P.4.005 - Predicting the naturalistic course of depression from a wide range of clinical, psychological and biological data: a machine learning approach

Abstract

Depression is among the leading causes of disability in industrialized countries [1]. To effectively target interventions for patients at risk for a worse long-term clinical outcome, there is a need to identify predictors of chronicity and remission at an early stage. Many clinical, psychological and biological variables have been linked to different course trajectories of depression. These findings, however, are based on group comparisons with unknown translational value. A variable that is statistically significantly different between groups does not necessarily carry sufficient predictive power at the individual level, e.g. because the average difference between groups may be small or because of a high degree of variation within each group. This study evaluated the prognostic value of a wide range of clinical, psychological and biological (markers related to somatic health, metabolic syndrome, inflammation and autonomic nervous system) characteristics for predicting the course of depression and aimed to identify the best set of predictors. We used data from the Netherlands Study of Depression and Anxiety (NESDA), including unipolar depression patients recruited from the community, primary care and specialized mental health care, thereby capturing a broad range of illness severity [2]. Unipolar depressed patients (major depressive disorder or dysthymia, N=804) were assessed on a panel of 81 clinical, psychological and biological measures and were clinically followed-up for 2 years. Subjects were grouped according to (i) the presence of a depression diagnosis at 2-year follow-up (yes N=397, no N=407), and (ii) three disease course trajectory groups (rapid remission, N=356, gradual improvement N=273, chronic N=175) identified by a latent class growth analysis [3]. We used a penalized logistic regression to predict depression course and a stability selection method to select the optimal set of significant predictor variables from the multivariate model. Using all clinical, psychological and biological predictors, we could discriminate between the three course trajectory groups; rapid remission (REM) with 0.69 AUROC and 66% balanced accuracy, the gradual improving (IMP) group with 0.62 AUROC and 60% balanced accuracy, and the chronic (CHR) group with 0.66 AUROC and 61% balanced accuracy. Furthermore, we could discriminate between patients with and without a unipolar depression diagnosis at two-year follow-up with 0.66 AUROC and 62% balanced accuracy. We identified the total score on the Inventory of Depressive Symptomatology (IDS)[4] as the most important predictor for the naturalistic course of depression, especially for predicting rapid remission with an AUROC of 0.66 (62% accuracy) and for predicting the presence of an MDD diagnosis at follow-up with an AUROC of 0.69 (66 % accuracy). Furthermore, The IDS total score is the only variable that survived family wise error correction (with pfwer Amongst a wide set of psychological, biological and clinical (anxiety and depression) variables no other measure improved the prediction accuracy that was obtained based on self-reported depressive symptoms (IDS scores) alone. However, our best model only showed moderate predictive performance at best, hence, the prediction model requires further improvements to be clinically useful.