Dataset Information

Predictors of remission from body dysmorphic disorder after internet-delivered cognitive behavior therapy: a machine learning approach.

ABSTRACT: BACKGROUND:Previous attempts to identify predictors of treatment outcomes in body dysmorphic disorder (BDD) have yielded inconsistent findings. One way to increase precision and clinical utility could be to use machine learning methods, which can incorporate multiple non-linear associations in prediction models. METHODS:This study used a random forests machine learning approach to test if it is possible to reliably predict remission from BDD in a sample of 88 individuals that had received internet-delivered cognitive behavioral therapy for BDD. The random forest models were compared to traditional logistic regression analyses. RESULTS:Random forests correctly identified 78% of participants as remitters or non-remitters at post-treatment. The accuracy of prediction was lower in subsequent follow-ups (68, 66 and 61% correctly classified at 3-, 12- and 24-month follow-ups, respectively). Depressive symptoms, treatment credibility, working alliance, and initial severity of BDD were among the most important predictors at the beginning of treatment. By contrast, the logistic regression models did not identify consistent and strong predictors of remission from BDD. CONCLUSIONS:The results provide initial support for the clinical utility of machine learning approaches in the prediction of outcomes of patients with BDD. TRIAL REGISTRATION:ClinicalTrials.gov ID: NCT02010619.

SUBMITTER: Flygare O

PROVIDER: S-EPMC7238519 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predictors of remission from body dysmorphic disorder after internet-delivered cognitive behavior therapy: a machine learning approach.

Flygare Oskar O Enander Jesper J Andersson Erik E Ljótsson Brjánn B Ivanov Volen Z VZ Mataix-Cols David D Rück Christian C

BMC psychiatry 20200519 1

<h4>Background</h4>Previous attempts to identify predictors of treatment outcomes in body dysmorphic disorder (BDD) have yielded inconsistent findings. One way to increase precision and clinical utility could be to use machine learning methods, which can incorporate multiple non-linear associations in prediction models.<h4>Methods</h4>This study used a random forests machine learning approach to test if it is possible to reliably predict remission from BDD in a sample of 88 individuals that had ...[more]

PMID: 32429939

Similar Datasets

Project description:ObjectivesTo evaluate the efficacy of therapist guided internet based cognitive behavioural therapy (CBT) programme for body dysmorphic disorder (BDD-NET) compared with online supportive therapy.DesignA 12 week single blind parallel group randomised controlled trial.SettingAcademic medical centre.Participants94 self referred adult outpatients with a diagnosis of body dysmorphic disorder and a modified Yale-Brown obsessive compulsive scale (BDD-YBOCS) score of ≥ 20. Concurrent psychotropic drug treatment was permitted if the dose had been stable for at least two months before enrolment and remained unchanged during the trial.InterventionsParticipants received either BDD-NET (n=47) or supportive therapy (n=47) delivered via the internet for 12 weeks.Main outcome measuresThe primary outcome was the BDD-YBOCS score after treatment and follow-up (three and six months from baseline) as evaluated by a masked assessor. Responder status was defined as a ≥ 30% reduction in symptoms on the scale. Secondary outcomes were measures of depression (MADRS-S), global functioning (GAF), clinical global improvement (CGI-I), and quality of life (EQ5D). The six month follow-up time and all outcomes other than BDD-YBOCS and MADRS-S at 3 months were not pre-specified in the registration at clinicaltrials.gov because of an administrative error but were included in the original trial protocol approved by the regional ethics committee before the start of the trial.ResultsBDD-NET was superior to supportive therapy and was associated with significant improvements in severity of symptoms of body dysmorphic disorder (BDD-YBOCS group difference -7.1 points, 95% confidence interval -9.8 to -4.4), depression (MADRS-S group difference -4.5 points, -7.5 to -1.4), and other secondary measures. At follow-up, 56% of those receiving BDD-NET were classed as responders, compared with 13% receiving supportive therapy. The number needed to treat was 2.34 (1.71 to 4.35). Self reported satisfaction was high.ConclusionsCBT can be delivered safely via the internet to patients with body dysmorphic disorder. BDD-NET has the potential to increase access to evidence based psychiatric care for this mental disorder, in line with NICE priority recommendations. It could be particularly useful in a stepped care approach, in which general practitioner or other mental health professionals can offer treatment to people with mild to moderate symptoms at low risk of suicide.Trial registration ClinicalTrials.gov ID: NCT02010619.

Project description:ObjectivesCognitive-behavioural therapy (CBT) is an effective treatment for body dysmorphic disorder (BDD). However, most sufferers do not have access to this treatment. One way to increase access to CBT is to administer treatment remotely via the Internet. This study piloted a novel therapist-supported, Internet-based CBT program for BDD (BDD-NET).DesignUncontrolled clinical trial.ParticipantsPatients (N=23) were recruited through self-referral and assessed face to face at a clinic specialising in obsessive-compulsive and related disorders. Suitable patients were offered secure access to BDD-NET.InterventionBDD-NET is a 12-week treatment program based on current psychological models of BDD that includes psychoeducation, functional analysis, cognitive restructuring, exposure and response prevention, and relapse prevention modules. A dedicated therapist provides active guidance and feedback throughout the entire process.Main outcome measureThe clinician-administered Yale-Brown Obsessive Compulsive Scale for BDD (BDD-YBOCS). Symptom severity was assessed pretreatment, post-treatment and at the 3-month follow-up.ResultsBDD-NET was deemed highly acceptable by patients and led to significant improvements on the BDD-YBOCS (p=<0.001) with a large within-group effect size (Cohen's d=2.01, 95% CI 1.05 to 2.97). At post-treatment, 82% of the patients were classified as responders (defined as≥30% improvement on the BDD-YBOCS). These gains were maintained at the 3-month follow-up. Secondary outcome measures of depression, global functioning and quality of life also showed significant improvements with moderate to large effect sizes. On average, therapists spent 10 min per patient per week providing support.ConclusionsThe results suggest that BDD-NET has the potential to greatly increase access to CBT, at least for low-risk individuals with moderately severe BDD symptoms and reasonably good insight. A randomised controlled trial of BDD-NET is warranted.Trial registration numberClinicaltrials.gov registration ID NCT01850433.

Project description:Cognitive behavior therapy (CBT) is an effective treatment for social anxiety disorder (SAD), but many patients do not respond sufficiently and a substantial proportion relapse after treatment has ended. Predicting an individual's long-term clinical response therefore remains an important challenge. This study aimed at assessing neural predictors of long-term treatment outcome in participants with SAD 1 year after completion of Internet-delivered CBT (iCBT). Twenty-six participants diagnosed with SAD underwent iCBT including attention bias modification for a total of 13 weeks. Support vector machines (SVMs), a supervised pattern recognition method allowing predictions at the individual level, were trained to separate long-term treatment responders from nonresponders based on blood oxygen level-dependent (BOLD) responses to self-referential criticism. The Clinical Global Impression-Improvement scale was the main instrument to determine treatment response at the 1-year follow-up. Results showed that the proportion of long-term responders was 52% (12/23). From multivariate BOLD responses in the dorsal anterior cingulate cortex (dACC) together with the amygdala, we were able to predict long-term response rate of iCBT with an accuracy of 92% (confidence interval 95% 73.2-97.6). This activation pattern was, however, not predictive of improvement in the continuous Liebowitz Social Anxiety Scale-Self-report version. Follow-up psychophysiological interaction analyses revealed that lower dACC-amygdala coupling was associated with better long-term treatment response. Thus, BOLD response patterns in the fear-expressing dACC-amygdala regions were highly predictive of long-term treatment outcome of iCBT, and the initial coupling between these regions differentiated long-term responders from nonresponders. The SVM-neuroimaging approach could be of particular clinical value as it allows for accurate prediction of treatment outcome at the level of the individual.

Project description:OBJECTIVES:Cognitive-behavioural therapy (CBT) has been shown to be an effective treatment for body dysmorphic disorder (BDD), but access to treatment around the world is limited. One way to increase access is to administer CBT remotely via the internet. This study represents the first effort to remotely deliver a therapist-supported, internet-based CBT treatment with no restrictions on enrolment based on geographical location, and it aims to assess whether this treatment can be delivered safely across international borders, with outcomes comparable to previous BDD-NET trials. DESIGN:Uncontrolled clinical trial. PARTICIPANTS:Patients (n=32) in nine different countries were recruited primarily through internet advertisements. INTERVENTION:BDD-NET is a 12-week treatment, consisting of eight treatment modules previously shown to be effective in a Swedish version. SETTING:Therapists based at a single, secondary care centre in Sweden provided active guidance and feedback throughout the treatment via asynchronous electronic messages. MAIN OUTCOME MEASURE:The clinician-administered Yale-Brown Obsessive Compulsive Scale for BDD (BDD-YBOCS). Symptom severity was assessed pretreatment, mid-treatment (6 weeks), post-treatment and at the 3-month follow-up. RESULTS:There were significant improvements on BDD-YBOCS scores (F(3, 71.63)=31.79, p<0.001), that were maintained at 3-month follow-up. Mean differences from baseline in BDD-YBOCS scores were -8.12 (week 6), -12.63 (post-treatment) and -11.71 (3-month follow-up). 47% and 50% of participants were considered treatment responders at post-treatment and 3-month follow-up, respectively. Additionally, remission rates were 28% at post-treatment and 44% at 3-month follow-up. The treatment was also deemed acceptable by patients. CONCLUSIONS:The results suggest that BDD-NET can be safely and effectively delivered across international borders to a culturally diverse sample. Larger scale randomised controlled trials with more participants from non-Western cultures are warranted to further validate the cross-cultural generalisability of this treatment. TRIAL REGISTRATION NUMBER:NCT03517384.

Dataset Information

Predictors of remission from body dysmorphic disorder after internet-delivered cognitive behavior therapy: a machine learning approach.

Publications

Predictors of remission from body dysmorphic disorder after internet-delivered cognitive behavior therapy: a machine learning approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets