Retinopathy of Prematurity (ROP) Research Projects 

Retinopathy of Prematurity (ROP)

Retinopathy of prematurity (ROP) is an eye disease that occurs in premature infants, primarily those born before 31 weeks or with a low birth weight. It is caused by abnormal blood vessel growth in the retina. In severe cases, ROP can lead to retinal detachment and blindness.

With 15 million babies born preterm every year, it is an important problem in child eye health which is rising as the number of children born prematurely increases with improved access to neonatal care and therefore increasing survival.

To treat ROP and prevent sight loss in children, it must be accurately diagnosed early with timely screening after birth. Current screening methods are costly and rely on specialized equipment that is often unavailable in low-resource settings.

Current Research

We are currently running a study in Nepal that will evaluate a new telemedicine-based model for screening ROP. The model will train non-specialist health workers to capture retinal images of preterm infants, which will then be assessed both by human graders and an artificial intelligence (AI) algorithm. This approach aims to determine whether trained non-specialists, supported by AI, can accurately identify infants who need referral for specialist care.

The research is a prospective, cross-sectional comparison conducted across three neonatal care sites in Kathmandu. Each enrolled infant will undergo retinal imaging using both a standard widefield digital fundus imaging (WFDI) camera and a newly developed, lower-cost smartphone-based fundus imaging (SBFI) system. Human assessments of images from both devices will be compared with AI-generated diagnoses.

In the first phase, the study will validate the accuracy of non-specialist-led telemedicine screening and AI-assisted diagnosis for detecting referral- and treatment-warranted ROP. In the second phase, it will compare the diagnostic performance of the new smartphone-based camera with the current standard WFDI device.

The ultimate goal is to demonstrate that:
a) Non-specialists can be effectively trained to perform ROP screening through telemedicine;
b) AI can accurately triage which infants require specialist review, reducing the workload for ophthalmologists; and
c) The smartphone-based imaging device provides image quality comparable to existing, expensive systems.

If validated, this combined approach: task-shifting to non-specialists, AI-assisted image interpretation, and use of affordable imaging technology, could make nationwide and regional ROP screening programmes feasible in low- and middle-income countries, preventing avoidable blindness in premature infants.

Retinopathy of Prematurity Network

An important tool in the fight against ROP is increased awareness, training and skills among health care professionals dealing with newborns. The ROP Network was established by the International Centre for Eye Health to reduce unnecessary blindness from retinopathy of prematurity in low resource settings, through south-south information sharing and training, capacity-strengthening, policy engagement, and context-specific research. Our aims are to bring together all those working to reduce blindness from ROP for the benefit of all, and especially the children and their families.

Find out more about the network here: https://iceh.lshtm.ac.uk/the-retinopathy-of-prematurity-network/

For more information on our ROP work, please email Aeesha.Malik@lshtm.ac.uk

Acknowledgements

We would like to thank Velux Stiftung for funding for the Nepal AI work.

We would also like to thank Nepal Netra Jyoti Sangh, Tribhuvan University Teaching Hospital, Kathmandu Medical College and the Tilganga Institute of Ophthalmology for their collaboration on the Nepal AI project.

Publications

Ademola-Popoola DS, Fajolu IB, Gilbert C, Olusanya BA, Onakpoya OH, Ezisi CN, Musa KO, Chan RVP, Okeigbemen VW, Muhammad RC, Malik ANJ, Adio AO, Bodunde OT, Rafindadi AL, Oluleye TS, Tongo OO, Badmus SA, Adebara OV, Padhi TR, Ezenwa BN, Obajolowo TS, Olokoba LB, Olatunji VA, Babalola YO, Ugalahi MO, Adenekan A, Adesiyun OO, Sahoo J, Miller MT, Uhumwangho OM, Olagbenro AS, Adejuyigbe EA, Ezeaka CVC, Mokuolu O, Ogunlesi TA, Ogunfowora OB, Abdulkadir I, Abdullahi FL, Fabiyi AT, Hassan LHL, Baiyeroju AM, Opara PI, Oladigbolu K, Eneh AU, Fiebai BE, Mahmud-Ajeigbe FA, Peter EN, Abdullahi HS. Strengthening retinopathy of prematurity screening and treatment services in Nigeria: a case study of activities, challenges and outcomes 2017-2020. BMJ Open Ophthalmol. 2021 Aug 23;6(1):e000645. doi: 10.1136/bmjophth-2020-000645. PMID: 34514173; PMCID: PMC8383855.

Gilbert C, Malik ANJ, Nahar N, Das SK, Visser L, Sitati S, Ademola-Popoola DS. Epidemiology of ROP update – Africa is the new frontier. Semin Perinatol. 2019 Oct;43(6):317-322. doi: 10.1053/j.semperi.2019.05.002. Epub 2019 May 11. PMID: 31151778.

Gilbert C, Malik ANJ, Vinekar A. Artificial Intelligence for ROP Screening and to Assess Quality of Care: Progress and Challenges. Pediatrics. 2021 Mar;147(3):e2020034314. doi: 10.1542/peds.2020-034314. PMID: 33637647.