Javascript must be enabled to continue!
51-OR: Medios—A Smartphone-Based Artificial Intelligence Algorithm in Screening for Diabetic Retinopathy
View through CrossRef
Background: Pupil dilatation, access to ophthalmologists, size and cost of fundus cameras, and network connectivity issues are barriers to diabetic retinopathy (DR) screening in primary care. This makes artificial intelligence a potential alternative in DR screening. This study aims to evaluate the performance of an offline AI algorithm - Medios in DR Screening using non mydriatic retinal images taken from the smartphone based Remidio Fundus on Phone (NM-FOP) retinal camera.
Methods: Non mydriatic retinal images from 900 patients with diabetes were captured prospectively with the Remidio NM FOP camera at Diacon Hospital, Bangalore, India. The images were graded by 5 ophthalmologists as per the International Diabetic Retinopathy Classification System and the majority diagnosis was considered as the ground truth. Two images [posterior pole (macula centered), nasal field] were captured per eye for each patient, and were analyzed offline on-device using the Medios AI. The diagnosis of Medios AI was compared to that of the ophthalmologist.
Results: DR was present in 252 patients. Performance of the AI for referable DR (Moderate NPDR or worse, or presence of DME) was - Sensitivity 93% (95% CI 91.3%-94.7%), Specificity: 92.5% (95% CI 90.8%-94.2%). Performance of the AI for all DR (Mild NPDR or worse, or presence of DME) was - Sensitivity: 83.3% (95% CI 80.9%-85.7%), Specificity: 95.5% (95% CI 94.1%-96.8%). Sensitivity for sight threatening DR (STDR) [severe NPDR, proliferative DR (PDR) or presence of DME] was 95.2% (95% CI 88.2%-98.6%). The 3 PDRs missed by the AI were post laser with no active changes visible. This is a common exclusion criteria in other studies, and when excluded, the sensitivity for STDR was found to be 98.7%.
Conclusion: This is one of the largest studies evaluating the performance of AI using non mydriatic retinal images offline. The Medios AI algorithm’s sensitivity and specificity exceeds the FDA mandated superiority end point and can be used for DR screening.
Disclosure
B. Sosale: None. A.R. Sosale: None. H. Murthy: None. S. Narayana: None. U. Sharma: None. S.G.V. Gowda: None. M. Naveenam: None.
American Diabetes Association
Title: 51-OR: Medios—A Smartphone-Based Artificial Intelligence Algorithm in Screening for Diabetic Retinopathy
Description:
Background: Pupil dilatation, access to ophthalmologists, size and cost of fundus cameras, and network connectivity issues are barriers to diabetic retinopathy (DR) screening in primary care.
This makes artificial intelligence a potential alternative in DR screening.
This study aims to evaluate the performance of an offline AI algorithm - Medios in DR Screening using non mydriatic retinal images taken from the smartphone based Remidio Fundus on Phone (NM-FOP) retinal camera.
Methods: Non mydriatic retinal images from 900 patients with diabetes were captured prospectively with the Remidio NM FOP camera at Diacon Hospital, Bangalore, India.
The images were graded by 5 ophthalmologists as per the International Diabetic Retinopathy Classification System and the majority diagnosis was considered as the ground truth.
Two images [posterior pole (macula centered), nasal field] were captured per eye for each patient, and were analyzed offline on-device using the Medios AI.
The diagnosis of Medios AI was compared to that of the ophthalmologist.
Results: DR was present in 252 patients.
Performance of the AI for referable DR (Moderate NPDR or worse, or presence of DME) was - Sensitivity 93% (95% CI 91.
3%-94.
7%), Specificity: 92.
5% (95% CI 90.
8%-94.
2%).
Performance of the AI for all DR (Mild NPDR or worse, or presence of DME) was - Sensitivity: 83.
3% (95% CI 80.
9%-85.
7%), Specificity: 95.
5% (95% CI 94.
1%-96.
8%).
Sensitivity for sight threatening DR (STDR) [severe NPDR, proliferative DR (PDR) or presence of DME] was 95.
2% (95% CI 88.
2%-98.
6%).
The 3 PDRs missed by the AI were post laser with no active changes visible.
This is a common exclusion criteria in other studies, and when excluded, the sensitivity for STDR was found to be 98.
7%.
Conclusion: This is one of the largest studies evaluating the performance of AI using non mydriatic retinal images offline.
The Medios AI algorithm’s sensitivity and specificity exceeds the FDA mandated superiority end point and can be used for DR screening.
Disclosure
B.
Sosale: None.
A.
R.
Sosale: None.
H.
Murthy: None.
S.
Narayana: None.
U.
Sharma: None.
S.
G.
V.
Gowda: None.
M.
Naveenam: None.
Related Results
Familial clustering of diabetic retinopathy in South Indian Type 2 diabetic patients
Familial clustering of diabetic retinopathy in South Indian Type 2 diabetic patients
AbstractAim The aim of the study was to determine whether there is familialclustering of diabetic retinopathy among South Indian Type 2 diabeticsubjects.Methods During the period S...
Diabetic Retinopathy-A Review
Diabetic Retinopathy-A Review
:
Diabetic Retinopathy is a vascular microvascular disease also called diabetic eye disease
caused by microangiopathy leading to progressive damage of the retina and blindness. The...
Association of HbA1c with Diabetic Retinopathy in Diabetic Patients
Association of HbA1c with Diabetic Retinopathy in Diabetic Patients
Background: Retinopathy due to diabetes is increasing in patients due to increase prevalence of diabetes.
Objective : We tried to find if there is any association of HbA1c with Dia...
Karakteristik pasien diabetic retinopathy dengan dislipidemia di RSUP Sanglah Denpasar
Karakteristik pasien diabetic retinopathy dengan dislipidemia di RSUP Sanglah Denpasar
Introduction: Diabetic retinopathy is diabetes mellitus complication which progressively causes microvascular changes in the retina, causing physical and psychosocial impact. Accor...
Gender Specific Distribution Of different patterns of Diabetic Retinopathy In Patients With Type 2 Diabetes Mellitus. A Cross-Sectional Study From a tertiary care specialized center in Lahore, Pakistan
Gender Specific Distribution Of different patterns of Diabetic Retinopathy In Patients With Type 2 Diabetes Mellitus. A Cross-Sectional Study From a tertiary care specialized center in Lahore, Pakistan
BACKGROUND:The patients of diabetic retinopathy are not aware of early retinal vascular dysfunction, which is a feature of diabetic retinopathy.
AIM:This study aimed to detec...
Awareness of diabetic retinopathy among diabetic patients
Awareness of diabetic retinopathy among diabetic patients
Abstract
Objectives: To assess the awareness of diabetic patients about diabetic retinopathy.
Method: The cross-sectional study was conducted at the Ophthalmology Department, Fauji...
Hba1c Levels an Indicator of Glycemic Control in Diabetics With and Without Retinopathy
Hba1c Levels an Indicator of Glycemic Control in Diabetics With and Without Retinopathy
Introduction: Diabetic retinopathy is a main cause of vision impairment and blindness due to uncontrolled diabetes. In Pakistan uncontrolled iabetes is on rise and one of the leadi...
Association of Serum Magnesium Levels with Diabetic Retinopathy in Patients with Type 2 Diabetes Mellitus: A Cross-Sectional Study
Association of Serum Magnesium Levels with Diabetic Retinopathy in Patients with Type 2 Diabetes Mellitus: A Cross-Sectional Study
Background: Diabetic retinopathy is a common microvascular complication of type 2 diabetes mellitus (T2DM). Magnesium is important for insulin action, glucose metabolism, and vascu...

