Related Experiment Video
Updated: May 10, 2026

Using Retinal Imaging to Study Dementia
Published on: November 6, 2017
Rate and Predictors of Misclassification of Active Diabetic Macular Edema as Detected by an Automated Retinal Image
Lamberto La Franca1, Carola Rutigliani2, Lisa Checchin1
1Department of Ophthalmology, IRCCS San Raffaele Scientific Institute, IRCCS Ospedale San Raffaele, University Vita-Salute, Via Olgettina 60, 20132, Milan, Italy.
Introduction:
The aim of this work is to estimate the sensitivity, specificity, and misclassification rate of an automated retinal image analysis system (ARIAS) in diagnosing active diabetic macular edema (DME) and to identify factors associated with true and false positives.
Methods:
We conducted a cross-sectional study of prospectively enrolled patients with diabetes mellitus (DM) referred to a tertiary medical retina center for screening or management of DME. All patients underwent two-field fundus photography (macula- and disc-centered) with a true-color confocal camera; images were processed by EyeArt V.2.1.0 (Woodland Hills, CA, USA). Active DME was defined as the presence of intraretinal or subretinal fluid on spectral-domain optical coherence tomography (SD-OCT). Sensitivity and specificity and their 95% confidence intervals (CIs) were calculated. Variables associated with true (i.e., DME labeled as present by ARIAS + fluid on SD-OCT) and false positives (i.e., DME labeled as present by ARIAS + no fluid on SD-OCT) of active DME were explored.
Results:
A total of 298 eyes were included; 92 eyes (31%) had active DME. ARIAS sensitivity and specificity were 82.61% (95% CI 72.37-89.60) and 84.47% (95% CI 78.34-89.10). The misclassification rate was 16%. Factors associated with true positives included younger age (p = 0.01), shorter DM duration (p = 0.006), presence of hard exudates (p = 0.005), and microaneurysms (p = 0.002). Factors associated with false positives included longer DM duration (p = 0.01), worse diabetic retinopathy severity (p = 0.008), history of inactivated DME (p < 0.001), and presence of hard exudates (p < 0.001), microaneurysms (p < 0.001), or epiretinal membrane (p = 0.06).
Conclusions:
The sensitivity of ARIAS was diminished in older patients and those without DME-related fundus lesions, while the specificity was reduced in cases with a history of inactivated DME. ARIAS performed well in screening for naïve DME but is not effective in surveillance inactivated DME.
Insights
This study evaluated the automated retinal image analysis system (ARIAS) for diagnosing diabetic macular edema (DME), finding it effective for screening new cases but less reliable for monitoring inactive DME.
Area of Science:
- Ophthalmology
- Medical Imaging
- Artificial Intelligence in Healthcare
Background:
- Diabetic macular edema (DME) is a leading cause of vision loss in diabetic patients.
- Accurate and timely diagnosis of active DME is crucial for effective treatment and vision preservation.
- Automated retinal image analysis systems (ARIAS) offer potential for efficient screening and diagnosis.
Purpose of the Study:
- To assess the sensitivity, specificity, and misclassification rate of ARIAS in detecting active DME.
- To identify clinical and imaging factors associated with true and false positive diagnoses by ARIAS.
Main Methods:
- A cross-sectional study involving 298 eyes of diabetic patients referred for DME evaluation.
- Fundus photography analyzed by ARIAS (EyeArt V.2.1.0).
- Active DME defined by spectral-domain optical coherence tomography (SD-OCT).
Main Results:
- ARIAS demonstrated a sensitivity of 82.61% and specificity of 84.47% for active DME.
- The overall misclassification rate was 16%.
- Factors like younger age and shorter diabetes duration were linked to true positives, while longer diabetes duration and history of inactivated DME were associated with false positives.
Conclusions:
- ARIAS is effective for screening treatment-naïve DME but less suitable for monitoring inactive DME.
- Sensitivity was lower in older patients and those lacking DME-related fundus lesions.
- Specificity decreased in patients with a history of inactivated DME.
More Related Videos
Related Concept Videos
Type II Diabetes Mellitus III: Clinical Manifestations and Diagnosis
Hyperglycemia
Diabetic Retinopathy
Diabetic Nephropathy

