Pre-treatment predictors of attrition in a randomised controlled trial of psychological therapy for severe and enduring anorexia nervosa

Background: Attrition is common in the treatment of anorexia nervosa and its causes are complex and incompletely understood. In particular, its relationship with adaptive function and motivational stage of change has been little studied. This study aimed to (1) investigate and (2) compare the strength of associations between adaptive function, stage of change and other previously found factors such as illness sub-type and treatment attrition in women with severe and enduring anorexia nervosa (SE-AN). Methods: Participants were 63 adult women with SE-AN of at least 7 years duration who were enrolled in a multi-site randomized controlled trial conducted from July 2007 through June 2011. Treatment comprised 30 outpatient visits over 8 months of either Cognitive Behaviour Therapy for Anorexia Nervosa (CBT-AN) or Specialist Supportive Clinical Management (SSCM) both of which were modified for severe and enduring illness. Assessments were done at baseline, end of treatment, and 6 and 12 month post treatment follow-up. Demographic variables, duration of illness, specific and generic health related quality of life (QoL), eating disorder (ED) and mood disorder symptoms, social adjustment, body mass index (BMI), and motivation for change were assessed with interview and self-report questionnaires. Treatment attrition was defined as leaving therapy after either premature termination according to trial protocol or self-instigated discharge. Binary logistic regression was used to investigate relative strength of associations. Results: Those who did not complete treatment were significantly more likely to have the purging sub-type of anorexia nervosa and poorer ED related QoL. There were no significant differences between attrition and which therapy was received, educational level, and global ED psychopathology, stage of change, BMI, social adjustment, duration of illness or level of depression. The strongest predictors on multivariable analysis were ED QoL and AN-purging subtype. Conclusion: This study supported previous findings of associations between attrition and purging subtype. Furthermore, we found associations between a potentially important cycle of attrition, and poorer EDQoL, which has not been previously reported. Contrary to expectations we did not find an association with BMI, severity of ED symptoms, low level of motivation to change ED features, or level of education.