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

Abstract Triaging 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 ana...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Richard Du, Efstratios D. Tsougenis, Joshua W. K. Ho, Joyce K. Y. Chan, Keith W. H. Chiu, Benjamin X. H. Fang, Ming Yen Ng, Siu-Ting Leung, Christine S. Y. Lo, Ho-Yuen F. Wong, Hiu-Yin S. Lam, Long-Fung J. Chiu, Tiffany Y So, Ka Tak Wong, Yiu Chung I. Wong, Kevin Yu, Yiu-Cheong Yeung, Thomas Chik, Joanna W. K. Pang, Abraham Ka-chung Wai, Michael D. Kuo, Tina P. W. Lam, Pek-Lan Khong, Ngai-Tseung Cheung, Varut Vardhanabhuti
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/f01d34f4f45d4097bfbec59ffa2e34af
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:f01d34f4f45d4097bfbec59ffa2e34af
record_format dspace
spelling oai:doaj.org-article:f01d34f4f45d4097bfbec59ffa2e34af2021-12-02T15:23:08ZMachine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph10.1038/s41598-021-93719-22045-2322https://doaj.org/article/f01d34f4f45d4097bfbec59ffa2e34af2021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-93719-2https://doaj.org/toc/2045-2322Abstract Triaging 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.Richard DuEfstratios D. TsougenisJoshua W. K. HoJoyce K. Y. ChanKeith W. H. ChiuBenjamin X. H. FangMing Yen NgSiu-Ting LeungChristine S. Y. LoHo-Yuen F. WongHiu-Yin S. LamLong-Fung J. ChiuTiffany Y SoKa Tak WongYiu Chung I. WongKevin YuYiu-Cheong YeungThomas ChikJoanna W. K. PangAbraham Ka-chung WaiMichael D. KuoTina P. W. LamPek-Lan KhongNgai-Tseung CheungVarut VardhanabhutiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Richard Du
Efstratios D. Tsougenis
Joshua W. K. Ho
Joyce K. Y. Chan
Keith W. H. Chiu
Benjamin X. H. Fang
Ming Yen Ng
Siu-Ting Leung
Christine S. Y. Lo
Ho-Yuen F. Wong
Hiu-Yin S. Lam
Long-Fung J. Chiu
Tiffany Y So
Ka Tak Wong
Yiu Chung I. Wong
Kevin Yu
Yiu-Cheong Yeung
Thomas Chik
Joanna W. K. Pang
Abraham Ka-chung Wai
Michael D. Kuo
Tina P. W. Lam
Pek-Lan Khong
Ngai-Tseung Cheung
Varut Vardhanabhuti
Machine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph
description Abstract Triaging 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.
format article
author Richard Du
Efstratios D. Tsougenis
Joshua W. K. Ho
Joyce K. Y. Chan
Keith W. H. Chiu
Benjamin X. H. Fang
Ming Yen Ng
Siu-Ting Leung
Christine S. Y. Lo
Ho-Yuen F. Wong
Hiu-Yin S. Lam
Long-Fung J. Chiu
Tiffany Y So
Ka Tak Wong
Yiu Chung I. Wong
Kevin Yu
Yiu-Cheong Yeung
Thomas Chik
Joanna W. K. Pang
Abraham Ka-chung Wai
Michael D. Kuo
Tina P. W. Lam
Pek-Lan Khong
Ngai-Tseung Cheung
Varut Vardhanabhuti
author_facet Richard Du
Efstratios D. Tsougenis
Joshua W. K. Ho
Joyce K. Y. Chan
Keith W. H. Chiu
Benjamin X. H. Fang
Ming Yen Ng
Siu-Ting Leung
Christine S. Y. Lo
Ho-Yuen F. Wong
Hiu-Yin S. Lam
Long-Fung J. Chiu
Tiffany Y So
Ka Tak Wong
Yiu Chung I. Wong
Kevin Yu
Yiu-Cheong Yeung
Thomas Chik
Joanna W. K. Pang
Abraham Ka-chung Wai
Michael D. Kuo
Tina P. W. Lam
Pek-Lan Khong
Ngai-Tseung Cheung
Varut Vardhanabhuti
author_sort Richard Du
title Machine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph
title_short Machine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph
title_full Machine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph
title_fullStr Machine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph
title_full_unstemmed Machine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph
title_sort machine learning application for the prediction of sars-cov-2 infection using blood tests and chest radiograph
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/f01d34f4f45d4097bfbec59ffa2e34af
work_keys_str_mv AT richarddu machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT efstratiosdtsougenis machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT joshuawkho machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT joycekychan machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT keithwhchiu machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT benjaminxhfang machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT mingyenng machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT siutingleung machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT christinesylo machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT hoyuenfwong machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT hiuyinslam machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT longfungjchiu machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT tiffanyyso machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT katakwong machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT yiuchungiwong machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT kevinyu machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT yiucheongyeung machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT thomaschik machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT joannawkpang machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT abrahamkachungwai machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT michaeldkuo machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT tinapwlam machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT peklankhong machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT ngaitseungcheung machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
AT varutvardhanabhuti machinelearningapplicationforthepredictionofsarscov2infectionusingbloodtestsandchestradiograph
_version_ 1718387360961396736