Our Research



The world health organization (WHO) defines Telemedicine as “The delivery of health care services, where distance is a critical factor, by all health care professionals using information and communication technologies for the exchange of valid information for diagnosis, treatment and prevention of disease and injuries, research and evaluation, and for the continuing education of health care providers, all in the interests of advancing the health of individuals and their communities” (1)(2)(3)

Vision 2020 was lunched by the WHO in 1999, which sort to achieve a goal; elimination of avoidable causes of blindness by 2020 through disease control and treatment, human resource development, developing appropriate infrastructure and technology development (4),(5).

Diabetes affects vital organs in the body, including the eye. One third of the people living with diabetes have some form of eye disease. Another 30% to 35% of these people end up with sight threatening eye disease. Seventy-five percent of those living with DR live in LMIC (6)(7)(8). Thus, focusing on LMIC in the global fight against DR cannot be overemphasized.

According to current data on diabetic retinopathy, all individuals who have lived with type 1 diabetes for 20 years and 60% of type 2 diabetics will have some form of DR (6).

Evidence shows that, blindness due to DR can be tackled at three levels. These include prevention at the primary level, secondary level and the tertiary level. At the primary level, the focus is on prevention of the disease affecting the eye through health education for example. The secondary level involves monitory DR to prevent progression mainly through screening and the tertiary level focuses on preventing blindness by treating blinding diabetic macular oedema (DMO) and proliferative diabetic retinopathy (PDR) (7)(8).

The UK and USA have been quite successful with their national diabetic eye screening program. This has seen a major impact especially in the UK, as DR is no longer the leading cause of blindness among the working age group (6).


Most of the focus on diabetes and the eye in recent times has been on retinopathy. Some studies however seem to suggest that there is some form of choroidopathy, prior to the development of retinopathy.

If there is early diagnosis, at the stage of choroidopathy, can DR be prevented? Metabolic memory, reported according to the United Kingdom Prospective Diabetic Study (UKPDS), which is a phenomenon that suggests a dysfunction in the vascular system due to persistent hyperglycaemia, because of epigenomic alterations, shows that, DR cannot be prevented should this happen. Early diagnosis and prevention is thus imperative (8)

AI, in healthcare is growing very rapidly in recent times. Studies to explore automated AI, which enables clinicians who have no knowledge about coding are on-going (6)(9).

A study in Zambia to evaluate the accuracy of an AI based system suggests that, the use of AI in Africa for DR screening could prove to bring much gains in the fight against DR in the continent (6).

If we can apply AI to pre-diabetic retinopathy, retinopathy will be reduced. Interventions can be initiated in a timely manner.

This study is aimed at exploring AI in diagnosing pre diabetic retinopathy.

With the goal of vision 2020 for the next decade, which is ending avoidable vision loss by 2030 (10), the impact of diabetic eye disease cannot be overemphasized. With the rate at which technology is expanding, it is a dream that can be realised if careful strategies are put in place. In their document, 2030 in sight strategy, they highlight the need for private public sector partnership as one of the important strategies that can help drive and achieve this goal (11).

The proposed study population is African diabetics, living in Ghana. The sample size is 600 diabetics at the Tema General Hospital. The focus is on Africa. It is a well-known fact that the parameters of the eye are affected by ethnicity. Moreover, globally numerous advances are underway. Africa should not be left behind.


  • Could AI be applied to the pre-diabetic retinopathy eye?
  • Can an AI system be applied to measure the CVI that is likely to predict or screen for an eye that could progress into diabetic retinopathy?


  • 1. World Health Organization. Global diffusion of eHealth: Making universal health coverage achievable. [Internet]. Report of the third global survey on eHealth. 2016. 160 p. Available from: http://who.int/goe/publications/global_diffusion/en/
  • 2. Mohammadpour M, Heidari Z, Mirghorbani M, Hashemi H. Smartphones, tele-ophthalmology, and VISION 2020. Int J Ophthalmol. 2017;10(12):1909–18.
  • 3. Li JO, Liu H, Ting DSJ, Jeon S, Chan RVP, Kim JE, et al. Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID- 19 . The COVID-19 resource centre is hosted on Elsevier Connect , the company ’ s public news and information . 2020;(January).
  • 4. WHO. Vision2020. Who/Pbl. 1997;52.
  • 5. Foster A, Resnikoff S. The impact of Vision 2020 on global blindness. Eye. 2005;19(10):1133–5.
  • 6. Wong TY, Sabanayagam C. Strategies to Tackle the Global Burden of Diabetic Retinopathy: From Epidemiology to Artificial Intelligence. Ophthalmologica. 2020;243(1):9–20.
  • 7. Yau JWY, Rogers SL, Kawasaki R, Lamoureux EL, Kowalski JW, Bek T, et al. Global Prevalence and Major Risk Factors of Diabetic Retinopathy. Diabetes Care. 2012 Mar;35(3):556–64.
  • 8. Wong TY, Sabanayagam C. The war on diabetic retinopathy: Where are we now? Asia-Pacific J Ophthalmol. 2019;8(6):448–56.
  • 9. Keane P, Topol E. Reinventing the eye exam. Lancet [Internet]. 2019 Dec 14;394(10215):2141. Available from: https://doi.org/10.1016/S0140-6736(19)33051-X
  • 10. Trounson A. Ending avoidable blindness. Pursuit. 2021;
  • 11. Trounson A. Ending avoidable blindness. Pursuit [Internet]. 2021; Available from: https://pursuit.unimelb.edu.au/features/ending-avoidable-blindness