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

Hollow MnO<sub>2</sub> Nanozyme with NO Prodrug to Boost Synergistic CDT/PDT/Gas Therapy via Oxidative Stress Cascade.

International journal of nanomedicine·2026
Same author

Photothermal targeting of lactate metabolism reverses radioresistance via disrupting the immunosuppressive barrier.

Biomaterials·2026
Same author

Smart Nanodelivery Systems for Immunometabolic Modulation in Osteoarthritis.

Exploration (Beijing, China)·2026
Same author

Recombinant RBD-based subunit vaccines incorporating high-frequency mutation sites elicit cross-immunity and robust protection against SARS-CoV-2.

Frontiers in microbiology·2026
Same author

Provoking disulfidptosis-enhanced mitophagy by manganese-based nanoplatform via regulating cellular energy supply and redox homeostasis.

Materials today. Bio·2026
Same author

Wireless, Deep-Seeing Smart Pill: A NIR-II Fluorescence Imaging Capsule Endoscope for Gastrointestinal Cancer.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Related Experiment Video

Updated: Sep 28, 2025

Fully Automated Centrifugal Microfluidic Device for Ultrasensitive Protein Detection from Whole Blood
08:58

Fully Automated Centrifugal Microfluidic Device for Ultrasensitive Protein Detection from Whole Blood

Published on: April 16, 2016

10.7K

Rapid segmentation and sensitive analysis of CRP with paper-based microfluidic device using machine learning.

Qihong Ning1, Wei Zheng1, Hao Xu2

  • 1School of Sensing Science and Engineering, School of Electronic Information and Electrical Engineering, Key Laboratory of Thin Film and Microfabrication Technology (Ministry of Education), Shanghai Jiao Tong University, Shanghai, 200240, China.

Analytical and Bioanalytical Chemistry
|March 30, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a machine learning approach to improve C-reactive protein (CRP) detection accuracy on microfluidic paper-based analytical devices (μPADs). A residual network algorithm achieved 96% accuracy in classifying CRP levels, enhancing point-of-care diagnostics.

Keywords:
C-reactive protein (CRP)Machine learningResNetYOLOμPADs

More Related Videos

Fabrication of Three-dimensional Paper-based Microfluidic Devices for Immunoassays
11:33

Fabrication of Three-dimensional Paper-based Microfluidic Devices for Immunoassays

Published on: March 9, 2017

15.9K
Dry Film Photoresist-based Electrochemical Microfluidic Biosensor Platform: Device Fabrication, On-chip Assay Preparation, and System Operation
13:42

Dry Film Photoresist-based Electrochemical Microfluidic Biosensor Platform: Device Fabrication, On-chip Assay Preparation, and System Operation

Published on: September 19, 2017

11.9K

Related Experiment Videos

Last Updated: Sep 28, 2025

Fully Automated Centrifugal Microfluidic Device for Ultrasensitive Protein Detection from Whole Blood
08:58

Fully Automated Centrifugal Microfluidic Device for Ultrasensitive Protein Detection from Whole Blood

Published on: April 16, 2016

10.7K
Fabrication of Three-dimensional Paper-based Microfluidic Devices for Immunoassays
11:33

Fabrication of Three-dimensional Paper-based Microfluidic Devices for Immunoassays

Published on: March 9, 2017

15.9K
Dry Film Photoresist-based Electrochemical Microfluidic Biosensor Platform: Device Fabrication, On-chip Assay Preparation, and System Operation
13:42

Dry Film Photoresist-based Electrochemical Microfluidic Biosensor Platform: Device Fabrication, On-chip Assay Preparation, and System Operation

Published on: September 19, 2017

11.9K

Area of Science:

  • Biomedical Engineering
  • Analytical Chemistry
  • Machine Learning Applications

Background:

  • Microfluidic paper-based analytical devices (μPADs) offer advantages for point-of-care testing, including simplicity and low sample volume.
  • Accurate quantitative results from μPADs are challenged by variations in reaction conditions and image acquisition.
  • C-reactive protein (CRP) is a key biomarker for inflammation and infection, necessitating reliable detection methods.

Purpose of the Study:

  • To enhance the accuracy and reliability of CRP detection using multi-layer μPADs.
  • To develop a machine learning-based method for analyzing colorimetric signals from μPADs under varying conditions.
  • To investigate the efficacy of different machine learning algorithms for CRP concentration classification.

Main Methods:

  • Fabrication of multi-layer μPADs using an imprinting method for colorimetric CRP detection.
  • Simulation of diverse lighting conditions and shooting angles during image acquisition.
  • Application of the You Only Look Once (YOLO) model for identifying reaction areas within μPAD images.
  • Classification of identified reaction areas using Multi-layer Perceptron (MLP), Convolutional Neural Network (CNN), and Residual Network (ResNet) algorithms.

Main Results:

  • The YOLO model successfully identified all reaction areas in μPADs without errors.
  • The residual network algorithm achieved the highest classification accuracy of 96% for determining CRP concentration levels.
  • The developed machine learning approach improved the detection-related performance of μPADs under simulated adverse imaging conditions.

Conclusions:

  • Machine learning, particularly the residual network, significantly enhances the accuracy of CRP detection on μPADs.
  • The YOLO model provides efficient and accurate localization of reaction zones on μPADs.
  • This integrated approach shows strong potential for fast, reliable, and automated analysis in point-of-care diagnostics.