Causal discovery analysis: A promising tool in advancing precision medicine for eating disorders

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.

Exploring biologically oriented precision mental health initiatives for the care of patients with eating disorders: A narrative review

OBJECTIVE

Eating disorders (EDs) represent a major public health burden. Increasingly, studies suggest mental health (MH) fields are failing to improve the effectiveness of treatments and that alternative models of care must be considered. Precision mental health (PMH) seeks to tailor treatment to individual needs and relies on a comprehensive understanding of the neurobiological and physiological underpinnings of mental illness.

METHODS

In this narrative review, published literature with focus on biological application of PMH strategies for EDs is reviewed and summarised.

RESULTS

A total of 39 articles were retained for the review covering a variety of themes with relevance to PMH. Many studies of biological markers with PMH applicability focused on anorexia nervosa. Although a variety of potential PMH research applications were identified, the review failed to identify any evidence of implementation into routine ED practice.

CONCLUSIONS

Despite the theoretical merit of biological application of PMH in ED treatment, clinical applications for standard practice are lacking. There is a need to invest further in studies that seek to identify biological markers and investigate neurobiological underpinnings of disease in hopes of targeting and developing treatments that can be better tailored to the individualised needs of patients.

A transdiagnostic and translational framework for delineating the neuronal mechanisms of compulsive exercise in anorexia nervosa

OBJECTIVE

The development of novel treatments for anorexia nervosa (AN) requires a detailed understanding of the biological underpinnings of specific, commonly occurring symptoms, including compulsive exercise. There is considerable bio-behavioral overlap between AN and obsessive-compulsive disorder (OCD), therefore it is plausible that similar mechanisms underlie compulsive behavior in both populations. While the association between these conditions is widely acknowledged, defining the shared mechanisms for compulsive behavior in AN and OCD requires a novel approach.

METHODS

We present an argument that a better understanding of the neurobiological mechanisms that underpin compulsive exercise in AN can be achieved in two critical ways. First, by applying a framework of the neuronal control of OCD to exercise behavior in AN, and second, by taking better advantage of the activity-based anorexia (ABA) rodent model to directly test this framework in the context of feeding pathology.

RESULTS

A cross-disciplinary approach that spans preclinical, neuroimaging, and clinical research as well as compulsive neurocircuitry and behavior can advance our understanding of when, why, and how compulsive exercise develops in the context of AN and provide targets for novel treatment strategies.

DISCUSSION

In this article, we (i) link the expression of compulsive behavior in AN and OCD via a transition between goal-directed and habitual behavior, (ii) present disrupted cortico-striatal circuitry as a key substrate for the development of compulsive behavior in both conditions, and (iii) highlight the utility of the ABA rodent model to better understand the mechanisms of compulsive behavior relevant to AN.

PUBLIC SIGNIFICANCE

Individuals with AN who exercise compulsively are at risk of worse health outcomes and have poorer responses to standard treatments. However, when, why, and how compulsive exercise develops in AN remains inadequately understood. Identifying whether the neural circuitry underlying compulsive behavior in OCD also controls hyperactivity in the activity-based anorexia model will aid in the development of novel eating disorder treatment strategies for this high-risk population.