Artificial Intelligence improves follow-up appointment uptake for diabetic retinal assessment: a systematic review and meta-analysis

Masoud Rahmati; Lee Smith; Mapa Prabhath Piyasena; Michael Bowen; Laurent Boyer; Guillaume Fond; Abdolreza Kazemi; Dong Keon Yon; Hayeon Lee; Tarnjit Sehmbi; Sanjiv Ahluwalia; Shahina Pardhan

doi:10.1038/s41433-025-03849-4

Artificial Intelligence improves follow-up appointment uptake for diabetic retinal assessment: a systematic review and meta-analysis

Eye (Lond). 2025 May 30. doi: 10.1038/s41433-025-03849-4. Online ahead of print.

Authors

Masoud Rahmati^{1

2

3

4}, Lee Smith⁵, Mapa Prabhath Piyasena⁶, Michael Bowen⁷, Laurent Boyer^{8

9}, Guillaume Fond^{8

9}, Abdolreza Kazemi¹⁰, Dong Keon Yon^{11

12}, Hayeon Lee¹¹, Tarnjit Sehmbi⁶, Sanjiv Ahluwalia¹³, Shahina Pardhan^{14

15}

Affiliations

¹ CEReSS-Health Service Research and Quality of Life Center, Assistance Publique-Hopitaux de Marseille, Aix-Marseille University, Marseille, France. masoud.rahmati@univ-amu.fr.
² CRSMP, Center for Mental Health and Psychiatry Research - PACA, Marseille, France. masoud.rahmati@univ-amu.fr.
³ Department of Physical Education and Sport Sciences, Faculty of Literature and Human Sciences, Lorestan University, Khoramabad, Iran. masoud.rahmati@univ-amu.fr.
⁴ Department of Physical Education and Sport Sciences, Faculty of Literature and Humanities, Vali-E-Asr University of Rafsanjan, Rafsanjan, Iran. masoud.rahmati@univ-amu.fr.
⁵ Centre for Health, Performance, and Wellbeing, Anglia Ruskin University, Cambridge, UK.
⁶ Vision and Eye Research Institute, School of Medicine, Anglia Ruskin University, Young Street, Cambridge, UK.
⁷ The College of Optometrists, London, UK.
⁸ CEReSS-Health Service Research and Quality of Life Center, Assistance Publique-Hopitaux de Marseille, Aix-Marseille University, Marseille, France.
⁹ CRSMP, Center for Mental Health and Psychiatry Research - PACA, Marseille, France.
¹⁰ Department of Physical Education and Sport Sciences, Faculty of Literature and Humanities, Vali-E-Asr University of Rafsanjan, Rafsanjan, Iran.
¹¹ Center for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, Republic of Korea.
¹² Department of Pediatrics, Kyung Hee University College of Medicine, Seoul, Republic of Korea.
¹³ Head of School of Medicine, Anglia Ruskin University, Chelmsford, England.
¹⁴ Vision and Eye Research Institute, School of Medicine, Anglia Ruskin University, Young Street, Cambridge, UK. shahina.pardhan@aru.ac.uk.
¹⁵ Centre for Inclusive Community Eye Health, Anglia Ruskin University, Cambridge, UK. shahina.pardhan@aru.ac.uk.

PMID: 40447778
DOI: 10.1038/s41433-025-03849-4

Abstract

Background/objectives: Artificial intelligence (AI) assessment of diabetic retinopathy (DR) instead of scarce trained specialists could potentially increases the efficiency and accessibility of screening programs. This systematic review aims to systematically examine the uptake of follow-up appointments with initial computer-based AI and human graders of DR.

Methods: We conducted a systematic review and meta-analysis by screening articles in any languages in PubMed, MEDLINE (Ovid), EMBASE, Web of Science, Cochrane CENTRAL and CDSR published from database inception up to 20^th August 2024. We used random-effects meta-analysis to pool the results as odds ratios (OR) with corresponding 95% confidence intervals (CI).

Results: Data from a total of 20,108 patients with diabetes (6476 participants graded using AI and 13,632 participants graded by human-graders; age range of the participants 5 to 67 years) from six studies were included. The result of the pooled meta-analysis showed that initial AI assessment of DR significantly increased uptake of follow-up appointments compared to human grader-based (OR = 1.89, 95% CI 1.78-2.01, P = 0.00001).

Conclusions: The present systematic review and meta-analysis suggest that initial AI-based algorithm for screening DR is associated with an increased uptake of follow-up examination. This is most likely due to instant results being made available with AI based algorithms when compared to a delay in assessment with human graders.