The most widely researched treatment for bulimia nervosa (BN) and binge-eating disorder (BED) is cognitive behavioral therapy (CBT), a present-focused, active, skill-oriented treatment. However, despite the success of CBT, many patients fail to achieve sufficient rates of skill utilization (i.e., the frequency with which a patient practices or uses therapeutic skills) or adequate skill acquisition (i.e., the ability to successfully perform a skill learned in treatment) by the end of treatment and outcomes suffer as a result. One method for improving skill acquisition and utilization in patients with BN or BED could be the augmentation of in-person treatment with just-in-time adaptive interventions (JITAIs), which use smartphone technology to deliver real-time interventions during app-identified moments of need. The current article discusses how novel JITAI systems that utilize machine learning or other predictive algorithms could be used to detect momentary risk for eating disordered behavior and provide tailored interventions to enhance outcomes. We will consider technologies that may help reduce patient burden and suggest avenues for future research on developing acceptable and effective JITAIs that can be used as an adjunct to CBT protocols.

No abstract

No abstract