Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same journal

Opioid Overdose Detection in a Murine Model Using a Custom-Designed Photoplethysmography Device.

Ingenierie et recherche biomedicale : IRBM = Biomedical engineering and research·2025
Same journal

Contents.

Ingenierie et recherche biomedicale : IRBM = Biomedical engineering and research·2023
Same journal

An Adaptive Low-Rank Modeling-Based Active Learning Method for Medical Image Annotation.

Ingenierie et recherche biomedicale : IRBM = Biomedical engineering and research·2021
Same journal

AI for COVID-19 Detection from Radiographs: Incisive Analysis of State of the Art Techniques, Key Challenges and Future Directions.

Ingenierie et recherche biomedicale : IRBM = Biomedical engineering and research·2021
Same journal

COVID-19 Detection System Using Chest CT Images and Multiple Kernels-Extreme Learning Machine Based on Deep Neural Network.

Ingenierie et recherche biomedicale : IRBM = Biomedical engineering and research·2021
Same journal

Automated Deep Transfer Learning-Based Approach for Detection of COVID-19 Infection in Chest X-rays.

Ingenierie et recherche biomedicale : IRBM = Biomedical engineering and research·2020

Related Experiment Video

Updated: Sep 20, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.7K

Automatic Detection of Severely and Mildly Infected COVID-19 Patients with Supervised Machine Learning Models.

M T Huyut1

  • 1Department of Biostatistics and Medical Informatics, Medical Faculty, Erzincan Binali Yıldırım University, 24100, Erzincan, Turkey.

Ingenierie Et Recherche Biomedicale : IRBM = Biomedical Engineering and Research
|June 8, 2022
PubMed
Summary

Early detection of COVID-19 prognosis using routine blood values (RBV) and demographic data aids healthcare. Machine learning models accurately identified severe and mild cases upon admission, reducing healthcare strain.

Keywords:
Biochemical and hematological biomarkersCOVID-19ClassificationFeature selection methodsRoutine blood valuesSupervised machine learning models

More Related Videos

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.6K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

892

Related Experiment Videos

Last Updated: Sep 20, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.7K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.6K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

892

Area of Science:

  • Medical Informatics
  • Machine Learning in Healthcare
  • COVID-19 Prognostics

Background:

  • Early detection of COVID-19 prognosis can alleviate healthcare system pressure.
  • Identifying disease severity at admission is crucial for resource allocation and patient management.

Purpose of the Study:

  • To identify routine blood values (RBV) and demographic data features that predict COVID-19 prognosis.
  • To apply supervised machine learning (ML) models to classify patients with severe versus mild COVID-19 upon hospital admission.

Main Methods:

  • Retrospective analysis of RBV and demographic data from 4204 hospitalized COVID-19 patients (March-September 2021).
  • Feature selection using Minimum Redundancy Maximum Relevance (MRMR), Principal Component Analysis, and forward multiple logistic regression.
  • Performance evaluation of ML models including Local Weighted Learning (LWL), K-star (K*), Naive Bayes (NB), and K-Nearest Neighbors (KNN).

Main Results:

  • A feature dataset comprising 28 RBV parameters and age was identified as significant for COVID-19 prognosis.
  • Local Weighted Learning (LWL) achieved the highest accuracy (97.86%) and Area Under the Curve (AUC) (0.95) in classifying patient severity.
  • Other models like K-star, Naive Bayes, and KNN also demonstrated high performance in differentiating between mild and severe COVID-19 cases.

Conclusions:

  • The identified features and ML models provide a valuable tool for healthcare professionals.
  • Early and accurate identification of COVID-19 severity at admission is feasible using routine clinical data and machine learning.
  • These findings can support timely clinical decisions and optimize healthcare resource utilization.