Eating Disorder Neuroimaging Initiative (EDNI): a multicentre prospective cohort study protocol for elucidating the neural effects of cognitive-behavioural therapy 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.

Systematic reduction of gray matter volume in anorexia nervosa, but relative enlargement with clinical symptoms in the prefrontal and posterior insular cortices: a multicenter neuroimaging study

Although brain morphological abnormalities have been reported in anorexia nervosa (AN), the reliability and reproducibility of previous studies were limited due to insufficient sample sizes, which prevented exploratory analysis of the whole brain as opposed to regions of interest (ROIs). Objective was to identify brain morphological abnormalities in AN and the association with severity of AN by brain structural magnetic resonance imaging (MRI) in a multicenter study, and to conduct exploratory analysis of the whole brain. Here, we conducted a cross-sectional multicenter study using T1-weighted imaging (T1WI) data collected between May 2014 and February 2019 in Japan. We analyzed MRI data from 103 female AN patients (58 anorexia nervosa restricting type [ANR] and 45 anorexia nervosa binge-purging type [ANBP]) and 102 age-matched female healthy controls (HC). MRI data from five centers were preprocessed using the latest harmonization method to correct for intercenter differences. Gray matter volume (GMV) was calculated from T1WI data of all participants. Of the 205 participants, we obtained severity of eating disorder symptom scores from 179 participants, including 87 in the AN group (51 ANR, 36 ANBP) and 92 HC using the Eating Disorder Examination Questionnaire (EDE-Q) 6.0. GMV reduction were observed in the AN brain, including the bilateral cerebellum, middle and posterior cingulate gyrus, supplementary motor cortex, precentral gyrus medial segment, and thalamus. In addition, the orbitofrontal cortex (OFC), ventromedial prefrontal cortex (vmPFC), rostral anterior cingulate cortex (ACC), and posterior insula volumes showed positive correlations with severity of symptoms. This multicenter study was conducted with a large sample size to identify brain morphological abnormalities in AN. The findings provide a better understanding of the pathogenesis of AN and have potential for the development of brain imaging biomarkers of AN. Trial Registration: UMIN000017456. https://center6.umin.ac.jp/cgi-open-bin/icdr/ctr_view.cgi?recptno=R000019303 .

Comprehensive elucidation of resting-state functional connectivity in anorexia nervosa by a multicenter cross-sectional study

BACKGROUND

Previous research on the changes in resting-state functional connectivity (rsFC) in anorexia nervosa (AN) has been limited by an insufficient sample size, which reduced the reliability of the results and made it difficult to set the whole brain as regions of interest (ROIs).

METHODS

We analyzed functional magnetic resonance imaging data from 114 female AN patients and 135 healthy controls (HC) and obtained self-reported psychological scales, including eating disorder examination questionnaire 6.0. One hundred sixty-four cortical, subcortical, cerebellar, and network parcellation regions were considered as ROIs. We calculated the ROI-to-ROI rsFCs and performed group comparisons.

RESULTS

Compared to HC, AN patients showed 12 stronger rsFCs mainly in regions containing dorsolateral prefrontal cortex (DLPFC), and 33 weaker rsFCs primarily in regions containing cerebellum, within temporal lobe, between posterior fusiform cortex and lateral part of visual network, and between anterior cingulate cortex (ACC) and thalamus (p < 0.01, false discovery rate [FDR] correction). Comparisons between AN subtypes showed that there were stronger rsFCs between right lingual gyrus and right supracalcarine cortex and between left temporal occipital fusiform cortex and medial part of visual network in the restricting type compared to the binge/purging type (p < 0.01, FDR correction).

CONCLUSION

Stronger rsFCs in regions containing mainly DLPFC, and weaker rsFCs in regions containing primarily cerebellum, within temporal lobe, between posterior fusiform cortex and lateral part of visual network, and between ACC and thalamus, may represent categorical diagnostic markers discriminating AN patients from HC.

Machine learning research based on diffusion tensor images to distinguish between anorexia nervosa and bulimia nervosa

Background

Anorexia nervosa (AN) and bulimia nervosa (BN), two subtypes of eating disorders, often present diagnostic challenges due to their overlapping symptoms. Machine learning has proven its capacity to improve group classification without requiring researchers to specify variables. The study aimed to distinguish between AN and BN using machine learning models based on diffusion tensor images (DTI).

Methods

This is a cross-sectional study, drug-naive females diagnosed with anorexia nervosa (AN) and bulimia nervosa (BN) were included. Demographic data and DTI were collected for all patients. Features for machine learning included Fractional anisotropy (FA), axial diffusivity (AD), radial diffusivity (RD), and mean diffusivity (MD). Support vector machine was constructed by LIBSVM, MATLAB2013b, and FSL5.0.9 software.

Results

A total of 58 female patients (24 AN, 34 BN) were included in this study. Statistical analysis revealed no significant differences in age, years of education, or course of illness between the two groups. AN patients had significantly lower BMI than BN patients. The AD model exhibited an area under the curve was 0.793 (accuracy: 75.86%, sensitivity: 66.67%, specificity: 88.23%), highlighting the left middle temporal gyrus (MTG_L) and the left superior temporal gyrus (STG_L) as differentiating brain regions. AN patients exhibited lower AD features in the STG_L and MTG_L than BN. Machine learning analysis indicated no significant differences in FA, MD, and RD values between AN and BN groups (p > 0.001).

Conclusion

Machine learning based on DTI could effectively distinguish between AN and BN, with MTG_L and STG_L potentially serving as neuroimaging biomarkers.

Potential benefits and limitations of machine learning in the field of eating disorders: current research and future directions

Advances in machine learning and digital data provide vast potential for mental health predictions. However, research using machine learning in the field of eating disorders is just beginning to emerge. This paper provides a narrative review of existing research and explores potential benefits, limitations, and ethical considerations of using machine learning to aid in the detection, prevention, and treatment of eating disorders. Current research primarily uses machine learning to predict eating disorder status from females' responses to validated surveys, social media posts, or neuroimaging data often with relatively high levels of accuracy. This early work provides evidence for the potential of machine learning to improve current eating disorder screening methods. However, the ability of these algorithms to generalise to other samples or be used on a mass scale is only beginning to be explored. One key benefit of machine learning over traditional statistical methods is the ability of machine learning to simultaneously examine large numbers (100s to 1000s) of multimodal predictors and their complex non-linear interactions, but few studies have explored this potential in the field of eating disorders. Machine learning is also being used to develop chatbots to provide psychoeducation and coping skills training around body image and eating disorders, with implications for early intervention. The use of machine learning to personalise treatment options, provide ecological momentary interventions, and aid the work of clinicians is also discussed. Machine learning provides vast potential for the accurate, rapid, and cost-effective detection, prevention, and treatment of eating disorders. More research is needed with large samples of diverse participants to ensure that machine learning models are accurate, unbiased, and generalisable to all people with eating disorders. There are important limitations and ethical considerations with utilising machine learning methods in practice. Thus, rather than a magical solution, machine learning should be seen as an important tool to aid the work of researchers, and eventually clinicians, in the early identification, prevention, and treatment of eating disorders.