Diagnostic Accuracy of Artificial Intelligence-Based Automated Diabetic Retinopathy Screening in Real-World Settings: A Systematic Review and Meta-Analysis.

PURPOSE: To evaluate the diagnostic accuracy of artificial intelligence (AI)-based automated diabetic retinopathy (DR) screening in real-world settings. DESIGN: Systematic review and meta-analysis METHODS: We conducted a systematic review of relevant literature from January 2012 to August 2022 using databases including PubMed, Scopus and Web of Science. The quality of studies was evaluated using Quality Assessment for Diagnostic Accuracy Studies 2 (QUADAS-2) checklist. We calculated pooled accuracy, sensitivity, specificity, and diagnostic odds ratio (DOR) as summary measures. The study protocol was registered with the International Prospective Register of Systematic Reviews (PROSPERO - CRD42022367034). RESULTS: We included 34 studies which utilized AI algorithms for diagnosing DR based on real-world fundus images. Quality assessment of these studies indicated a low risk of bias and low applicability concern. Among gradable images, the overall pooled accuracy, sensitivity, specificity, and DOR were 81%, 94% (95% CI: 92.0-96.0), 89% (95% CI: 85.0-92.0) and 128 (95% CI: 80-204) respectively. Sub-group analysis showed that, when acceptable quality imaging could be obtained, non-mydriatic fundus images had a better DOR of 143 (95% CI: 82-251) and studies using 2 field images had a better DOR of 161 (95% CI 74-347). Our meta-regression analysis revealed a statistically significant association between DOR and variables such as the income status, and the type of fundus camera. CONCLUSION: Our findings indicate that AI algorithms have acceptable performance in screening for DR using fundus images compared to human graders. Implementing a fundus camera with AI-based software has the potential to assist ophthalmologists in reducing their workload and improving the accuracy of DR diagnosis.

Evaluation of the agreement and reliability of Transpalpebral Tonometers compared with Goldmann Applanation Tonometer - A systematic Review and Meta-Analysis Protocol.

In 2020, the global prevalence of glaucoma was estimated to be 76 million and it was projected to increase to 111.8 million by 2040. Accurate intraocular pressure (IOP) measurement is imperative in glaucoma management since it is the only modifiable risk factor. Numerous studies have compared the reliability of IOP measured using transpalpebral tonometers and Goldmann applanation tonometry (GAT). This systematic review and meta-analysis aims to update the existing literature with a reliability and agreement comparison of transpalpebral tonometers against the gold standard GAT for IOP measurement among individuals presenting for ophthalmic examinations. The data collection will be performed using a predefined search strategy through electronic databases. Prospective methods-comparison studies published between January 2000 and September 2022 will be included. Studies will be deemed eligible if they report empirical findings on the agreement between transpalpebral tonometry and Goldmann applanation tonometry. The standard deviation and limits of agreement between each study and their pooled estimate along with weights and percentage of error will be reported using a forest plot. Cochrane's Q test and the I2 statistic will be used to assess heterogeneity, and the publication bias will be investigated using a funnel plot, Begg's and Egger's tests. The review results will provide additional evidence on the reliability of transpalpebral tonometers that, in turn, could possibly assist practitioners to make informed decision about using it as a screening or diagnostic device for clinical practice, outreach camps, or home-based screening. Institutional Ethics Committee registration number: RET202200390. PROSPERO Registration Number: CRD42022321693.