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 computer program to determine photorefractive keratectomy nomograms

S H Yang1, R N Van Gelder, J S Pepose

  • 1Department of Ophthalmology and Visual Sciences, Washington University School of Medicine, St. Louis, Missouri 63110, USA.

Journal of Cataract and Refractive Surgery
|July 31, 1998
PubMed
Summary

A neural network program showed potential for personalizing photorefractive keratectomy (PRK) nomograms. However, a small dataset limited its accuracy in predicting individual patient outcomes for PRK treatment.

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

A Novel Multi-Cross-linking Diluent System to Stabilize Self-Etch Bonding.

Journal of dental research·2026
Same author

[Association between residential greenness exposure and obesity risk based on remote sensing].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2026
Same author

Application of artificial intelligence on magnetocardiology.

Clinical hemorheology and microcirculation·2026
Same author

Effects of partial replacement of soybean meal by flaxseed cake on growth performance, rumen function and meat quality of Simmental cows.

Animal : an international journal of animal bioscience·2026
Same author

Multifunctional Primer for Dentin Bonding via Biomimetic Mineralization.

Journal of dental research·2025
Same author

[Clinical analysis of 8 cases of laparoscopic combined with colonoscopic transanal total mesorectal resection].

Zhonghua wei chang wai ke za zhi = Chinese journal of gastrointestinal surgery·2025

Area of Science:

  • Ophthalmology
  • Artificial Intelligence
  • Medical Technology

Background:

  • Photorefractive keratectomy (PRK) is a refractive surgery procedure.
  • Treatment nomograms are essential for optimizing PRK outcomes.
  • Neural networks offer advanced computational capabilities for complex data analysis.

Purpose of the Study:

  • To evaluate a commercial neural network program for calculating PRK treatment nomograms.
  • To assess the accuracy of a neural network-derived nomogram compared to a standard nomogram.
  • To determine the influence of patient demographics and clinical data on neural network predictions.

Main Methods:

  • A commercial neural network program (PRK/LASIK Brain) was trained using data from 44 patients.
  • Data included demographics, preoperative clinical data, surgical parameters, and 1-year postoperative results.

Related Experiment Videos

  • Neural network nomograms were compared to standard nomograms, and the contribution of various factors was analyzed.

    • Main Results:

    • Neural network nomograms were qualitatively similar to standard nomograms.
    • The order of data entry during training influenced the network's predictions.
    • Both outcome- and chronologically ordered nomograms diverged from the standard in individual cases, showing sensitivity to patient factors like age, sex, keratometry, and IOP.

    Conclusions:

    • Neural networks have the potential to individualize PRK treatment nomograms.
    • A dataset of 44 patients was insufficient for accurate prediction of individual treatment parameters.
    • Larger datasets or alternative learning algorithms may be necessary to enhance neural network performance in refractive surgery.