheless, the efficient extraction of valuable information from EHRs poses challenges, primarily due to the overwhelming volume of unstructured data, the wide variability in data formats, and the lack of standardised labels. Leveraging deep learning and concept embeddings, we address the gap in context-aware systems for EHRs. The proposed solution was evaluated on the MIMIC III dataset and demonstrated superior performance compared to other methodologies. We addressed the positive impact of the latent feature combined with the note representation in four different settings. Model performance was evaluated using a case study conducted with BertScore, assessing precision, recall, and F1 scores. The model excels in Medical Natural Language Inference (MedNLI) with an 89.3% accuracy, further boosted to 90.5% through retraining the embeddings using International Classification of Diseases (ICD) codes, which we formally designate as ClinicNarrIR. The ClinicNarrIR was tested with 1000 randomly sampled notes, achieving an N DCG@10 score of approximately 0.54 with accuracy@10 of 0.85. The study also demonstrates a high correlation between the results produced by the proposed representation and medical coders. Notably, in all evaluation cases, the optimal base pretrained model that emerged was BlueBERT.</abstract>
<identifier type="citekey">lena-al-etal-2023-enriching</identifier>
<location>
<url>https://aclanthology.org/2023.icon-1.15</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>151</start>
<end>161</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enriching Electronic Health Record with Semantic Features UtilisingPretrained Transformers
%A Lena Al, Mutair
%A Eric, Atwell
%A Nishant, Ravikumar
%Y Jyoti, D. Pawar
%Y Sobha, Lalitha Devi
%S Proceedings of the 20th International Conference on Natural Language Processing (ICON)
%D 2023
%8 December
%I NLP Association of India (NLPAI)
%C Goa University, Goa, India
%F lena-al-etal-2023-enriching
%X Electronic Health Records (EHRs) have revolutionised healthcare by enhancing patient care and facilitating provider communication. Nevertheless, the efficient extraction of valuable information from EHRs poses challenges, primarily due to the overwhelming volume of unstructured data, the wide variability in data formats, and the lack of standardised labels. Leveraging deep learning and concept embeddings, we address the gap in context-aware systems for EHRs. The proposed solution was evaluated on the MIMIC III dataset and demonstrated superior performance compared to other methodologies. We addressed the positive impact of the latent feature combined with the note representation in four different settings. Model performance was evaluated using a case study conducted with BertScore, assessing precision, recall, and F1 scores. The model excels in Medical Natural Language Inference (MedNLI) with an 89.3% accuracy, further boosted to 90.5% through retraining the embeddings using International Classification of Diseases (ICD) codes, which we formally designate as ClinicNarrIR. The ClinicNarrIR was tested with 1000 randomly sampled notes, achieving an N DCG@10 score of approximately 0.54 with accuracy@10 of 0.85. The study also demonstrates a high correlation between the results produced by the proposed representation and medical coders. Notably, in all evaluation cases, the optimal base pretrained model that emerged was BlueBERT.
%U https://aclanthology.org/2023.icon-1.15
%P 151-161
Markdown (Informal)
[Enriching Electronic Health Record with Semantic Features UtilisingPretrained Transformers](https://aclanthology.org/2023.icon-1.15) (Lena Al et al., ICON 2023)
ACL