Artificial Neural Network Model for the Prediction of Obsessive-Compulsive Disorder Treatment Response

Abstract

Several patients with obsessive-compulsive disorder (OCD) who are refractory to adequate treatment with first-line treatments are considered treatment-resistant. Further surveys were to be implemented to explore the outcome predictors of the antiobsessional response. Such study was aimed at building a model suitable to predict the final outcome of a mixed OCD pharmacologic and nonpharmacologic treatment approaches. We studied 130 subjects with OCD who underwent pharmacologic (with selective serotonin reuptake inhibitors alone or with selective serotonin reuptake inhibitors and risperidone at low dosage) and/or behavioral therapy (using exposure and response prevention techniques). The following variables were used as predictors: symptoms dimension, as resulting from the Yale-Brown Obsessive-Compulsive Scale items factor analysis; neuropsychologic performances; and epidemiologic variables. The treatment response arising from 3 to 6 months of therapy was used as dependent variable. A conventional logistic regression was used to define a previsional model of treatment response and multilayer perceptrons and to supervise an artificial neural network technique. The 46.9% of the sample resulted to be refractory to treatment. Results obtained with the logistic regression model showed that the only predictors of treatment outcome are hoarding symptoms, repeating rituals, and counting compulsions. Furthermore, using all the variables considered in the models, multilayer perceptrons showed highly better predictive performance as compared with the logistic regression models (93.3% vs 61.5%, respectively, of correct classification of cases). Complex interactions between different clinical and neuropsychologic variables are involved in defining OCD treatment response profile, and nonlinear and interactive modeling strategies, that is, supervised artificial neural networks, seem to be more suitable to investigate this complexity than linear techniques.

Studying depression using imaging and machine learning methods

“…With only 50% of patients experiencing treatment response to first-line agents, and an adequate antidepressant trial requiring several weeks before symptom improvement becomes evident, machine-learning methods have the potential to significantly reduce the duration of patient suffering. Outside the scope of depression, these techniques have shown promise in predicting treatment response in other various other psychiatric diseases, including schizophrenia and obsessive–compulsive disorder ( Khodayari-Rostamabad et al, 2010 , Salomoni et al, 2009 ). Therefore, advances in development of machine-learning are likely to have wide-ranging implications throughout psychiatry, regardless of the specific disease to which they are first applied.…”

Venlafaxine extended-release treatment of hoarding disorder

“…Some retrospective studies investigating the influence of OCD symptom factors on treatment response found that hoarding and saving symptoms in patients with OCD were associated with poor response to pharmacotherapy with serotonin reuptake inhibitor (SRI) medications (Black et al 1998, Winsberg et al 1999, Mataix-Cols et al 1999, Stein et al 2007 & 2008, Salomoni et al 2009), but many others have failed to replicate this association (Saxena 2011). Several studies found that hoarding/saving symptoms had no significant effect on response to treatment in OCD patients (Alonso et al 2001, Ferrao et al 2006, Erzegovesi et al 2001, Shetti et al 2005, Landeros-Weisenberger et al 2010).…”

Treatment for Hoarding Behaviors: A Review of the Evidence

“…The presence of hoarding symptoms on the Y-BOCS symptom checklist was associated with poor treatment response regardless of the type of pharmacological treatment. Another study examined 130 adult patients with OCD who received SSRIs alone or with low dose of an atypical antipsychotic, risperidone, and/or behavioral therapy (using exposure and response prevention techniques) (Salomoni et al 2009). Using factors identified from the Y-BOCS, hoarding was again found to be a predictor of worse outcome.…”