Toward a Machine Learning Predictive-Oriented Approach to Complement Explanatory Modeling. An Application for Evaluating Psychopathological Traits Based on Affective Neurosciences and Phenomenology.

This paper presents a procedure that aims to integrate explanatory and predictive modelling for the construction of novel psychometric questionnaires based on psychological and neuroscientific theoretical grounding. It presents the methodology and the results of a procedure for items selection that considers both the explanatory power of the theory and the predictive power of modern computational techniques, namely factor analysis for investigating the dimensional structure and artificial neural networks (ANN) for predicting psychopathological diagnosis of clinical subjects. Such integration allows to derive theoretical insights on the characteristics of the items selected and their conformity with the theoretical framework of reference. At the same time, it permits to select those items that have the most relevance in term of prediction, by therefore considering the relationship of the items with the actual psychopathological diagnosis. This helps to construct a diagnostic tool that both conforms with the theory and with the individual characteristics of the population at hand, by providing insights on the power of the scale in precisely identifying out-of-sample pathological subjects. The proposed procedure is based on a sequence of steps that allows to construct a ANN that predicts the diagnosis of a group of subject based on their item responses to a questionnaire and subsequently automatically selects the most predictive items, by preserving the factorial structure of the scale. It is shown that the machine learning procedure selected a set of items that drastically improved the prediction accuracy of the model, compared to the predictions obtained using all the original items. At the same time, it reduced the redundancy of the items and eliminated those with less consistency.