Conducting Eating Disorder Research in the Era of Generative AI: Researcher Perspectives and Guidelines From the International Journal of Eating Disorders.

Objectives: Generative Artificial Intelligence (AI) could transform how science is conducted, supporting researchers with writing, coding, peer review, and evidence synthesis. However, it is not yet known how eating disorder researchers utilize generative AI, and uncertainty remains regarding its safe, ethical, and transparent use. The Executive Committee of the International Journal of Eating Disorders disseminated a survey for eating disorder researchers investigating their practices and perspectives on generative AI, with the goal of informing guidelines on appropriate AI use for authors, reviewers, and editors.

Absolute and relative rates of treatment non-initiation, dropout, and attrition in internet-based and face-to-face cognitive-behavioral therapy: a meta-analysis of randomized controlled trials.

Internet-based cognitive-behavioral therapy (ICBT) appears to produce comparable clinical benefits to face-to-face CBT. However, whether these two CBT modalities are equally accepted by patients remains unclear. We conducted a meta-analysis examining absolute and relative rates of treatment non-initiation, dropout, and attrition in ICBT and face-to-face CBT.

Looking beyond depression: meta-analysis of digital interventions for depression on eleven secondary mental health and wellbeing outcomes.

Prior meta-analyses show that digital interventions for depression can effectively reduce primary symptoms. However, it remains unclear whether these digital interventions provide broader benefits beyond symptom reduction. Randomized controlled trials (RCTs) of digital depression interventions typically assess a wide range of secondary outcomes, but no study has aggregated these using meta-analytic techniques to quantify the interventions' broader impacts.

Transdiagnostic-focused apps for depression and anxiety: a meta-analysis.

Mental health apps that adopt a transdiagnostic approach to addressing depression and anxiety are emerging, yet a synthesis of their evidence-base is missing. This meta-analysis evaluated the efficacy of transdiagnostic-focused apps for depression and anxiety, and aimed to understand how they compare to diagnostic-specific apps. Nineteen randomized controlled trials (N = 5165) were included.

Role of large language models in mental health research: an international survey of researchers' practices and perspectives.

Background: Large language models (LLMs) offer significant potential to streamline research workflows and enhance productivity. However, limited data exist on the extent of their adoption within the mental health research community.

Objective: We examined how LLMs are being used in mental health research, the types of tasks they support, barriers to their adoption and broader attitudes towards their integration.

Applying models of self-regulated learning to understand engagement with digital health interventions: a narrative review.

Digital health interventions (DHIs) are often burdened by poor user engagement and high drop-out rates, diminishing their potential public health impact. Identifying user-related factors predictive of engagement has therefore drawn significant research attention in recent years. Absent from this literature-yet implied by DHI design-is the notion that individuals who use DHIs have well-regulated learning capabilities that facilitate engagement with unguided intervention content.

Smartphone monitoring and digital phenotyping apps for schizophrenia: A review of the academic literature.

Background: Monitoring-based applications are increasingly administered in mental health research to detect relapses and track symptoms by using digital phenotyping. This review systematically examines unique datasets generated from unique apps for schizophrenia-spectrum disorders, including identifying patterns in study design, sample size, duration, comparison groups, device usage, incentives, and eligibility criteria.

Methods: In January 2025, we conducted a systematic review with a narrative/qualitative synthesis of research for schizophrenia-related apps and coded them for demographics, eligibility, outcomes and experiences, engagement and features, and app availability.

Integrating Artificial Intelligence and Smartphone Technology to Enhance Personalized Assessment and Treatment for Eating Disorders.

Objective: Smartphone technology presents a promising path toward expanding access to evidence-based eating disorder assessment and treatment. Despite rapid technological advances, research has yet to harness these systems in ways that make personalized digital health care a clinical reality. In this forum, we review extant research testing smartphone intervention and monitoring tools for eating disorders and explore innovative ways integrating this technology with AI can enhance assessment, symptom detection, and intervention efforts.

Acceptability and Efficacy of a Web-Based, Intuitive Eating-Focused Single Session Intervention for Recurrent Binge Eating: A Randomized Controlled Trial.

Objective: Intuitive eating is a viable intervention target for binge eating, yet current programs designed to cultivate this pattern of eating face challenges with scalability and accessibility. We developed a web-based, intuitive eating-focused, single-session intervention (SSI) and evaluated its acceptability and efficacy among individuals with recurrent binge eating.

Method: Two-hundred-forty-eight participants reporting recurrent binge eating were randomly assigned to the SSI or a waitlist.

The evolving field of digital mental health: current evidence and implementation issues for smartphone apps, generative artificial intelligence, and virtual reality.

The expanding domain of digital mental health is transitioning beyond traditional telehealth to incorporate smartphone apps, virtual reality, and generative artificial intelligence, including large language models. While industry setbacks and methodological critiques have highlighted gaps in evidence and challenges in scaling these technologies, emerging solutions rooted in co-design, rigorous evaluation, and implementation science offer promising pathways forward. This paper underscores the dual necessity of advancing the scientific foundations of digital mental health and increasing its real-world applicability through five themes.

Delivery formats of cognitive behavior therapy in adults with eating disorders: a network meta-analysis.

Although CBT has been found to be effective in the treatment of eating disorders, it is not clear if there are differences between treatment formats. We conducted a network meta-analysis (NMA) of randomized trials of broadly defined CBT comparing individual, group, guided self-help (GSH) and unguided self-help (USH) with each other or with a control condition. The NMA used a frequentist graph-theoretical approach and included 36 trials (53 comparisons; 3,136 participants).

Predicting responsiveness to a dialectical behaviour therapy skills training app for recurrent binge eating: A machine learning approach.

Objective: Smartphone applications (apps) show promise as an effective and scalable intervention modality for disordered eating, yet responsiveness varies considerably. The ability to predict user responses to app-based interventions is currently limited. Machine learning (ML) techniques have shown potential to improve prediction of complex clinical outcomes.

Cognitive Behavior Therapy for Mental Disorders in Adults: A Unified Series of Meta-Analyses.

Importance: Cognitive behavior therapy (CBT) is a first-line treatment for most mental disorders. However, no meta-analytic study has yet integrated the results of randomized clinical trials on CBT across different disorders, using uniform methodologies and providing a complete overview of the field.

Objective: To examine the effect sizes of CBT for 4 anxiety disorders, 2 eating disorders, major depression, obsessive-compulsive disorder (OCD), posttraumatic stress disorder (PTSD), and psychotic and bipolar disorders on symptoms of the respective disorders using uniform methodologies for data extraction, risk of bias (RoB) assessment, and meta-analytic techniques.

Self-Guided Psychological Interventions for the Treatment and Prevention of Eating Disorders: A Meta-Analysis of Randomized Controlled Trials.

Background: Self-guided interventions may broaden the dissemination of evidence-based prevention and treatment protocols for eating disorders. We conducted a meta-analysis comparing self-guided prevention and treatment approaches for eating disorders to (1) control groups and (2) professionally guided self-help programs.

Methods: Forty-six trials were included.

Methodological quality in randomised clinical trials of mental health apps: systematic review and longitudinal analysis.

Question: This study investigated the methodological rigour of randomised controlled trials (RCTs) of mental health apps for depression and anxiety, and whether quality has improved over time.

Study Selection And Analysis: RCTs were drawn from the most recent meta-analysis of mental health apps for depression and anxiety symptoms. 20 indicators of study quality were coded, encompassing risk of bias, participant diversity, study design features and app accessibility measures.

Smartphone digital phenotyping in mental health disorders: A review of raw sensors utilized, machine learning processing pipelines, and derived behavioral features.

With increased access to digital technology, there has been a surge in the use of and interest in digital phenotyping as a tool to calculate various features from raw smart device data. However, the increased usage of digital phenotyping has created confusion. The vast number of sensors that can be utilized to collect passive data, and diverse methods utilized to convert that sensor data into features has introduced conflicting results and conclusions into the literature.

Predictors of functionality appreciation: Prospective findings.

Research indicates that functionality appreciation, a core facet of positive body image, may protect against eating disorder symptoms and body image disturbances. However, there is still limited knowledge about what factors determine functionality appreciation over time, as longitudinal research designed to identify such predictors is absent. In light of theoretical and empirical research linking intuitive eating, symptoms of disordered eating (i.

Mental Health Impacts of Self-Help Interventions for the Treatment and Prevention of Eating Disorders. A Meta-Analysis.

Objective: Self-help programs are recommended as a first step in the management of eating disorders. Yet, whether self-help interventions have broader mental health benefits beyond symptom and risk reduction remains unclear. As randomized controlled trials (RCTs) also assess general mental health secondary to eating disorder symptoms, we conducted a meta-analysis to investigate whether and to what extent pure self-help interventions for eating disorders produce improvements in these secondary outcomes.

Mental health clinicians' practices and perspectives of eating disorder apps.

Smartphone apps have the potential to play an integral role in the management of eating disorders. However, despite evidence of efficacy, apps have yet to be widely adopted and integrated into clinical practice. This study sought to understand mental health clinicians' practices and perspectives of eating disorder apps.

Using Artificial Intelligence to Advance Eating Disorder Research, Treatment and Practice.

Artificial intelligence (AI) has the potential to revolutionize eating disorder research, treatment, and practice by assisting with complex problems such as predicting illness prognosis, supporting diagnostic decisions, tailoring treatment plans, and even data analysis and study design choices. Yet, research on the applications of AI in eating disorders remains limited. This editorial discusses the importance of AI, explores practical applications, and outlines key directions for future research.

The impact of patient choice on uptake, adherence, and outcomes across depression, anxiety, and eating disorders: a systematic review and meta-analysis.

Growing evidence highlights the critical role of patient choice of treatment, with significant benefits for outcomes found in some studies. While four meta-analyses have previously examined the association between treatment choice and outcomes in mental health, robust conclusions have been limited by the inclusion of studies with biased preference trial designs. The current systematic review included 30 studies across three common and frequently comorbid mental health disorders (depression  = 23; anxiety,  = 5; eating disorders,  = 2) including 7055 participants ( 42.

Current Practices and Perspectives of Artificial Intelligence in the Clinical Management of Eating Disorders: Insights From Clinicians and Community Participants.

Objective: Artificial intelligence (AI) could revolutionize the delivery of mental health care, helping to streamline clinician workflows and assist with diagnostic and treatment decisions. Yet, before AI can be integrated into practice, it is necessary to understand perspectives of these tools to inform facilitators and barriers to their uptake. We gathered data on clinician and community participant perspectives of incorporating AI in the clinical management of eating disorders.

Systematic review and meta-analysis of adverse events in clinical trials of mental health apps.

Mental health apps are efficacious, yet they may pose risks in some. This review (CRD42024506486) examined adverse events (AEs) from mental health apps. We searched (May 2024) the Medline, PsycINFO, Web of Science, and ProQuest databases to identify clinical trials of mental health apps.

A dialectical behavior therapy skills training smartphone app for recurrent binge eating: a randomized clinical trial.

Background: Dialectical behavior therapy (DBT) is a specialized treatment that has a growing evidence base for binge-spectrum eating disorders. However, cost and workforce capacity limit wide-scale uptake of DBT since it involves over 20 in-person sessions with a trained professional (and six sessions for guided self-help format). Interventions translated for delivery through modern technology offer a solution to increase the accessibility of evidence-based treatments.

Application of Machine Learning Techniques to the Prediction of Onset and Persistence of Binge Eating: A Prospective Study.

Objective: Machine learning (ML) techniques have shown promise for enhancing prediction of clinical outcomes; however, its application to predicting binge eating has been scarcely explored. We applied ML techniques to predict binge eating onset (vs. continued absence) and persistence (vs.