Generating Models of Mental Retardation from Data with Machine Learning

This study focused on generating simple and expressive domain models of Mental Retardation (MR) from data using Knowledge Discovery and Datamining (KDD) methods. 2137 cases (mild or borderline MR) and 2165 controls (randomly selected) from the National Collaborative Perinatal Project (NCPP), a multicentric study involving pregnant mothers and the outcomes, constituted our sample. Twenty attributes (prenatal, perinatal and postnatal), thought to play a role in MR were utilized. The outcome variable (class), was, whether the child was retarded or not, based on the IQ score. Tree learners (C4.5,CART), rule inducers (C4.5Rules,FOCL) and a reference classi er (Naive Bayes) were the machine learning algorithms used for model building. The predictive accuracy ranged from 68.4% (FOCL) to 70.3% (Naive Bayes). CART obtained a sensitivity of 79.0% and also generated highly stable and simple trees across fty random two-third (training), one-third (testing) partitions of the sample. The algorithms identi ed emotional/behavioral problem in children as a signi cant predictor of MR risk. Our study shows that KDD methods hold promise in recovering useful structure from medical data.