File Download
  Links for fulltext
     (May Require Subscription)

Article: Machine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph

TitleMachine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph
Authors
Issue Date2021
PublisherNature Research: Fully open access journals. The Journal's web site is located at http://www.nature.com/srep/index.html
Citation
Scientific Reports, 2021, v. 11, p. article no. 14250 How to Cite?
AbstractTriaging and prioritising patients for RT-PCR test had been essential in the management of COVID-19 in resource-scarce countries. In this study, we applied machine learning (ML) to the task of detection of SARS-CoV-2 infection using basic laboratory markers. We performed the statistical analysis and trained an ML model on a retrospective cohort of 5148 patients from 24 hospitals in Hong Kong to classify COVID-19 and other aetiology of pneumonia. We validated the model on three temporal validation sets from different waves of infection in Hong Kong. For predicting SARS-CoV-2 infection, the ML model achieved high AUCs and specificity but low sensitivity in all three validation sets (AUC: 89.9–95.8%; Sensitivity: 55.5–77.8%; Specificity: 91.5–98.3%). When used in adjunction with radiologist interpretations of chest radiographs, the sensitivity was over 90% while keeping moderate specificity. Our study showed that machine learning model based on readily available laboratory markers could achieve high accuracy in predicting SARS-CoV-2 infection.
Persistent Identifierhttp://hdl.handle.net/10722/306446
ISSN
2023 Impact Factor: 3.8
2023 SCImago Journal Rankings: 0.900
PubMed Central ID
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorDu, R-
dc.contributor.authorTsougenis, ED-
dc.contributor.authorHo, JWK-
dc.contributor.authorChan, JKY-
dc.contributor.authorChiu, KWH-
dc.contributor.authorFang, BXH-
dc.contributor.authorNg, MY-
dc.contributor.authorLeung, ST-
dc.contributor.authorLo, CSY-
dc.contributor.authorWong, HYF-
dc.contributor.authorLam, HYS-
dc.contributor.authorChiu, LFJ-
dc.contributor.authorSo, TY-
dc.contributor.authorWong, KT-
dc.contributor.authorWong, YCI-
dc.contributor.authorYu, K-
dc.contributor.authorYeung, YC-
dc.contributor.authorChik, T-
dc.contributor.authorPang, JWK-
dc.contributor.authorWai, AKC-
dc.contributor.authorKuo, MD-
dc.contributor.authorLam, TPW-
dc.contributor.authorKhong, PL-
dc.contributor.authorCheung, NT-
dc.contributor.authorVardhanabhuti, V-
dc.date.accessioned2021-10-22T07:34:44Z-
dc.date.available2021-10-22T07:34:44Z-
dc.date.issued2021-
dc.identifier.citationScientific Reports, 2021, v. 11, p. article no. 14250-
dc.identifier.issn2045-2322-
dc.identifier.urihttp://hdl.handle.net/10722/306446-
dc.description.abstractTriaging and prioritising patients for RT-PCR test had been essential in the management of COVID-19 in resource-scarce countries. In this study, we applied machine learning (ML) to the task of detection of SARS-CoV-2 infection using basic laboratory markers. We performed the statistical analysis and trained an ML model on a retrospective cohort of 5148 patients from 24 hospitals in Hong Kong to classify COVID-19 and other aetiology of pneumonia. We validated the model on three temporal validation sets from different waves of infection in Hong Kong. For predicting SARS-CoV-2 infection, the ML model achieved high AUCs and specificity but low sensitivity in all three validation sets (AUC: 89.9–95.8%; Sensitivity: 55.5–77.8%; Specificity: 91.5–98.3%). When used in adjunction with radiologist interpretations of chest radiographs, the sensitivity was over 90% while keeping moderate specificity. Our study showed that machine learning model based on readily available laboratory markers could achieve high accuracy in predicting SARS-CoV-2 infection.-
dc.languageeng-
dc.publisherNature Research: Fully open access journals. The Journal's web site is located at http://www.nature.com/srep/index.html-
dc.relation.ispartofScientific Reports-
dc.rightsScientific Reports. Copyright © Nature Research: Fully open access journals.-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.titleMachine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph-
dc.typeArticle-
dc.identifier.emailHo, JWK: jwkho@hku.hk-
dc.identifier.emailNg, MY: myng2@hku.hk-
dc.identifier.emailWai, AKC: awai@hku.hk-
dc.identifier.emailVardhanabhuti, V: varv@hku.hk-
dc.identifier.authorityHo, JWK=rp02436-
dc.identifier.authorityChiu, KWH=rp02074-
dc.identifier.authorityNg, MY=rp01976-
dc.identifier.authorityWai, AKC=rp02261-
dc.identifier.authorityKhong, PL=rp00467-
dc.identifier.authorityVardhanabhuti, V=rp01900-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1038/s41598-021-93719-2-
dc.identifier.pmid34244563-
dc.identifier.pmcidPMC8270945-
dc.identifier.scopuseid_2-s2.0-85109742102-
dc.identifier.hkuros328845-
dc.identifier.volume11-
dc.identifier.spagearticle no. 14250-
dc.identifier.epagearticle no. 14250-
dc.identifier.isiWOS:000674491200027-
dc.publisher.placeUnited Kingdom-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats