Related Experiment Video
Updated: Nov 9, 2025
Primed Mycobacterial Uveitis PMU as a Model for Post-Infectious Uveitis
Published on: December 17, 2021
Classification Criteria for Multifocal Choroiditis With Panuveitis
Purpose:
To determine classification criteria for multifocal choroiditis with panuveitis (MFCPU).
Design:
Machine learning of cases with MFCPU and 8 other posterior uveitides.
Methods:
Cases of posterior uveitides were collected in an informatics-designed preliminary database, and a final database was constructed of cases achieving supermajority agreement on diagnosis, using formal consensus techniques. Cases were split into a training set and a validation set. Machine learning using multinomial logistic regression was used on the training set to determine a parsimonious set of criteria that minimized the misclassification rate among the posterior uveitides. The resulting criteria were evaluated on the validation set.
Results:
One thousand sixty-eight cases of posterior uveitides, including 138 cases of MFCPU, were evaluated by machine learning. Key criteria for MFCPU included (1) multifocal choroiditis with the predominant lesions size >125 µm in diameter; (2) lesions outside the posterior pole (with or without posterior involvement); and either (3) punched-out atrophic chorioretinal scars or (4) more than minimal mild anterior chamber and/or vitreous inflammation. Overall accuracy for posterior uveitides was 93.9% in the training set and 98.0% (95% confidence interval 94.3, 99.3) in the validation set. The misclassification rates for MFCPU were 15% in the training set and 0% in the validation set.
Conclusions:
The criteria for MFCPU had a reasonably low misclassification rate and seemed to perform sufficiently well for use in clinical and translational research.
Insights
New criteria for multifocal choroiditis with panuveitis (MFCPU) were developed using machine learning. These classification criteria demonstrated a low misclassification rate, proving effective for clinical research.
Area of Science:
- Ophthalmology
- Medical Informatics
- Machine Learning
Background:
- Multifocal choroiditis with panuveitis (MFCPU) requires precise classification criteria.
- Accurate diagnosis is crucial for effective clinical and translational research in uveitis.
Purpose of the Study:
- To establish reliable classification criteria for multifocal choroiditis with panuveitis (MFCPU).
Main Methods:
- Machine learning, specifically multinomial logistic regression, was employed.
- A database of 1,068 posterior uveitis cases, including 138 MFCPU cases, was utilized.
- The dataset was divided into training and validation sets to refine and test the criteria.
Main Results:
- Key MFCPU criteria identified: lesion size >125 µm, extra-posterior pole involvement, and either atrophic scars or mild inflammation.
- High overall accuracy achieved: 93.9% in training and 98.0% in validation sets.
- MFCPU misclassification rates were 15% (training) and 0% (validation).
Conclusions:
- The developed criteria for MFCPU exhibit a low misclassification rate.
- These criteria are suitable for application in clinical and translational research settings.
