Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Using Machine Learning to Estimate Unobserved COVID-19 Infections in North America.

The Journal of bone and joint surgery. American volume·2020

Same author

Risk of a second wave of Covid-19 infections: using artificial intelligence to investigate stringency of physical distancing policies in North America.

International orthopaedics·2020

Same author

Cochrane in CORR (®): Interventions for Treating Proximal Humeral Fractures in Adults (Review).

Clinical orthopaedics and related research·2015

Same author

The fragility of statistically significant findings from randomized trials in spine surgery: a systematic survey.

The spine journal : official journal of the North American Spine Society·2015

Same author

Strategies to improve the credibility of meta-analyses in spine surgery: a systematic survey.

The spine journal : official journal of the North American Spine Society·2015

Same author

Are Volar Locking Plates Superior to Percutaneous K-wires for Distal Radius Fractures? A Meta-analysis.

Clinical orthopaedics and related research·2015

Search research articles

Related Experiment Video

Updated: Dec 20, 2025

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

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

Published on: May 10, 2024

Deep learning COVID-19 detection bias: accuracy through artificial intelligence.

Shashank Vaid¹, Reza Kalantar², Mohit Bhandari³

¹DeGroote School of Business, McMaster University, 1280 Main Street W, Hamilton, Ontario, L8S 4 M4, Canada. vaids1@mcmaster.ca.

International Orthopaedics

|May 29, 2020

Summary

A novel deep learning model accurately detects COVID-19 from chest X-rays, achieving over 96.3% accuracy. This AI tool minimizes false negatives and positives, aiding in precise disease diagnosis and management.

Keywords:

Artificial intelligence COVID-19 Deep learning Detection bias

More Related Videos

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

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

Published on: October 27, 2023

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Dec 20, 2025

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

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

Published on: May 10, 2024

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

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

Published on: October 27, 2023

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Area of Science:

Medical Imaging
Artificial Intelligence
Infectious Diseases

Background:

Accurate COVID-19 detection remains a challenge, with concerns about missed infections and false-negative test results.
The global impact of COVID-19 necessitates reliable diagnostic tools to manage the pandemic effectively.
Publicly available data on test accuracy, particularly concerning false negatives, is limited, increasing diagnostic uncertainty.

Purpose of the Study:

To develop and validate a deep learning model for accurate COVID-19 detection using chest X-ray scans.
To improve the precision of reported COVID-19 cases through automated analysis of radiographic data.
To address the limitations of existing diagnostic methods by reducing reliance on manual interpretation and minimizing diagnostic errors.

Main Methods:

A deep learning model utilizing convolutional neural networks (CNNs) was developed for disease detection and categorization.
Transfer learning techniques were employed to analyze anterior-posterior chest radiographs from publicly available datasets.
The model was trained and validated on diverse international patient data to ensure generalizability.

Main Results:

The deep learning model achieved a high accuracy of 96.3% with a binary cross-entropy loss of 0.151.
The model demonstrated strong performance in identifying true negatives (74 cases) and true positives (32 cases).
Analysis revealed a low rate of misclassification, with only three false-positive and one false-negative finding among healthy patient scans.

Conclusions:

The developed deep learning model automates the identification of structural abnormalities in chest X-rays, reducing the need for manual radiologist input.
The AI model shows significant potential in accurately distinguishing between true and false positives and negatives, exceeding 96.3% accuracy.
This automated approach offers a reliable and efficient method for COVID-19 detection, improving diagnostic accuracy and patient outcomes.