Prediction of remission in obsessive compulsive disorder using a novel machine learning strategy

Abstract

The study objective was to apply machine learning methodologies to identify predictors of remission in a longitudinal sample of 296 adults with a primary diagnosis of obsessive compulsive disorder (OCD). Random Forests is an ensemble machine learning algorithm that has been successfully applied to large-scale data analysis across vast biomedical disciplines, though rarely in psychiatric research or for application to longitudinal data. When provided with 795 raw and composite scores primarily from baseline measures, Random Forest regression prediction explained 50.8% (5000-run average, 95% bootstrap confidence interval [CI]: 50.3–51.3%) of the variance in proportion of time spent remitted. Machine performance improved when only the most predictive 24 items were used in a reduced analysis. Consistently high-ranked predictors of longitudinal remission included Yale–Brown Obsessive Compulsive Scale (Y-BOCS) items, NEO items and subscale scores, Y-BOCS symptom checklist cleaning/washing compulsion score, and several self-report items from social adjustment scales. Random Forest classification was able to distinguish participants according to binary remission outcomes with an error rate of 24.6% (95% bootstrap CI: 22.9–26.2%). Our results suggest that clinically-useful prediction of remission may not require an extensive battery of measures. Rather, a small set of assessment items may efficiently distinguish high- and lower-risk patients and inform clinical decision-making.

Prediction of outcome in internet‐delivered cognitive behaviour therapy for paediatric obsessive‐compulsive disorder: A machine learning approach

“…More specifically, the predictive models that were trained in a subset of the sample could then accurately predict treatment response in 75 to 83% of previously unseen cases in the test sample. The degree of accuracy is in line with previous machine learning studies in adults with OCD (Askland et al, ) and children with ADHD (Kim et al, ). The Linear Model with best subset predictor selection had slightly higher accuracy than the other three models, perhaps indicating superiority of the model and at the same time providing good interpretability due to linear modelling.…”

“…One recent example of machine learning from the adult OCD field is the study by Askland et al (), in which a machine learning approach was used to predict remission in a large longitudinal sample of N = 296 individuals. The resulting model was able to predict time spent in remission accurately in 75.4% of cases, using a subset of 24 baseline variables.…”

General personality dimensions, impairment and treatment response in obsessive–compulsive disorder

“…Given the retrospective nature of this study, it cannot determine the direction of the relationship between personality, impairment and treatment response. On the one hand, the Brown Longitudinal Obsessive Compulsive Study found a relationship between neuroticism and remission of OCD symptoms (however, because the NEO was administered only once, between years 2 and 10 of follow‐up, the direction of the relationship could not be determined with certainty) . On the other hand, although personality is thought to become relatively stable by young adulthood, OCD often has an early age of onset, before adolescence in many cases .…”

“…In 56 OCD patients, Rector and colleagues found that lower scores on two openness facets, openness to ideas and openness to actions, were related to greater severity of OCD symptoms . In a prospective study of 296 OCD patients, neuroticism was a strong predictor of remission during the follow‐up period . Apart from these studies, however, little has been reported on the relationship between general personality dimensions, severity, and treatment response in OCD.…”

The revolution of personalized psychiatry: will technology make it happen sooner?

“…Several more examples are available in the recent literature, with the aim or early predicting response to both pharmacological and nonpharmacological treatment (Salomoni et al 2009;Amminger et al 2015;Mansson et al 2015;Patel et al 2015a;Chekroud et al 2016), remission (Askland et al 2015), relapse , severity levels of depression and suicidal ideation (Setoyama et al 2016), risk for later developing a certain psychiatric disorder (Carpenter et al 2016;Chuang & Kuo, 2017;Emerson et al 2017), as well as to automatically perform diagnosis (Wall et al 2012;Khodayari-Rostamabad et al 2013;Johnston et al 2014;Amminger et al 2015;Askland et al 2015;Liu et al 2015;Mansson et al 2015;Qin et al 2015;Ravan et al 2015;Patel et al 2015a;Chekroud et al 2016) and this field will surely expand exponentially in the years to come. Theoretically, predictive tools may be developed for nearly all clinically relevant questions, assisting clinicians when making decisions with patients.…”