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 Acute Posterior Multifocal Placoid Pigment Epitheliopathy
Purpose:
To determine classification criteria for acute posterior multifocal placoid pigment epitheliopathy (APMPPE).
Design:
Machine learning of cases with APMPPE 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 82 cases of APMPPE, were evaluated by machine learning. Key criteria for APMPPE included (1) choroidal lesions with a plaque-like or placoid appearance and (2) characteristic imaging on fluorescein angiography (lesions "block early and stain late diffusely"). Overall accuracy for posterior uveitides was 92.7% in the training set and 98.0% (95% confidence interval 94.3, 99.3) in the validation set. The misclassification rates for APMPPE were 5% in the training set and 0% in the validation set.
Conclusions:
The criteria for APMPPE had a low misclassification rate and seemed to perform sufficiently well for use in clinical and translational research.
Insights
This study developed machine learning criteria to accurately classify acute posterior multifocal placoid pigment epitheliopathy (APMPPE) and other posterior uveitides. The new criteria demonstrated high accuracy and low misclassification rates in validation, aiding clinical research.
Area of Science:
- Ophthalmology
- Medical Informatics
- Machine Learning
Background:
- Acute posterior multifocal placoid pigment epitheliopathy (APMPPE) is a rare inflammatory eye condition.
- Accurate classification of APMPPE is crucial for diagnosis and treatment.
- Distinguishing APMPPE from other posterior uveitides can be challenging.
Purpose of the Study:
- To establish reliable classification criteria for APMPPE using machine learning.
- To differentiate APMPPE from eight other posterior uveitis conditions.
Main Methods:
- A large dataset of posterior uveitis cases was compiled and validated.
- Machine learning (multinomial logistic regression) was employed on a training set to identify key diagnostic criteria.
- The derived criteria were tested on a separate validation set.
Main Results:
- Machine learning analysis of 1,068 cases, including 82 APMPPE cases, identified key criteria: placoid choroidal lesions and specific fluorescein angiography patterns.
- The classification model achieved 92.7% accuracy on the training set and 98.0% on the validation set.
- APMPPE misclassification rates were 5% (training) and 0% (validation).
Conclusions:
- The developed criteria for APMPPE are accurate and have a low misclassification rate.
- These criteria show promise for application in clinical practice and translational research.
- The study highlights the utility of machine learning in defining ophthalmic disease classifications.
