Intelligent quotient estimation of mental retarded people from different psychometric instruments using artificial neural networks

OBJECTIVE The estimation of a person's intelligence quotient (IQ) by means of psychometric tests is indispensable in the application of psychological assessment to several fields. When complex tests as the Wechsler scales, which are the most commonly used and universally recognized parameter for the diagnosis of degrees of retardation, are not applicable, it is necessary to use other psycho-diagnostic tools more suited for the subject's specific condition. But to ensure a homogeneous diagnosis it is necessary to reach a common metric, thus, the aim of our work is to build models able to estimate accurately and reliably the Wechsler IQ, starting from different psycho-diagnostic tools. METHODS AND MATERIALS Four different psychometric tests (Leiter international performance scale; coloured progressive matrices test; the mental development scale; psycho educational profile), along with the Wechsler scale, were administered to a group of 40 mentally retarded subjects, with various pathologies, and control persons. The obtained database is used to evaluate Wechsler IQ estimation models starting from the scores obtained in the other tests. Five modelling methods, two statistical and three from machine learning, that belong to the family of artificial neural networks (ANNs) are employed to build the estimator. RESULTS Several error metrics for estimated IQ and for retardation level classification are defined to compare the performance of the various models with univariate and multivariate analyses. Eight empirical studies show that, after ten-fold cross-validation, best average estimation error is of 3.37 IQ points and mental retardation level classification error of 7.5%. Furthermore our experiments prove the superior performance of ANN methods over statistical regression ones, because in all cases considered ANN models show the lowest estimation error (from 0.12 to 0.9 IQ points) and the lowest classification error (from 2.5% to 10%). CONCLUSIONS Since the estimation performance is better than the confidence interval of Wechsler scales (five IQ points), we consider models built very accurate and reliable and they can be used into help clinical diagnosis. Therefore a computer software based on the results of our work is currently used in a clinical center and empirical trails confirm its validity. Furthermore positive results in our multivariate studies suggest new approaches for clinicians.