Scientific Reports (Jul 2021)

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

  • 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

DOI
https://doi.org/10.1038/s41598-021-93719-2
Journal volume & issue
Vol. 11, no. 1
pp. 1 – 13

Abstract

Read online

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.