Predictors and Moderators of Outcomes in a Trial of Cognitive Behavioural Therapy Integrated with Behavioural Weight Loss for High Weight Individuals with Disorders of Recurrent Binge Eating

Abstract

Background/Objectives: To inform person-centred clinical practice, it is important to know what features may predict or moderate treatment outcomes. Thus, we investigated pre-treatment clinical features and mid-therapy reduction in loss of control over eating (MTLOCE), including impacts on treatment outcomes of a new manualised psychotherapy, a healthy approach to weight management and food in eating disorders (HAPIFED). HAPIFED was developed as an integrated psychological and behavioural treatment for individuals with bulimia nervosa or binge eating disorder, which are co-morbid with a high body mass index (BMI). Methods: In total, 50 participants were randomised to HAPIFED and 48 were randomised to the control cognitive behaviour therapy-enhanced group. Assessments included mental health-related quality of life (MHRQoL), eating disorder symptom severity, binge-eating frequency, BMI, and loss of control over eating (LOCE) at baseline, mid-treatment, end-treatment, and 6 and 12 months end of follow-up (EndFU). These were measured with the SF-12, the EDE-Q, and the LOCES, respectively. Linear and negative binomial mixed models were used. Missing data were imputed multiple times, assuming intention of treatment for the analysis. Results: Pre-treatment eating disorder symptom severity, MHRQoL, and BMI positively predicted eating disorder symptom severity, MHRQoL, and BMI up to 6 and 12 months end of follow-up. Mid-treatment LOCE MTLOCE predicted improved MHRQoL (coefficient = 0.387, 95% CI 0.0824-0.6921, p = 0.004), reduced binge-eating frequency (IRR = 0.5637, 95% CI 0.3539-0.8977, p = 0.0191), and eating disorder symptom severity (coefficient= -0.65, 95% CI -1.0792--0.2217, p = 0.0139). Neither purging nor illness duration were a significant predictor of any of the outcomes. The effect of HAPIFED was not moderated by baseline weight/BMI but was moderated negatively by MTLOCE for binge-eating frequency (coefficient = -0.636, SE = 0.28, p < 0.05, IRR = 0.529) and eating disorder symptom severity (coefficient = -0.268, SE = 0.13, p < 0.05, Cohen's d = -0.102). Conclusions: Greater control over eating improved MHRQoL and decreased the frequency of binge-eating episodes and eating disorder symptom severity. These positive effects were moderated by being in the HAPIFED group, supporting previous findings of benefits to people's mental health through participation in the HAPIFED trial.

Keywords: eating disorders; loss of control; mid-therapy; moderators; overeating; predictors.