Affordable Access

deepdyve-link
Publisher Website

Ensemble learning model for diagnosing COVID-19 from routine blood tests

Authors
  • AlJame, Maryam1
  • Ahmad, Imtiaz1
  • Imtiaz, Ayyub2
  • Mohammed, Ameer1
  • 1 Computer Engineering Department, Kuwait University, Kuwait
  • 2 College of Medicine, Kuwait University, Kuwait
Type
Published Article
Journal
Informatics in Medicine Unlocked
Publisher
The Author(s). Published by Elsevier Ltd.
Publication Date
Oct 20, 2020
Volume
21
Pages
100449–100449
Identifiers
DOI: 10.1016/j.imu.2020.100449
PMID: 33102686
PMCID: PMC7572278
Source
PubMed Central
Keywords
License
Unknown

Abstract

• State-of-the-art review on emerging machine learning techniques for diagnosing COVID-19 from routine laboratory and clinical data. • Proposed an ensemble learning model for initial screening of COVID-19 patients from routine blood tests. • Achieved high accuracy of 99.88% in distinguishing COVID-19 positive cases from normal ones. • ERLX model provides more accessible and less costly alternative tool for an accurate early screening of COVID-19 patients.

Report this publication

Statistics

Seen <100 times