Prediction of illness remission in patients with Obsessive-Compulsive Disorder with supervised machine learning
收藏资源简介：
Prediction of illness remission in patients with Obsessive-Compulsive<br> Disorder with supervised machine learning Introduction: The course of OCD differs widely among OCD patients, varying from chronic symptoms to full<br> remission. No tools for individual prediction of OCD remission are currently available. This study aimed to<br> develop a machine learning algorithm to predict OCD remission after two years, using solely predictors easily<br> accessible in the daily clinical routine.<br> Methods: Subjects were recruited in a longitudinal multi-center study (NOCDA). Gradient boosted decision<br> trees were used as supervised machine learning technique. The training of the algorithm was performed with 227<br> predictors and 213 observations collected in a single clinical center. Hyper-parameter optimization was performed<br> with cross-validation and a Bayesian optimization strategy. The predictive performance of the algorithm<br> was subsequently tested in an independent sample of 215 observations collected in five different centers.<br> Between-center differences were investigated with a bootstrap resampling approach.<br> Results: The average predictive performance of the algorithm in the test centers resulted in an AUROC of<br> 0.7820, a sensitivity of 73.42%, and a specificity of 71.45%. Results also showed a significant between-center<br> variation in the predictive performance. The most important predictors resulted related to OCD severity, OCD<br> chronic course, use of psychotropic medications, and better global functioning.<br> Limitations: All recruiting centers followed the same assessment protocol and are in The Netherlands. Moreover,<br> the sample of the data recruited in some of the test centers was limited in size.<br> Discussion: The algorithm demonstrated a moderate average predictive performance, and future studies will<br> focus on increasing the stability of the predictive performance across clinical settings.
