About the research topic
Retinopathy of prematurity (ROP) is a rare but very serious eye disease caused by the abnormal development of the blood vessels in the retina in children who are born (extremely) prematurely. Severe ROP can lead to lifelong visual impairment despite treatment, and in its worst form, blindness. Therefore, premature infants are intensively screened for ROP. However, the ROP screening process is very stressful for child and parent, and is also associated with logistical difficulties. In order to better tailor ophthalmic care for premature infants to the individual risk of severe ROP, we want to use artificial intelligence to build models that can predict which child will develop a severe, treatment-dependent form of ROP.
The baseline for this project was set in the paper “Early prediction of severe retinopathy of prematurity requiring laser treatment using physiological data”, by Poppe et al., where machine learning models are applied to certain clinical variables to predict if the child will develop severe ROP (see Figure).
Funding: Wis(h)dom foundation
