Review of machine learning solutions for eating disorders.

BACKGROUND: Eating Disorders (EDs) are one of the most complex psychiatric disorders, with significant impairment of psychological and physical health, and psychosocial functioning, and are associated with low rates of early detection, low recovery and high relapse rates. This underscores the need for better diagnostic and treatment methods. OBJECTIVE: This narrative review explores current Machine Learning (ML) and Artificial Intelligence (AI) applications in the domain of EDs, with a specific emphasis on clinical management in treatment settings. The primary objective are to (i) decrease the knowledge gap between ED researchers and AI-practitioners, by presenting the current state-of-the-art AI applications (including models for causality) in different ED use-cases; (ii) identify limitations of these existing AI interventions and how to address them. RESULTS: AI/ML methods have been applied in different ED use-cases, including ED risk factor identification and incidence prediction (including the analysis of social media content in the general population), diagnosis, monitoring patients and treatment response and prognosis in clinical populations. A comparative analysis of AI-techniques deployed in these use-cases have been performed, considering factors such as complexity, flexibility, functionality, explainability and adaptability to healthcare constraints. CONCLUSION: Multiple restrictions have been identified in the existing methods in ML and Causality in terms of achieving actionable healthcare for ED, like lack of good quality and quantity of data for models to train on, while requiring models to be flexible, high-performing, yet being explainable and producing counterfactual explanations, for ensuring the fairness and trustworthiness of its decisions. We conclude that to overcome these limitations and for future AI research and application in clinical management of ED, (i) careful considerations are required with regards to AI-model selection, and (ii) joint efforts from ED researcher and patient community are essential in building better quality and quantity of dedicated ED datasets and secure AI-solution framework.

Is a dissonance-based group intervention targeting thin-ideal internalization a successful potential add-on for specialized eating disorder care? A randomized feasibility and acceptability pilot study.

BACKGROUND: Dissonance-based eating disorder programs have successfully targeted body dissatisfaction by challenging the thin beauty ideal in the preventive context and in groups of patients with a subthreshold and full threshold DSM-5 eating disorder. As there is a need for interventions specifically targeting thin-ideal internalization in (highly) specialized treatment centres, the present study adapted Stice's et al.'s Body Project for its use as an add-on treatment for severe eating disorders with the aims to identify whether it was feasible and acceptable in this treatment context, to determine any necessary modifications with regard to the treatment and study procedures, and to test preliminary effectiveness. METHODS: The study was a randomized controlled pilot/feasibility trial. Thirty patients started in the Body Project group and 25 in the Psycho-education group. Measurements took place pre- and post-intervention, and at three and six months follow-up. Patients and staff evaluated treatment and study procedures, and patients completed questionnaires on thin-ideal internalization, body dissatisfaction, self-objectification, negative affect and eating disorder pathology. RESULTS: The Body Project group and Psycho-education group both proved highly feasible and acceptable, as well as preliminarily effective, based on quantitative scores and qualitative feedback. Preliminary analyses showed that treatment effects did not differ between treatment groups. As both groups were an add-on to standard treatment, treatment effects cannot be disentangled from effects resulting from standard treatment. Qualitative feedback for the Body Project group included several recommendations for future implementation: increasing the number of treatment sessions, creating homogeneous therapy groups, and optimizing timing of the treatment. CONCLUSIONS: Future research should examine further modifications to the Body Project group for severe eating disorders, as well as for whom, and when in the course of treatment the intervention is most effective. The present study also showed the benefits of implementing a structured Psycho-education group. We tested the feasibility and acceptability of a group intervention targeting the thin beauty ideal (Body Project group) in patients with severe eating disorders and compared this intervention to a group intervention focusing on psycho-education about eating disorders (Psycho-education group). Both interventions were added to standard treatment. We adapted the protocol for patients with severe eating disorders. Both the Body Project group and the Psycho-education group were evaluated by patients as well as staff as highly feasible and acceptable, and effects were positive. Treatment effects did not differ between treatment groups. As both treatments were an add-on to standard treatment, treatment effects cannot be disentangled from effects resulting from standard treatment. The study suggested further modifications to the Body Project group. Future research should examine these modifications as well as for whom, and when in the course of treatment the intervention is most effective. The present study also showed the benefits of implementing a structured Psycho-education group.

Anorexia nervosa and COVID-19 infection: Clinical case report.

The true risk of COVID-19 infection in anorexia nervosa (AN) including the duration of viral RNA shedding and infectivity is still unclear. We report on a case of a patient with severe AN with a mild course of COVID-19 and prolonged viral RNA shedding for at least 39 days after symptom onset. A careful evaluation of long-term infectivity must include viral load, live virus isolation, and viral genome sequencing.

COVID-19, anorexia nervosa and obese patients with an eating disorder - some considerations for practitioners and researchers.

Since COVID-19 is a global health emergency, there is an urgent need to share experiences on decision-making with regard to safety recommendations and for hypotheses that can inform a more focused prevention and treatment. Moreover, combining research into eating disorders and obesity with research into COVID-19 may provide a unique opportunity to shed light on the susceptibility to COVID-19.

Anorexia nervosa and uric acid beyond gout: An idea worth researching.

Uric acid is best known for its role in gout-the most prevalent inflammatory arthritis in humans-that is also described as an unusual complication of anorexia nervosa (AN). However, beyond gout, uric acid could also be involved in the pathophysiology and psychopathology of AN, as it has many biological functions serving as a pro- and antioxidant, neuroprotector, neurostimulant, and activator of the immune response. Further, recent research suggests that uric acid could be a biomarker of mood dysfunction, personality traits, and behavioral patterns. This article discusses the hypothesis that uric acid in AN may not be a mere innocent bystander determined solely by AN behavior and its medical complications. In contrast, the relation between uric acid and AN may have evolutionary origin and may be reciprocal, where uric acid regulates some features and pathophysiological processes of AN, including weight and metabolism regulation, oxidative stress, immunity, mood, cognition, and (hyper)activity.

Sociocultural factors in the development of bulimia nervosa in a blind woman: a case report.

BACKGROUND: Although several cases of eating disorders in visually impaired women have been reported, there has been little research on the development of body image and disordered eating in the blind. Overall, it is argued that blind women are protected from developing body dissatisfaction because of having had little or no exposure to thin-ideal images, and that if they do develop an eating disorder, this would be linked to other risk factors. In the one reported case of bulimia nervosa in a blind woman, body image concerns were even absent. METHOD: We report a single case of bulimia nervosa in a 28-year-old congenitally blind woman whose presentation was typical, including body dissatisfaction and drive for thinness. DISCUSSION: The present case underscores the need to also consider an etiological role of perceived sociocultural pressure and thin-ideal internalization in promoting body dissatisfaction and eating disorders in visually impaired women.