Artificial intelligence versus manual screening for the detection of diabetic retinopathy: a comparative systematic review and meta-analysis

BackgroundDiabetic retinopathy is one of the leading causes of blindness globally, among individuals with diabetes mellitus. Early detection through screening can help in preventing disease progression. In recent advancements artificial Intelligence assisted screening has emerged as an alternative t...

Full description

Saved in:
Bibliographic Details
Main Authors: Hasan Nawaz Tahir, Naseer Ullah, Mursala Tahir, Inbaraj Susai Domnic, Ramaprabha Prabhakar, Semmal Syed Meerasa, Ahmed Ibrahim AbdElneam, Shahnawaz Tahir, Yousaf Ali
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1519768/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850191436760219648
author Hasan Nawaz Tahir
Naseer Ullah
Mursala Tahir
Inbaraj Susai Domnic
Ramaprabha Prabhakar
Semmal Syed Meerasa
Ahmed Ibrahim AbdElneam
Ahmed Ibrahim AbdElneam
Shahnawaz Tahir
Yousaf Ali
author_facet Hasan Nawaz Tahir
Naseer Ullah
Mursala Tahir
Inbaraj Susai Domnic
Ramaprabha Prabhakar
Semmal Syed Meerasa
Ahmed Ibrahim AbdElneam
Ahmed Ibrahim AbdElneam
Shahnawaz Tahir
Yousaf Ali
author_sort Hasan Nawaz Tahir
collection DOAJ
description BackgroundDiabetic retinopathy is one of the leading causes of blindness globally, among individuals with diabetes mellitus. Early detection through screening can help in preventing disease progression. In recent advancements artificial Intelligence assisted screening has emerged as an alternative to traditional manual screening methods. This diagnostic test accuracy (DTA) review aims to compare the sensitivity and specificity of AI versus manual screening for detecting diabetic retinopathy, focusing on both dilated and un-dilated eyes.MethodsA systematic review and meta-analysis were conducted for comparison of AI vs. manual screening of diabetic retinopathy using 25 observational (cross sectional, validation and cohort) studies with total images of 613,690 used for screening published between January 2015 and December 2024. Outcomes of the study was sensitivity, and specificity. Risk of bias was assessed using the QUADAS-2 tool for validation studies, the AXIS tool for cross-sectional studies, and the Newcastle-Ottawa Scale for cohort studies.ResultsThe results of this meta-analysis showed that for un-dilated eyes, AI screening showed pooled sensitivity of 0.90 [95% CI: 0.85–0.94] and pooled specificity of 0.94 [95% CI: 0.91–0.96] while manual screening shows pooled sensitivity of 0.79 [95% CI: 0.60–0.91] and pooled specificity of 0.99 [95% CI: 0.98–0.99]. For dilated eyes the pooled sensitivity of AI screening is 0.95 [95% CI: 0.91–0.97] and pooled specificity is 0.87 [95% CI: 0.79–0.92], while manual screening sensitivity is 0.90 [95% CI: 0.87–0.92] and specificity is 0.99 [95% CI: 0.99–1.00]. These data show comparable sensitivities and specificities of AI and manual screening, with AI performing better in sensitivity.ConclusionAI-assisted screening for diabetic retinopathy shows comparable sensitivity and specificity compared to manual screening. These results suggest that AI can be a reliable alternative in clinical settings, with increased early detection rates and reducing the burden on ophthalmologists. Further research is needed to validate these findings.Systematic review registrationhttps://www.crd.york.ac.uk/PROSPERO/home, CRD42024596611.
format Article
id doaj-art-9f00ffdb3e9d4bdca49241778031dd65
institution OA Journals
issn 2296-858X
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-9f00ffdb3e9d4bdca49241778031dd652025-08-20T02:14:54ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-05-011210.3389/fmed.2025.15197681519768Artificial intelligence versus manual screening for the detection of diabetic retinopathy: a comparative systematic review and meta-analysisHasan Nawaz Tahir0Naseer Ullah1Mursala Tahir2Inbaraj Susai Domnic3Ramaprabha Prabhakar4Semmal Syed Meerasa5Ahmed Ibrahim AbdElneam6Ahmed Ibrahim AbdElneam7Shahnawaz Tahir8Yousaf Ali9Department of Community Medicine, College of Medicine, Dwadimi, Shaqra University, Shaqra, Saudi ArabiaDepartment of Community Medicine, Khyber Medical College Peshawar, Peshawar, PakistanDepartment of Community Medicine, Liaquat National Hospital and Medical College, Jinnah Sindh Medical University, Karachi, PakistanDepartment of Pharmacology, College of Medicine, Dwadimi, Shaqra University, Shaqra, Saudi ArabiaDepartment of Physiology, College of Medicine, Shaqra University, Shaqra, Saudi ArabiaDepartment of Physiology, College of Medicine, Shaqra University, Shaqra, Saudi ArabiaDepartments of Clinical Biochemistry and Basic Medical Sciences, College of Medicine, Dwadimi, Shaqra University, Shaqra, Saudi ArabiaMolecular Genetics and Enzymology Department, Human Genetics and Genome Research Institute, National Research Center, Dokki, Cairo, EgyptDepartment of Gastroenterology, Dow University of Health Sciences, Karachi, PakistanDepartment of Community Medicine, College of Medicine, Dwadimi, Shaqra University, Shaqra, Saudi ArabiaBackgroundDiabetic retinopathy is one of the leading causes of blindness globally, among individuals with diabetes mellitus. Early detection through screening can help in preventing disease progression. In recent advancements artificial Intelligence assisted screening has emerged as an alternative to traditional manual screening methods. This diagnostic test accuracy (DTA) review aims to compare the sensitivity and specificity of AI versus manual screening for detecting diabetic retinopathy, focusing on both dilated and un-dilated eyes.MethodsA systematic review and meta-analysis were conducted for comparison of AI vs. manual screening of diabetic retinopathy using 25 observational (cross sectional, validation and cohort) studies with total images of 613,690 used for screening published between January 2015 and December 2024. Outcomes of the study was sensitivity, and specificity. Risk of bias was assessed using the QUADAS-2 tool for validation studies, the AXIS tool for cross-sectional studies, and the Newcastle-Ottawa Scale for cohort studies.ResultsThe results of this meta-analysis showed that for un-dilated eyes, AI screening showed pooled sensitivity of 0.90 [95% CI: 0.85–0.94] and pooled specificity of 0.94 [95% CI: 0.91–0.96] while manual screening shows pooled sensitivity of 0.79 [95% CI: 0.60–0.91] and pooled specificity of 0.99 [95% CI: 0.98–0.99]. For dilated eyes the pooled sensitivity of AI screening is 0.95 [95% CI: 0.91–0.97] and pooled specificity is 0.87 [95% CI: 0.79–0.92], while manual screening sensitivity is 0.90 [95% CI: 0.87–0.92] and specificity is 0.99 [95% CI: 0.99–1.00]. These data show comparable sensitivities and specificities of AI and manual screening, with AI performing better in sensitivity.ConclusionAI-assisted screening for diabetic retinopathy shows comparable sensitivity and specificity compared to manual screening. These results suggest that AI can be a reliable alternative in clinical settings, with increased early detection rates and reducing the burden on ophthalmologists. Further research is needed to validate these findings.Systematic review registrationhttps://www.crd.york.ac.uk/PROSPERO/home, CRD42024596611.https://www.frontiersin.org/articles/10.3389/fmed.2025.1519768/fulldiabetic retinopathyscreeningartificial intelligencedeep learningmanual screeningautomated detection
spellingShingle Hasan Nawaz Tahir
Naseer Ullah
Mursala Tahir
Inbaraj Susai Domnic
Ramaprabha Prabhakar
Semmal Syed Meerasa
Ahmed Ibrahim AbdElneam
Ahmed Ibrahim AbdElneam
Shahnawaz Tahir
Yousaf Ali
Artificial intelligence versus manual screening for the detection of diabetic retinopathy: a comparative systematic review and meta-analysis
Frontiers in Medicine
diabetic retinopathy
screening
artificial intelligence
deep learning
manual screening
automated detection
title Artificial intelligence versus manual screening for the detection of diabetic retinopathy: a comparative systematic review and meta-analysis
title_full Artificial intelligence versus manual screening for the detection of diabetic retinopathy: a comparative systematic review and meta-analysis
title_fullStr Artificial intelligence versus manual screening for the detection of diabetic retinopathy: a comparative systematic review and meta-analysis
title_full_unstemmed Artificial intelligence versus manual screening for the detection of diabetic retinopathy: a comparative systematic review and meta-analysis
title_short Artificial intelligence versus manual screening for the detection of diabetic retinopathy: a comparative systematic review and meta-analysis
title_sort artificial intelligence versus manual screening for the detection of diabetic retinopathy a comparative systematic review and meta analysis
topic diabetic retinopathy
screening
artificial intelligence
deep learning
manual screening
automated detection
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1519768/full
work_keys_str_mv AT hasannawaztahir artificialintelligenceversusmanualscreeningforthedetectionofdiabeticretinopathyacomparativesystematicreviewandmetaanalysis
AT naseerullah artificialintelligenceversusmanualscreeningforthedetectionofdiabeticretinopathyacomparativesystematicreviewandmetaanalysis
AT mursalatahir artificialintelligenceversusmanualscreeningforthedetectionofdiabeticretinopathyacomparativesystematicreviewandmetaanalysis
AT inbarajsusaidomnic artificialintelligenceversusmanualscreeningforthedetectionofdiabeticretinopathyacomparativesystematicreviewandmetaanalysis
AT ramaprabhaprabhakar artificialintelligenceversusmanualscreeningforthedetectionofdiabeticretinopathyacomparativesystematicreviewandmetaanalysis
AT semmalsyedmeerasa artificialintelligenceversusmanualscreeningforthedetectionofdiabeticretinopathyacomparativesystematicreviewandmetaanalysis
AT ahmedibrahimabdelneam artificialintelligenceversusmanualscreeningforthedetectionofdiabeticretinopathyacomparativesystematicreviewandmetaanalysis
AT ahmedibrahimabdelneam artificialintelligenceversusmanualscreeningforthedetectionofdiabeticretinopathyacomparativesystematicreviewandmetaanalysis
AT shahnawaztahir artificialintelligenceversusmanualscreeningforthedetectionofdiabeticretinopathyacomparativesystematicreviewandmetaanalysis
AT yousafali artificialintelligenceversusmanualscreeningforthedetectionofdiabeticretinopathyacomparativesystematicreviewandmetaanalysis