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 Experiment Videos

Neural network approach to classify infective keratitis.

Jagjit S Saini1, Arun Kumar Jain, Sanjay Kumar

  • 1Advanced Eye Center, Department of Ophthalmology, Post Graduate Institute of Medical Education & Research, Chandigarh, India. jssainichd@hotmail.com

Current Eye Research
|November 25, 2003
PubMed
Summary

Artificial neural networks (ANNs) can accurately classify infectious keratitis, a leading cause of blindness in India. This AI approach shows potential for improving diagnosis and treatment of corneal ulcers.

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

Management of post-cataract surgery corneal fungal tunnel infections.

International ophthalmology·2025
Same author

Decreased activity of acetylcholine esterase as a biomarker of pesticide exposure in female tea plantation workers.

Toxicology and industrial health·2025
Same author

Pesticide Exposure in Agricultural Workplaces and Resultant Health Effects in Women.

Birth defects research·2025
Same author

Post-campaign coverage evaluation of a measles and rubella supplementary immunization activity in five districts in India, 2019-2020.

PloS one·2024
Same author

Correlation of anterior segment optical coherence tomography and ultrasound biomicroscopy in congenital corneal opacity.

Journal of AAPOS : the official publication of the American Association for Pediatric Ophthalmology and Strabismus·2024
Same author

Integrated bioinformatics approach to unwind key genes and pathways involved in colorectal cancer.

Journal of cancer research and therapeutics·2024

Area of Science:

  • Ophthalmology
  • Medical Artificial Intelligence
  • Infectious Diseases

Background:

  • Infective keratitis is a significant cause of vision loss, particularly in developing nations.
  • Accurate and timely diagnosis is crucial for effective treatment of corneal ulcers.
  • Understanding epidemiological trends and clinical features aids in initial treatment decisions.

Purpose of the Study:

  • To evaluate the utility of artificial neural networks (ANNs) for classifying infective keratitis.
  • To compare ANN diagnostic accuracy against clinical predictions.

Main Methods:

  • A three-layer feed-forward neural network was trained using 40 input variables from 63 known bacterial or fungal corneal ulcers.
  • The trained ANN was then used to classify an independent set of 43 corneal ulcers.

Related Experiment Videos

Main Results:

  • The ANN achieved 100% accuracy on the training set (63 ulcers).
  • In the test set (43 ulcers), the ANN correctly classified 39 cases (90.7% accuracy).
  • ANN classification accuracy (90.7%) significantly outperformed clinicians' predictions (62.8%, p < 0.01).

Conclusions:

  • Artificial neural networks demonstrate significant potential in enhancing the accuracy of corneal ulcer classification.
  • ANNs can serve as a valuable tool to assist clinicians in diagnosing infective keratitis.
  • Improved diagnostic accuracy through AI may lead to better patient outcomes for sight-threatening corneal conditions.