Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature With Unsupervised Word Embeddings and Machine Learning: Evidence-Based Study
BackgroundEvidence from peer-reviewed literature is the cornerstone for designing responses to global threats such as COVID-19. In massive and rapidly growing corpuses, such as COVID-19 publications, assimilating and synthesizing information is challenging. Leveraging a robus...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
JMIR Publications
2022-11-01
|
Series: | Journal of Medical Internet Research |
Online Access: | https://www.jmir.org/2022/11/e34067 |
_version_ | 1797734696156659712 |
---|---|
author | Ridam Pal Harshita Chopra Raghav Awasthi Harsh Bandhey Aditya Nagori Tavpritesh Sethi |
author_facet | Ridam Pal Harshita Chopra Raghav Awasthi Harsh Bandhey Aditya Nagori Tavpritesh Sethi |
author_sort | Ridam Pal |
collection | DOAJ |
description |
BackgroundEvidence from peer-reviewed literature is the cornerstone for designing responses to global threats such as COVID-19. In massive and rapidly growing corpuses, such as COVID-19 publications, assimilating and synthesizing information is challenging. Leveraging a robust computational pipeline that evaluates multiple aspects, such as network topological features, communities, and their temporal trends, can make this process more efficient.
ObjectiveWe aimed to show that new knowledge can be captured and tracked using the temporal change in the underlying unsupervised word embeddings of the literature. Further imminent themes can be predicted using machine learning on the evolving associations between words.
MethodsFrequently occurring medical entities were extracted from the abstracts of more than 150,000 COVID-19 articles published on the World Health Organization database, collected on a monthly interval starting from February 2020. Word embeddings trained on each month’s literature were used to construct networks of entities with cosine similarities as edge weights. Topological features of the subsequent month’s network were forecasted based on prior patterns, and new links were predicted using supervised machine learning. Community detection and alluvial diagrams were used to track biomedical themes that evolved over the months.
ResultsWe found that thromboembolic complications were detected as an emerging theme as early as August 2020. A shift toward the symptoms of long COVID complications was observed during March 2021, and neurological complications gained significance in June 2021. A prospective validation of the link prediction models achieved an area under the receiver operating characteristic curve of 0.87. Predictive modeling revealed predisposing conditions, symptoms, cross-infection, and neurological complications as dominant research themes in COVID-19 publications based on the patterns observed in previous months.
ConclusionsMachine learning–based prediction of emerging links can contribute toward steering research by capturing themes represented by groups of medical entities, based on patterns of semantic relationships over time. |
first_indexed | 2024-03-12T12:47:07Z |
format | Article |
id | doaj.art-20d245763cd948f1b4cab9ba116fffcc |
institution | Directory Open Access Journal |
issn | 1438-8871 |
language | English |
last_indexed | 2024-03-12T12:47:07Z |
publishDate | 2022-11-01 |
publisher | JMIR Publications |
record_format | Article |
series | Journal of Medical Internet Research |
spelling | doaj.art-20d245763cd948f1b4cab9ba116fffcc2023-08-28T23:13:10ZengJMIR PublicationsJournal of Medical Internet Research1438-88712022-11-012411e3406710.2196/34067Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature With Unsupervised Word Embeddings and Machine Learning: Evidence-Based StudyRidam Palhttps://orcid.org/0000-0003-1561-1173Harshita Choprahttps://orcid.org/0000-0003-3331-2003Raghav Awasthihttps://orcid.org/0000-0002-6643-4333Harsh Bandheyhttps://orcid.org/0000-0002-4113-0616Aditya Nagorihttps://orcid.org/0000-0002-6389-2179Tavpritesh Sethihttps://orcid.org/0000-0002-4776-7941 BackgroundEvidence from peer-reviewed literature is the cornerstone for designing responses to global threats such as COVID-19. In massive and rapidly growing corpuses, such as COVID-19 publications, assimilating and synthesizing information is challenging. Leveraging a robust computational pipeline that evaluates multiple aspects, such as network topological features, communities, and their temporal trends, can make this process more efficient. ObjectiveWe aimed to show that new knowledge can be captured and tracked using the temporal change in the underlying unsupervised word embeddings of the literature. Further imminent themes can be predicted using machine learning on the evolving associations between words. MethodsFrequently occurring medical entities were extracted from the abstracts of more than 150,000 COVID-19 articles published on the World Health Organization database, collected on a monthly interval starting from February 2020. Word embeddings trained on each month’s literature were used to construct networks of entities with cosine similarities as edge weights. Topological features of the subsequent month’s network were forecasted based on prior patterns, and new links were predicted using supervised machine learning. Community detection and alluvial diagrams were used to track biomedical themes that evolved over the months. ResultsWe found that thromboembolic complications were detected as an emerging theme as early as August 2020. A shift toward the symptoms of long COVID complications was observed during March 2021, and neurological complications gained significance in June 2021. A prospective validation of the link prediction models achieved an area under the receiver operating characteristic curve of 0.87. Predictive modeling revealed predisposing conditions, symptoms, cross-infection, and neurological complications as dominant research themes in COVID-19 publications based on the patterns observed in previous months. ConclusionsMachine learning–based prediction of emerging links can contribute toward steering research by capturing themes represented by groups of medical entities, based on patterns of semantic relationships over time.https://www.jmir.org/2022/11/e34067 |
spellingShingle | Ridam Pal Harshita Chopra Raghav Awasthi Harsh Bandhey Aditya Nagori Tavpritesh Sethi Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature With Unsupervised Word Embeddings and Machine Learning: Evidence-Based Study Journal of Medical Internet Research |
title | Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature With Unsupervised Word Embeddings and Machine Learning: Evidence-Based Study |
title_full | Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature With Unsupervised Word Embeddings and Machine Learning: Evidence-Based Study |
title_fullStr | Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature With Unsupervised Word Embeddings and Machine Learning: Evidence-Based Study |
title_full_unstemmed | Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature With Unsupervised Word Embeddings and Machine Learning: Evidence-Based Study |
title_short | Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature With Unsupervised Word Embeddings and Machine Learning: Evidence-Based Study |
title_sort | predicting emerging themes in rapidly expanding covid 19 literature with unsupervised word embeddings and machine learning evidence based study |
url | https://www.jmir.org/2022/11/e34067 |
work_keys_str_mv | AT ridampal predictingemergingthemesinrapidlyexpandingcovid19literaturewithunsupervisedwordembeddingsandmachinelearningevidencebasedstudy AT harshitachopra predictingemergingthemesinrapidlyexpandingcovid19literaturewithunsupervisedwordembeddingsandmachinelearningevidencebasedstudy AT raghavawasthi predictingemergingthemesinrapidlyexpandingcovid19literaturewithunsupervisedwordembeddingsandmachinelearningevidencebasedstudy AT harshbandhey predictingemergingthemesinrapidlyexpandingcovid19literaturewithunsupervisedwordembeddingsandmachinelearningevidencebasedstudy AT adityanagori predictingemergingthemesinrapidlyexpandingcovid19literaturewithunsupervisedwordembeddingsandmachinelearningevidencebasedstudy AT tavpriteshsethi predictingemergingthemesinrapidlyexpandingcovid19literaturewithunsupervisedwordembeddingsandmachinelearningevidencebasedstudy |