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

• Published in: International journal of methods in psychiatric research Vol. 24; no. 2; pp. 156 - 169
• Main Authors: Askland, Kathleen D., Garnaat, Sarah, Sibrava, Nicholas J., Boisseau, Christina L., Strong, David, Mancebo, Maria, Greenberg, Benjamin, Rasmussen, Steve, Eisen, Jane
• Format: Journal Article
• Language: English
• Published: United States Blackwell Publishing Ltd 01.06.2015; John Wiley & Sons, Inc; John Wiley and Sons Inc
• Subjects: Adult; Female; Humans; Longitudinal Studies; Machine Learning; Male; obsessive compulsive disorder; Obsessive-Compulsive Disorder - diagnosis; Original; Predictive Value of Tests; Psychiatric Status Rating Scales; Psychometrics; Recurrence; Retrospective Studies; risk factors; statistics; obsessive compulsive disorder; risk factors; statistics
• ISSN: 1049-8931; 1557-0657
• DOI: 10.1002/mpr.1463

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. Copyright © 2015 John Wiley & Sons, Ltd.