Machine Learning to Predict the Incidence of Retinopathy of Prematurity.

摘要: Retinopathy of Prematurity (ROP) is a disorder afflicting prematurely born infants. ROP can be positively diagnosed few weeks after birth. The goal this study to build an automatic tool for prediction the incidence from standard clinical factors recorded at birth premature babies. data presents various challenges including mixing categorical and numeric attributes noisy data. In article we present ensemble classifier—hierarchical committee random trees—that uses risk in order predict developing ROP. We empirically demonstrate that our classifier outperforms other state art classification approaches.