Diagnosis from fundus photographs

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.

An Eye Tracking Analysis on Diagnostic Performance of Digital Fundus Photography Images between Ophthalmologists and Optometrists

To investigate the parameters of eye movement between ophthalmologists and optometrists while diagnosing digital fundus photographs, sixteen participants (eight ophthalmologists and eight optometrists) were recruited in this study. Every participant’s eye movement during diagnosis of a randomized set of fundus photographs displayed on an eye tracker were recorded. Fixation metrics (duration, count and rate) and scan path patterns were extracted from the eye tracker. These parameters of eye movement and correct diagnosis score were compared between both groups. Correlation analyses between fixation metrics and correct diagnosis score were also performed. Although fixation metrics between ophthalmologists and optometrists were not statistically different (p > 0.05), these parameters were statistically different when compared between different area of interests. Both participant groups had a similar correct diagnosis score. No correlation was found between fixation metrics and correct diagnosis score between both groups, except for total fixation duration and ophthalmologists’ diagnosis score of diabetic retinopathy photographs. The ophthalmologists’ scan paths were simpler, with larger saccades, and were distributed at the middle region of the photographs. Conversely, optometrists’ scan paths were extensive, with shorter saccades covering wider fundus areas, and were accumulated in some unrelated fundus areas. These findings indicated comparable efficiency and systematic visual search patterns between both the groups. Understanding visual search strategy could expedite the creation of a novel training routine for interpretation of ophthalmic diagnostic imaging.