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

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

There are no consistent predictors of treatment outcome in paediatric obsessive–compulsive disorder (OCD). One reason for this might be the use of suboptimal statistical methodology. Machine learning is an approach to efficiently analyse complex data. Machine learning has been widely used within other fields, but has rarely been tested in the prediction of paediatric mental health treatment outcomes. To test four different machine learning methods in the prediction of treatment response in a sample of paediatric OCD patients who had received Internet‐delivered cognitive behaviour therapy (ICBT). Participants were 61 adolescents (12–17 years) who enrolled in a randomized controlled trial and received ICBT. All clinical baseline variables were used to predict strictly defined treatment response status three months after ICBT. Four machine learning algorithms were implemented. For comparison, we also employed a traditional logistic regression approach. Multivariate logistic regression could not detect any significant predictors. In contrast, all four machine learning algorithms performed well in the prediction of treatment response, with 75 to 83% accuracy. The results suggest that machine learning algorithms can successfully be applied to predict paediatric OCD treatment outcome. Validation studies and studies in other disorders are warranted.

Related collections

Most cited references 40

Record: found
Abstract: found
Article: not found

Cognitive behavior therapy via the Internet: a systematic review of applications, clinical efficacy and cost-effectiveness.

Erik Hedman, Brjánn Ljótsson, Nils Lindefors (2012)

Internet-based cognitive behavior therapy (ICBT) is a promising treatment that may increase availability of cognitive behavior therapy (CBT) for psychiatric disorders and other clinical problems. The main objective of this study was to determine the applications, clinical efficacy and cost-effectiveness of ICBT. The authors conducted a systematic review to identify randomized controlled trials investigating CBT delivered via the internet for adult patient populations. Searches to identify studies investigating cost-effectiveness of ICBT were also conducted. Evidence status for each clinical application was determined using the American Psychologist Association criteria for empirically supported treatments. Of 1104 studies reviewed, 108 met criteria for inclusion, of which 103 reported on clinical efficacy and eight on cost-effectiveness. Results showed that ICBT has been tested for 25 different clinical disorders, whereas most randomized controlled trials have been aimed at depression, anxiety disorders and chronic pain. Internet-based treatments for depression, social phobia and panic disorder were classified as well-established, that is, meeting the highest level of criteria for evidence. Effect sizes were large in the treatment of depression, anxiety disorders, severe health anxiety, irritable bowel syndrome, female sexual dysfunction, eating disorders, cannabis use and pathological gambling. For other clinical problems, effect sizes were small to moderate. Comparison to conventional CBT showed that ICBT produces equivalent effects. Cost-effectiveness data were relatively scarce but suggested that ICBT has more than 50% probability of being cost effective compared with no treatment or to conventional CBT when willingness to pay for an additional improvement is zero. Although ICBT is a promising treatment option for several disorders, it can only be regarded as a well-established treatment for depression, panic disorder and social phobia. It seems that ICBT is as effective as conventional CBT for respective clinical disorder, that is, if conventional CBT works then ICBT works. The large effects and the limited therapist time required suggest that the treatment is highly cost effective for well-established indications.

0 comments Cited 246 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Introduction to machine learning for brain imaging.

Steven Lemm, Benjamin Blankertz, Thorsten Dickhaus … (2011)

Machine learning and pattern recognition algorithms have in the past years developed to become a working horse in brain imaging and the computational neurosciences, as they are instrumental for mining vast amounts of neural data of ever increasing measurement precision and detecting minuscule signals from an overwhelming noise floor. They provide the means to decode and characterize task relevant brain states and to distinguish them from non-informative brain signals. While undoubtedly this machinery has helped to gain novel biological insights, it also holds the danger of potential unintentional abuse. Ideally machine learning techniques should be usable for any non-expert, however, unfortunately they are typically not. Overfitting and other pitfalls may occur and lead to spurious and nonsensical interpretation. The goal of this review is therefore to provide an accessible and clear introduction to the strengths and also the inherent dangers of machine learning usage in the neurosciences. Copyright © 2010 Elsevier Inc. All rights reserved.

0 comments Cited 200 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: found

Is Open Access

Predicting sample size required for classification performance

Rosa Figueroa, Qing Zeng-Treitler, Sasikiran Kandula … (2012)

Background Supervised learning methods need annotated data in order to generate efficient models. Annotated data, however, is a relatively scarce resource and can be expensive to obtain. For both passive and active learning methods, there is a need to estimate the size of the annotated sample required to reach a performance target. Methods We designed and implemented a method that fits an inverse power law model to points of a given learning curve created using a small annotated training set. Fitting is carried out using nonlinear weighted least squares optimization. The fitted model is then used to predict the classifier's performance and confidence interval for larger sample sizes. For evaluation, the nonlinear weighted curve fitting method was applied to a set of learning curves generated using clinical text and waveform classification tasks with active and passive sampling methods, and predictions were validated using standard goodness of fit measures. As control we used an un-weighted fitting method. Results A total of 568 models were fitted and the model predictions were compared with the observed performances. Depending on the data set and sampling method, it took between 80 to 560 annotated samples to achieve mean average and root mean squared error below 0.01. Results also show that our weighted fitting method outperformed the baseline un-weighted method (p < 0.05). Conclusions This paper describes a simple and effective sample size prediction algorithm that conducts weighted fitting of learning curves. The algorithm outperformed an un-weighted algorithm described in previous literature. It can help researchers determine annotation sample size for supervised machine learning.