Scaling trachoma surveillance in endemic areas using machine learning.
Deep learning model identified trachoma from eyelid photos with 85% accuracy
Scaling trachoma surveillance in endemic areas using machine learning.
Trachoma remains a leading infectious cause of blindness in endemic regions despite progress towards global elimination.
We retrospectively analysed anonymised inner eyelid photographs collected from trachoma prevalence surveys conducted in Ethiopia, Tanzania, Australia, Solomon Islands, Colombia, the Gambia, and Guatemala (n = 572 images).
correctly matched the expert diagnosis in most eyelid photos checked
The model achieved a sensitivity of 80.9% for detecting trachoma and a specificity of 90.5% for correctly identifying non-trachoma eyes.
Agreement between predictions and grader labels was substantial (κ = 0.71, 95% CI 0.58–0.84).
Our findings demonstrate the feasibility of using a reproducible R-based deep learning pipeline for automated trachoma classification in large-scale surveys.
These findings demonstrate the feasibility of automated trachoma classification using a transfer-learning framework. Larger datasets will be required before operational deployment in surveillance programmes.
CLINICAL TRIAL NUMBER: Not applicable.