AI-supported eye screening almost doubles clinic attendance in Tanzanian trial
People with sight-threatening diabetic eye disease in Tanzania were almost twice as likely to attend a specialist clinic after screening when artificial intelligence (AI) was used to assess their retinal photographs, according to a randomised controlled trial published in The Lancet Global Health.
The study was led by the International Centre for Eye Health (ICEH) from the London School of Hygiene & Tropical Medicine (LSHTM) alongside global partners including UCL Institute of Ophthalmology and NIHR Moorfields Biomedical Research Centre.
Researchers found that 35.9% of patients who had potentially sight-threatening diabetic retinopathy and received AI-supported screening attended the specialist eye clinic within eight weeks, compared to 18.2% of those who received standard screening. This is an absolute increase of 17.7 percentage points and a 97% relative increase
People allocated to AI-supported screening who then attended the specialist clinic did so an average of 10.9 days after screening, compared with 36.9 days in the standard pathway
The findings suggest that using AI to provide immediate screening results and face-to-face counselling could help many more people reach specialist care where they can access treatment to prevent vision loss. The Tanzanian Ministry of Health, a collaborator on the study, has now committed to integrating AI diagnostics into diabetic eye screening in multiple regions of the country.
Below, top to bottom: LSHTM worked with Kilimanjaro Christian Medical Centre to enrol 2,378 adults with diabetes at 24 hospitals in the Kilimanjaro and Arusha regions between March 2023 and August 2024. (All images: Hugh Bassett, LSHTM)
Dr Charles Cleland, ophthalmologist and clinical research fellow at LSHTM, said: “In this study, using AI in a diabetic eye screening programme in Tanzania enabled patients to receive their result along with face-to-face counselling at the point of screening, giving people the opportunity to ask questions, understand treatment options and feel supported in their care. In places where healthcare workers are already stretched, the results from this study suggest AI could improve access to specialist care and help prevent irreversible sight loss from diabetic retinopathy.”
The project is a collaboration between the International Centre for Eye Health (ICEH) at the London School of Hygiene & Tropical Medicine and Kilimanjaro Christian Medical Centres and includes researchers from:
Ministry of Health Tanzania
NIHR Moorfields Biomedical Research Centre
UCLInstitute of Ophthalmology
NIHR Birmingham Biomedical Research Centre
College of Medical and Dental Sciences, University of Birmingham
Homerton University Hospital, London
University of Dodoma, Tanzania
University of Freiburg, Germany.
The trial forms part of ICEH’s wider work on AI and eye imaging in Africa, which includes the Africa Oculomics Research Programme. That eight-year programme is funded by a Wellcome Discovery Award and run with the Medical Research Council/Uganda Virus Research Institute, Makerere University and the UCL Institute of Ophthalmology, will add retinal imaging to Uganda’s General Population Cohort to study how the eye can reveal cardiovascular, kidney and neurological disease.
