Objective: Diabetic retinopathy (DR) is a top leading cause of blindness worldwide, requiring early detection for timely intervention. Artificial intelligence (AI) has emerged as a promising tool to improve DR screening efficiency, accessibility, and cost-effectiveness. This study conducted a systematic review of literature and meta-analysis on the economic outcomes of AI-based DR screening. Methods: A systematic review of studies published before September 2024 was conducted throughout PubMed, Scopus, Embase, the Cochrane Library, the National Health Service Economic Evaluation Database, and the Cost-Effectiveness Analysis Registry. Eligible studies were included if they were (1) conducted among type 1 diabetes mellitus or type 2 diabetes mellitus  adult diabetic population; (2) studies compared AI-based DR screening strategy to non-AI screening; and (3) performed a cost-effectiveness analysis. Meta-analysis was applied to pool incremental net benefit (INB) across studies stratified by country income and study perspective using a random-effects model. Statistical heterogeneity among studies was assessed using the I2 statistic, Cochrane Q statistics, and meta regression. Results: Nine studies were included in the analysis. From a healthcare system/payer perspective, AI-based DR screening was significantly cost-effective compared to non-AI-based screening, with a pooled INB of 615.77 (95% confidence interval [CI]: 558.27-673.27). Subgroup analysis showed robust cost-effectiveness of AI-based DR screening in high-income countries (INB = 613.62, 95% CI: 556.06-671.18) and upper-/lower- middle income countries (INB = 1,739.97, 95% CI: 423.13-3,056.82) with low heterogeneity. From a societal perspective, AI-based DR screening was generally cost-effective (INB= 5,102.33, 95% CI: -815.47-11,020.13), though the result lacked statistical significance and showed high heterogeneity. Conclusions: AI-based DR screening is generally cost-effective from a healthcare system perspective, particularly in high-income countries. Heterogeneity in cost-effectiveness across different perspectives highlights the importance of context-specific evaluations, to accurately evaluate the potential of AI-based DR screening in reducing global healthcare disparities.

Objective: Diabetic retinopathy (DR) is a top leading cause of blindness worldwide, requiring early detection for timely intervention. Artificial intelligence (AI) has emerged as a promising tool to improve DR screening efficiency, accessibility, and cost-effectiveness. This study conducted a systematic review of literature and meta-analysis on the economic outcomes of AI-based DR screening. Methods: A systematic review of studies published before September 2024 was conducted throughout PubMed, Scopus, Embase, the Cochrane Library, the National Health Service Economic Evaluation Database, and the Cost-Effectiveness Analysis Registry. Eligible studies were included if they were (1) conducted among type 1 diabetes mellitus or type 2 diabetes mellitus  adult diabetic population; (2) studies compared AI-based DR screening strategy to non-AI screening; and (3) performed a cost-effectiveness analysis. Meta-analysis was applied to pool incremental net benefit (INB) across studies stratified by country income and study perspective using a random-effects model. Statistical heterogeneity among studies was assessed using the I2 statistic, Cochrane Q statistics, and meta regression. Results: Nine studies were included in the analysis. From a healthcare system/payer perspective, AI-based DR screening was significantly cost-effective compared to non-AI-based screening, with a pooled INB of 615.77 (95% confidence interval [CI]: 558.27-673.27). Subgroup analysis showed robust cost-effectiveness of AI-based DR screening in high-income countries (INB = 613.62, 95% CI: 556.06-671.18) and upper-/lower- middle income countries (INB = 1,739.97, 95% CI: 423.13-3,056.82) with low heterogeneity. From a societal perspective, AI-based DR screening was generally cost-effective (INB= 5,102.33, 95% CI: -815.47-11,020.13), though the result lacked statistical significance and showed high heterogeneity. Conclusions: AI-based DR screening is generally cost-effective from a healthcare system perspective, particularly in high-income countries. Heterogeneity in cost-effectiveness across different perspectives highlights the importance of context-specific evaluations, to accurately evaluate the potential of AI-based DR screening in reducing global healthcare disparities.

Background: Diabetic retinopathy (DR) screening using artificial intelligence (AI) has evolved significantly over the past decade. This study aimed to analyze research trends, developments, and patterns in AI-based fundus image DR screening from 2014 to 2024 through bibliometric analysis.Methods: The study used CiteSpace and Microsoft Excel to analyze 1,172 publications from the Web of Science Core Collection database. The analysis included publication trends over time, citation patterns, institutional collaborations, and the emergence of keywords. Results: From 2014-2022, there was a steady increase in the number of publications, reaching a peak in 2021. India (26%), China (20.05%), and the USA (9.98%) were the major contributors to research output in this field. Among the publication venues, IEEE ACCESS stood out as the leading one, with 44 articles published. The research landscape has evolved from traditional image processing techniques to deep learning approaches. In recent years, there has been a growing emphasis on multimodal AI models. The analysis identified three distinct phases in the development of AI-based DR screening: CNN-based systems (2014-2020), Vision Transformers and innovative learning paradigms (2020-2022), and large foundation models (2022-2024). Conclusions: The field has demonstrated a mature development in traditional AI approaches and is currently in the process of transitioning toward multimodal learning technologies. Future directions suggest an increased focus on the integration of telemedicine, innovative AI algorithms, and real-world implementation of these technologies in real-world settings.

Background: Diabetic retinopathy (DR) screening using artificial intelligence (AI) has evolved significantly over the past decade. This study aimed to analyze research trends, developments, and patterns in AI-based fundus image DR screening from 2014 to 2024 through bibliometric analysis. Methods: The study used CiteSpace and Microsoft Excel to analyze 1,172 publications from the Web of Science Core Collection database. The analysis included publication trends over time, citation patterns, institutional collaborations, and the emergence of keywords. Results: From 2014-2022, there was a steady increase in the number of publications, reaching a peak in 2021. India (26%), China (20.05%), and the USA (9.98%) were the major contributors to research output in this field. Among the publication venues, IEEE ACCESS stood out as the leading one, with 44 articles published. The research landscape has evolved from traditional image processing techniques to deep learning approaches. In recent years, there has been a growing emphasis on multimodal AI models. The analysis identified three distinct phases in the development of AI-based DR screening: CNN-based systems (2014-2020), Vision Transformers and innovative learning paradigms (2020-2022), and large foundation models (2022-2024). Conclusions: The field has demonstrated a mature development in traditional AI approaches and is currently in the process of transitioning toward multimodal learning technologies. Future directions suggest an increased focus on the integration of telemedicine, innovative AI algorithms, and real-world implementation of these technologies in real-world settings.

Background: Diabetic retinopathy (DR) urgently needs novel and effective therapeutic targets. Integrated analyses of plasma proteomic and genetic markers can clarify the causal relevance of proteins and discover novel targets for diseases, but no systematic screening for DR has been performed.

Methods: Summary statistics of plasma protein quantitative trait loci (pQTL) were derived from two extensive genome-wide analysis study (GWAS) datasets and one systematic review, with over 100 thousand participants covering thousands of plasma proteins. DR data were sourced from the largest FinnGen study, comprising 10,413 DR cases and 308,633 European controls. Genetic instrumental variables were identified using multiple filters. In the two-sample MR analysis, Wald ratio and inverse variance-weighted (IVW) MR were utilized to investigate the

causality of plasma proteins with DR. Bidirectional MR, Bayesian Co-localization, and phenotype scanning were employed to test for potential reverse causality and confounding factors in the main MR analyses. By systemically searching druggable gene lists, the ChEMBL database, DrugBank, and Gene Ontology database, the druggability and relevant functional pathways of the identified proteins were systematically evaluated.

Results: Genetically predicted levels of 24 proteins were significantly associated with DR risk at a false discovery rate <0.05 including 11 with positive associations and 13 with negative associations. For each standard deviation increase in plasm protein levels, the odds ratios (ORs) for DR varied from 0.51 (95% CI: 0.36-0.73; P=2.22×10-5) for tubulin polymerization-promoting protein family member 3 (TPPP3) to 2.02 (95% CI: 1.44-2.83; P=5.01×10-5) for olfactomedin like 3 (OLFML3). Bidirectional MR indicated there was no reverse causality that interfered with the results of the main MR analyses. Four proteins exhibited strong co-localization evidence (PH4 ≥0.8): cytoplasmic tRNA synthetase (WARS), acrosin binding protein(ACRBP), and intercellular adhesion molecule 1 (ICAM1) were negatively associated with DR risk, while neurogenic locus notch homolog protein 2 (NOTCH2) showed a positive association. No confounding factors were detected between pQTLs and DR according to the phenotypic scan. Drugability assessments highlighted 6 proteins already in drug development endeavor and 18 novel drug targets, with metalloproteinase inhibitor 3 (TIMP) currently in phase I clinical trials for DR. GO analysis identified 18 of 24 plasma proteins enriching 22 pathways related to cell differentiation and proliferation regulation.

Conclusions:Twenty-four promising drug targets for DR were identified, including four plasma proteins with particular co-localization evidence. These findings offer new insights into DR's etiology and therapeutic targeting, exemplifying the value of genomic and proteomic data in drug target discovery.

Background: Diabetic retinopathy (DR) urgently needs novel and effective therapeutic targets. Integrated analyses of plasma proteomic and genetic markers can clarify the causal relevance of proteins and discover novel targets for diseases, but no systematic screening for DR has been performed.

Methods: Summary statistics of plasma protein quantitative trait loci (pQTL) were derived from two extensive genome-wide analysis study (GWAS) datasets and one systematic review, with over 100 thousand participants covering thousands of plasma proteins. DR data were sourced from the largest FinnGen study, comprising 10,413 DR cases and 308,633 European controls. Genetic instrumental variables were identified using multiple filters. In the two-sample MR analysis, Wald ratio and inverse variance-weighted (IVW) MR were utilized to investigate the

causality of plasma proteins with DR. Bidirectional MR, Bayesian Co-localization, and phenotype scanning were employed to test for potential reverse causality and confounding factors in the main MR analyses. By systemically searching druggable gene lists, the ChEMBL database, DrugBank, and Gene Ontology database, the druggability and relevant functional pathways of the identified proteins were systematically evaluated.

Results: Genetically predicted levels of 24 proteins were significantly associated with DR risk at a false discovery rate <0.05 including 11 with positive associations and 13 with negative associations. For each standard deviation increase in plasm protein levels, the odds ratios (ORs) for DR varied from 0.51 (95% CI: 0.36-0.73; P=2.22×10-5) for tubulin polymerization-promoting protein family member 3 (TPPP3) to 2.02 (95% CI: 1.44-2.83; P=5.01×10-5) for olfactomedin like 3 (OLFML3). Bidirectional MR indicated there was no reverse causality that interfered with the results of the main MR analyses. Four proteins exhibited strong co-localization evidence (PH4 ≥0.8): cytoplasmic tRNA synthetase (WARS), acrosin binding protein(ACRBP), and intercellular adhesion molecule 1 (ICAM1) were negatively associated with DR risk, while neurogenic locus notch homolog protein 2 (NOTCH2) showed a positive association. No confounding factors were detected between pQTLs and DR according to the phenotypic scan. Drugability assessments highlighted 6 proteins already in drug development endeavor and 18 novel drug targets, with metalloproteinase inhibitor 3 (TIMP) currently in phase I clinical trials for DR. GO analysis identified 18 of 24 plasma proteins enriching 22 pathways related to cell differentiation and proliferation regulation.

Conclusions:Twenty-four promising drug targets for DR were identified, including four plasma proteins with particular co-localization evidence. These findings offer new insights into DR's etiology and therapeutic targeting, exemplifying the value of genomic and proteomic data in drug target discovery.