Cargando…

Generalizability of machine learning methods in detecting adverse drug events from clinical narratives in electronic medical records

We assessed the generalizability of machine learning methods using natural language processing (NLP) techniques to detect adverse drug events (ADEs) from clinical narratives in electronic medical records (EMRs). We constructed a new corpus correlating drugs with adverse drug events using 1,394 clini...

Descripción completa

Detalles Bibliográficos
Autores principales: Zitu, Md Muntasir, Zhang, Shijun, Owen, Dwight H., Chiang, Chienwei, Li, Lang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10368879/
https://www.ncbi.nlm.nih.gov/pubmed/37502211
http://dx.doi.org/10.3389/fphar.2023.1218679
_version_ 1785077599998836736
author Zitu, Md Muntasir
Zhang, Shijun
Owen, Dwight H.
Chiang, Chienwei
Li, Lang
author_facet Zitu, Md Muntasir
Zhang, Shijun
Owen, Dwight H.
Chiang, Chienwei
Li, Lang
author_sort Zitu, Md Muntasir
collection PubMed
description We assessed the generalizability of machine learning methods using natural language processing (NLP) techniques to detect adverse drug events (ADEs) from clinical narratives in electronic medical records (EMRs). We constructed a new corpus correlating drugs with adverse drug events using 1,394 clinical notes of 47 randomly selected patients who received immune checkpoint inhibitors (ICIs) from 2011 to 2018 at The Ohio State University James Cancer Hospital, annotating 189 drug-ADE relations in single sentences within the medical records. We also used data from Harvard’s publicly available 2018 National Clinical Challenge (n2c2), which includes 505 discharge summaries with annotations of 1,355 single-sentence drug-ADE relations. We applied classical machine learning (support vector machine (SVM)), deep learning (convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM)), and state-of-the-art transformer-based (bidirectional encoder representations from transformers (BERT) and ClinicalBERT) methods trained and tested in the two different corpora and compared performance among them to detect drug–ADE relationships. ClinicalBERT detected drug–ADE relationships better than the other methods when trained using our dataset and tested in n2c2 (ClinicalBERT F-score, 0.78; other methods, F-scores, 0.61–0.73) and when trained using the n2c2 dataset and tested in ours (ClinicalBERT F-score, 0.74; other methods, F-scores, 0.55–0.72). Comparison among several machine learning methods demonstrated the superior performance and, therefore, the greatest generalizability of findings of ClinicalBERT for the detection of drug–ADE relations from clinical narratives in electronic medical records.
format Online
Article
Text
id pubmed-10368879
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-103688792023-07-27 Generalizability of machine learning methods in detecting adverse drug events from clinical narratives in electronic medical records Zitu, Md Muntasir Zhang, Shijun Owen, Dwight H. Chiang, Chienwei Li, Lang Front Pharmacol Pharmacology We assessed the generalizability of machine learning methods using natural language processing (NLP) techniques to detect adverse drug events (ADEs) from clinical narratives in electronic medical records (EMRs). We constructed a new corpus correlating drugs with adverse drug events using 1,394 clinical notes of 47 randomly selected patients who received immune checkpoint inhibitors (ICIs) from 2011 to 2018 at The Ohio State University James Cancer Hospital, annotating 189 drug-ADE relations in single sentences within the medical records. We also used data from Harvard’s publicly available 2018 National Clinical Challenge (n2c2), which includes 505 discharge summaries with annotations of 1,355 single-sentence drug-ADE relations. We applied classical machine learning (support vector machine (SVM)), deep learning (convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM)), and state-of-the-art transformer-based (bidirectional encoder representations from transformers (BERT) and ClinicalBERT) methods trained and tested in the two different corpora and compared performance among them to detect drug–ADE relationships. ClinicalBERT detected drug–ADE relationships better than the other methods when trained using our dataset and tested in n2c2 (ClinicalBERT F-score, 0.78; other methods, F-scores, 0.61–0.73) and when trained using the n2c2 dataset and tested in ours (ClinicalBERT F-score, 0.74; other methods, F-scores, 0.55–0.72). Comparison among several machine learning methods demonstrated the superior performance and, therefore, the greatest generalizability of findings of ClinicalBERT for the detection of drug–ADE relations from clinical narratives in electronic medical records. Frontiers Media S.A. 2023-07-12 /pmc/articles/PMC10368879/ /pubmed/37502211 http://dx.doi.org/10.3389/fphar.2023.1218679 Text en Copyright © 2023 Zitu, Zhang, Owen, Chiang and Li. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Pharmacology
Zitu, Md Muntasir
Zhang, Shijun
Owen, Dwight H.
Chiang, Chienwei
Li, Lang
Generalizability of machine learning methods in detecting adverse drug events from clinical narratives in electronic medical records
title Generalizability of machine learning methods in detecting adverse drug events from clinical narratives in electronic medical records
title_full Generalizability of machine learning methods in detecting adverse drug events from clinical narratives in electronic medical records
title_fullStr Generalizability of machine learning methods in detecting adverse drug events from clinical narratives in electronic medical records
title_full_unstemmed Generalizability of machine learning methods in detecting adverse drug events from clinical narratives in electronic medical records
title_short Generalizability of machine learning methods in detecting adverse drug events from clinical narratives in electronic medical records
title_sort generalizability of machine learning methods in detecting adverse drug events from clinical narratives in electronic medical records
topic Pharmacology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10368879/
https://www.ncbi.nlm.nih.gov/pubmed/37502211
http://dx.doi.org/10.3389/fphar.2023.1218679
work_keys_str_mv AT zitumdmuntasir generalizabilityofmachinelearningmethodsindetectingadversedrugeventsfromclinicalnarrativesinelectronicmedicalrecords
AT zhangshijun generalizabilityofmachinelearningmethodsindetectingadversedrugeventsfromclinicalnarrativesinelectronicmedicalrecords
AT owendwighth generalizabilityofmachinelearningmethodsindetectingadversedrugeventsfromclinicalnarrativesinelectronicmedicalrecords
AT chiangchienwei generalizabilityofmachinelearningmethodsindetectingadversedrugeventsfromclinicalnarrativesinelectronicmedicalrecords
AT lilang generalizabilityofmachinelearningmethodsindetectingadversedrugeventsfromclinicalnarrativesinelectronicmedicalrecords