Predicting depression history from a short reward/aversion task with behavioral economic features
This paper presents a novel example of depression prediction, merging cognitive science with data-driven machine learning. Behavioral economic features were engineered from a short picture rating task. Relative Preference Theory was ap-plied to rating data for quantifying the degree to which partici-pants liked, disliked, or were neutral to several types of pictures; thus, behavioral economic variables including loss aversion, risk aversion, and 13 others that are amenable to psychological in-terpretation were mined. These variables were features of a lo-gistic regression predictive model that targeted depression in a population-based sample (N=281) with high test accuracy and no overfitting. Per our review of the literature, we cannot iden-tify other papers that explicitly use behavioral economic fea-tures to predict depression with machine learning