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

Pulmonary Tuberculosis III01:31

Pulmonary Tuberculosis III

291
Tuberculosis (TB) is a contagious infection primarily affecting the lung parenchyma but which can also affect other body parts. TB can be classified based on disease development, presentation, and the affected anatomical site.
The first classification is based on the development of the disease, and it includes the following categories:
291

You might also read

Related Articles

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

Sort by
Same author

Genetics and Screening in Prostate Cancer.

The Surgical clinics of North America·2026
Same author

Community perspectives on awareness, care-seeking, and implementation of a corneal ulcer prevention program in Nepal: a mixed-methods study.

Global health action·2026
Same author

Acanthamoeba Keratitis: Recent Advances in Diagnosis and Management.

Cornea·2026
Same author

Diagnostic Accuracy of a Retinal Birefringence Scanning Device Compared With a Traditional Autorefraction Device.

JAMA ophthalmology·2026
Same author

Correlates of trachoma persistence and recrudescence: A global analysis of 33 countries.

International journal of infectious diseases : IJID : official publication of the International Society for Infectious Diseases·2026
Same author

De-Escalated Adjuvant Radiation Therapy in Patients With HPV-Positive Oropharyngeal Cancer.

JAMA network open·2026

Related Experiment Video

Updated: May 26, 2025

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

6.9K

Identifying Borderline Trachoma Grades Using a Three-Latent Class Model.

Vinayak Prathikanti1, Renee Casentini1, Jonathan Hwang1

  • 1F. I. Proctor Foundation, Department of Ophthalmology, University of California, San Francisco, California.

The American Journal of Tropical Medicine and Hygiene
|February 25, 2025
PubMed
Summary
This summary is machine-generated.

Latent Class Analysis identified borderline trachoma cases, improving grading accuracy. This method enhances grader training and aids AI model development for trachoma assessment.

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

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

Published on: October 27, 2023

1.3K
Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.4K

Related Experiment Videos

Last Updated: May 26, 2025

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

6.9K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

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

Published on: October 27, 2023

1.3K
Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.4K

Area of Science:

  • Ophthalmology
  • Public Health
  • Biostatistics

Background:

  • The World Health Organization (WHO) utilizes a simplified grading system for trachoma assessment.
  • Accurate trachoma grading is challenging, even for experienced graders, due to ambiguous cases.
  • A definitive gold standard for trachoma grading is currently lacking.

Purpose of the Study:

  • To apply Latent Class Analysis (LCA) to identify and characterize borderline cases in trachoma grading.
  • To evaluate the impact of identifying a "borderline" class on inter-grader agreement.
  • To explore the utility of LCA as a probabilistic gold standard for trachoma assessment.

Main Methods:

  • Latent Class Analysis (LCA) was performed on 200 graded photos of the superior tarsal conjunctiva.
  • Ten trained graders assessed for trachomatous inflammation-follicular (TF) and trachomatous inflammation-intense (TI).
  • LCA models were compared with two classes (presence/absence) and three classes (including a borderline class). Cohen's kappa (κ) assessed inter-grader agreement.

Main Results:

  • A three-class LCA model, incorporating a "borderline" class, significantly improved inter-grader agreement for both TF (κ increase of 0.10) and TI (κ increase of 0.13).
  • The third latent class was identified as representing discrepant or borderline grading cases.
  • The inclusion of the borderline class enhanced the reliability of trachoma grading.

Conclusions:

  • A three-class LCA effectively identifies borderline cases in trachoma grading, enhancing diagnostic precision.
  • This approach can inform the development of more balanced grader certification examinations.
  • Multiclass LCA offers a potential probabilistic gold standard for training and evaluating AI models in ophthalmology.