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 author

An integrative multi-omics approach points to membrane composition as a key factor in E. coli persistence.

PloS one·2026
Same author

Who's at risk on the road? Demonstrating young and novice driver risk in low-to middle-income contexts.

Journal of safety research·2026
Same author

International multisite implementation of distributed cell-free protein biomanufacturing to advance health and research equity.

Science advances·2026
Same author

Genome sequences of seven <i>Streptomyces</i> isolates for genome prospecting.

Microbiology resource announcements·2026
Same author

Air pollution, driver mutations, and survival in non-small cell lung cancer: insights from a high-altitude Hispanic cohort.

Translational lung cancer research·2026
Same author

Community voices to understand and promote liveability in the Green Corridor urban transformation project in Bogotá, Colombia.

BMC public health·2026

Related Experiment Video

Updated: Sep 26, 2025

Large-Scale SARS-CoV-2 Testing Utilizing Saliva and Transposition Sample Pooling
08:26

Large-Scale SARS-CoV-2 Testing Utilizing Saliva and Transposition Sample Pooling

Published on: June 23, 2022

1.8K

Smart pooling: AI-powered COVID-19 informative group testing.

María Escobar1, Guillaume Jeanneret1, Laura Bravo-Sánchez1

  • 1Center for Research and Formation in Artificial Intelligence, Universidad de los Andes, Bogotá, Colombia.

Scientific Reports
|April 21, 2022
PubMed
Summary
This summary is machine-generated.

Smart Pooling, a machine learning approach, enhances COVID-19 testing efficiency by intelligently grouping patient samples. This method optimizes mass testing strategies, especially when disease incidence is low.

More Related Videos

Efficient SARS-CoV-2 Quantitative Reverse Transcriptase PCR Saliva Diagnostic Strategy utilizing Open-Source Pipetting Robots
11:11

Efficient SARS-CoV-2 Quantitative Reverse Transcriptase PCR Saliva Diagnostic Strategy utilizing Open-Source Pipetting Robots

Published on: February 11, 2022

4.7K
Dynamic Monitoring of Seroconversion using a Multianalyte Immunobead Assay for Covid-19
08:48

Dynamic Monitoring of Seroconversion using a Multianalyte Immunobead Assay for Covid-19

Published on: February 16, 2022

3.0K

Related Experiment Videos

Last Updated: Sep 26, 2025

Large-Scale SARS-CoV-2 Testing Utilizing Saliva and Transposition Sample Pooling
08:26

Large-Scale SARS-CoV-2 Testing Utilizing Saliva and Transposition Sample Pooling

Published on: June 23, 2022

1.8K
Efficient SARS-CoV-2 Quantitative Reverse Transcriptase PCR Saliva Diagnostic Strategy utilizing Open-Source Pipetting Robots
11:11

Efficient SARS-CoV-2 Quantitative Reverse Transcriptase PCR Saliva Diagnostic Strategy utilizing Open-Source Pipetting Robots

Published on: February 11, 2022

4.7K
Dynamic Monitoring of Seroconversion using a Multianalyte Immunobead Assay for Covid-19
08:48

Dynamic Monitoring of Seroconversion using a Multianalyte Immunobead Assay for Covid-19

Published on: February 16, 2022

3.0K

Area of Science:

  • Infectious Disease Epidemiology
  • Computational Biology
  • Public Health

Background:

  • Massive molecular testing is crucial for controlling the COVID-19 pandemic.
  • Current pooling methods for SARS-CoV-2 testing are effective only at low disease incidences.
  • Optimizing testing efficiency is vital for managing widespread outbreaks.

Purpose of the Study:

  • To introduce Smart Pooling, a novel machine learning method for enhancing COVID-19 testing.
  • To improve the efficiency of informed Dorfman testing by creating all-negative sample pools.
  • To leverage clinical and sociodemographic data for more accurate pooling strategies.

Main Methods:

  • Trained machine learning models using a retrospective dataset of over 8000 SARS-CoV-2 tested patients.
  • Simulated test outcomes to estimate efficiency gains with the Smart Pooling predictor.
  • Mathematically computed efficiency gains for non-adaptive pooling schemes.
  • Assessed false-negative error rates for viral genes (ORF1ab and N) in RT-qPCR dilutions.

Main Results:

  • Smart Pooling demonstrated significant efficiency gains in optimizing Dorfman testing for COVID-19.
  • The method successfully arranged samples into all-negative pools, reducing the number of tests required.
  • Proof-of-concept pooled tests validated the efficiency gains of the proposed Smart Pooling scheme.

Conclusions:

  • Smart Pooling offers an efficient strategy for optimizing massive SARS-CoV-2 molecular testing.
  • The integration of machine learning with pooling methods can overcome limitations at low disease incidences.
  • This approach has the potential to improve the scalability and cost-effectiveness of pandemic testing.