Title of the Study:
Advancing Diabetic Retinopathy Screening: A Systematic Review of Artificial Intelligence and OCTA Innovations
Study Objectives:
1. To systematically evaluate the performance of artificial intelligence (AI) algorithms, particularly deep learning (DL) models, in analyzing OCTA images for the detection and classification of diabetic retinopathy (DR).
2. To compare the diagnostic accuracy, sensitivity, and specificity of various AI models with traditional machine learning approaches in DR screening.
3. To identify the strengths and limitations of integrating AI-driven analysis with OCTA imaging for clinical application.
4. To highlight existing challenges and propose future research directions for the clinical translation of AI-enhanced OCTA tools.
Inclusion and Exclusion Criteria:
Inclusion Criteria:
1. Original, peer-reviewed research articles written in English.
2. Studies employing AI algorithms to analyze OCTA images for retinal and choroidal microvasculature evaluation in DR patients.
3. Presence of a control group for comparative analysis.
Exclusion Criteria:
1. Non-English articles, non-original research, or non-human studies.
2. Case reports, reviews, book chapters, letters, or conference abstracts.
3. Studies lacking a control group or not utilizing OCTA imaging.
Databases and Search Strategy:
1. Databases searched: PubMed, Scopus, Embase, and Web of Science.
2. Search terms: Diabetic Retinopathy, Optical Coherence Tomography Angiography, Artificial Intelligence, Deep Learning, Machine Learning, Ophthalmology, Screening
3. Search strategy:
Pubmed: ((((((((("Neural Networks, Computer"[Mesh]) OR "Deep Learning"[Mesh]) OR "Artificial Intelligence"[Mesh]) OR ( "Machine Learning"[Mesh] OR "Unsupervised Machine Learning"[Mesh] OR "Supervised Machine Learning"[Mesh] )) OR (neural network)) OR (convolutional neural network)) OR ("Computers"[Mesh])) OR (predictive markers[Title/Abstract])) AND ((((("Retinal Diseases"[Mesh] OR "Hypertensive Retinopathy"[Mesh] OR "Diabetic Retinopathy"[Mesh]) OR ( "Diabetes Mellitus"[Mesh] OR "Diabetes, Gestational"[Mesh] OR "Diabetes Mellitus, Type 1"[Mesh] OR "Diabetes Mellitus, Type 2"[Mesh] )) OR ("Eye Diseases"[Mesh])) OR ("Eye"[Mesh])) OR ("Neovascularization, Pathologic"[Mesh]))) AND ((((((((((OCTA) OR (oct angiography)) OR (oct-angiography)) OR (Optical coherence tomography angiography)) OR (( "Angiography/classification"[Mesh] OR "Angiography/methods"[Mesh] ))) OR ("Tomography, Optical Coherence/methods"[Mesh])) OR (En Face OCT)) OR (Swept-Source OCT)) OR (OCT angiogram[Title/Abstract])) OR (angiographic OCT))
Scopus: (TITLE-ABS-KEY("Neural Networks, Computer" OR "Deep Learning" OR "Artificial Intelligence" OR "Machine Learning" OR "Unsupervised Machine Learning" OR "Supervised Machine Learning" OR "neural network" OR "convolutional neural network" OR "Computers" OR "predictive markers")) AND (TITLE-ABS-KEY("Retinal Diseases" OR "Hypertensive Retinopathy" OR "Diabetic Retinopathy" OR "Diabetes Mellitus" OR "Gestational Diabetes" OR "Type 1 Diabetes Mellitus" OR "Type 2 Diabetes Mellitus" OR "Eye Diseases" OR "Eye" OR "Pathologic Neovascularization")) AND (TITLE-ABS-KEY(OCTA OR "oct angiography" OR "oct-angiography" OR "Optical Coherence Tomography Angiography" OR "Angiography classification" OR "Angiography methods" OR "Optical Coherence Tomography methods" OR "En Face OCT" OR "Swept-Source OCT" OR "OCT angiogram" OR "angiographic OCT"))
Web Of Science: TS=( ("artificial intelligence" OR "machine learning" OR "deep learning" OR "neural network*" OR "convolutional neural network*") AND ("diabetes" OR "type 1 diabetes" OR "type 2 diabetes" OR "diabetic complication*" OR "diabetic management") AND ("optical coherence tomography angiography" OR "optical coherence tomography" OR "angiography" OR "retinal imaging"))
Embase: ('artificial intelligence'/exp OR 'machine learning'/exp OR 'deep learning'/exp OR 'neural networks'/exp OR 'convolutional neural network'/exp) AND ('diabetes'/exp OR 'type 1 diabetes'/exp OR 'type 2 diabetes'/exp OR 'diabetic complications'/exp OR 'diabetic management') AND ('optical coherence tomography angiography'/exp OR 'angiography'/exp OR 'retinal imaging'/exp)
4. No geographical or publication location restrictions will be applied.
5. Manual reference checks of included studies will be conducted to ensure no relevant studies were overlooked.
Quality Assessment Methods:
1. Adherence to the PRISMA guidelines for systematic reviews.
2. Use of validated quality appraisal tools for evaluating the methodological rigor and bias in included studies.
Data Analysis Methodology:
1. Extracted data on training datasets, imaging modalities, AI algorithms/models will be used, outcomes, and performance metrics will be compiled and analyzed.
2. Descriptive and comparative analyses will be performed to summarize findings.
3. If applicable, meta-analysis of diagnostic accuracy (sensitivity, specificity, and AUC) will be conducted using appropriate statistical software.
