PLoS ONE (Jan 2021)

A machine learning based exploration of COVID-19 mortality risk.

  • Mahdi Mahdavi,
  • Hadi Choubdar,
  • Erfan Zabeh,
  • Michael Rieder,
  • Safieddin Safavi-Naeini,
  • Zsolt Jobbagy,
  • Amirata Ghorbani,
  • Atefeh Abedini,
  • Arda Kiani,
  • Vida Khanlarzadeh,
  • Reza Lashgari,
  • Ehsan Kamrani

DOI
https://doi.org/10.1371/journal.pone.0252384
Journal volume & issue
Vol. 16, no. 7
p. e0252384

Abstract

Read online

Early prediction of patient mortality risks during a pandemic can decrease mortality by assuring efficient resource allocation and treatment planning. This study aimed to develop and compare prognosis prediction machine learning models based on invasive laboratory and noninvasive clinical and demographic data from patients' day of admission. Three Support Vector Machine (SVM) models were developed and compared using invasive, non-invasive, and both groups. The results suggested that non-invasive features could provide mortality predictions that are similar to the invasive and roughly on par with the joint model. Feature inspection results from SVM-RFE and sparsity analysis displayed that, compared with the invasive model, the non-invasive model can provide better performances with a fewer number of features, pointing to the presence of high predictive information contents in several non-invasive features, including SPO2, age, and cardiovascular disorders. Furthermore, while the invasive model was able to provide better mortality predictions for the imminent future, non-invasive features displayed better performance for more distant expiration intervals. Early mortality prediction using non-invasive models can give us insights as to where and with whom to intervene. Combined with novel technologies, such as wireless wearable devices, these models can create powerful frameworks for various medical assignments and patient triage.