Using machine learning to explore core risk factors associated with the risk of eating disorders among non-clinical young women in China: A decision-tree classification analysis

Machine learning models for diagnosis and risk prediction in eating disorders, depression, and alcohol use disorder

This study uses machine learning models to uncover diagnostic and risk prediction markers for eating disorders (EDs), major depressive disorder (MDD), and alcohol use disorder (AUD). Utilizing case-control samples (ages 18-25 years) and a longitudinal population-based sample (n=1,851), the models, incorporating diverse data domains, achieved high accuracy in classifying EDs, MDD, and AUD from healthy controls. The area under the receiver operating characteristic curves (AUC-ROC [95% CI]) reached 0.92 [0.86-0.97] for AN and 0.91 [0.85-0.96] for BN, without relying on body mass index as a predictor. The classification accuracies for MDD (0.91 [0.88-0.94]) and AUD (0.80 [0.74-0.85]) were also high. Each data domain emerged as accurate classifiers individually, with personality distinguishing AN, BN, and their controls with AUC-ROCs ranging from 0.77 to 0.89. The models demonstrated high transdiagnostic potential, as those trained for EDs were also accurate in classifying AUD and MDD from healthy controls, and vice versa (AUC-ROCs, 0.75-0.93). Shared predictors, such as neuroticism, hopelessness, and symptoms of attention-deficit/hyperactivity disorder, were identified as reliable classifiers. For risk prediction in the longitudinal population sample, the models exhibited moderate performance (AUC-ROCs, 0.64-0.71), highlighting the potential of combining multi-domain data for precise diagnostic and risk prediction applications in psychiatry.

Association between Body Image Flexibility and Intermittent Fasting in Chinese Medical Students: A Cross-Sectional Study

Unhealthy dietary behaviors and body dissatisfaction are becoming increasingly common among college students. Understanding the association between body image flexibility and intermittent fasting is particularly meaningful, especially for medical college students. This study aimed to investigate the association between body image flexibility and intermittent fasting among medical students. We conducted a cross-sectional study with 5138 medical college students at Jitang College of North China University of Science and Technology. Univariate and multivariate logistic regression were used to evaluate the association between body image flexibility and intermittent fasting. Subgroup analysis and interaction tests were further used to examine the possible interaction between body image flexibility and intermittent fasting. In this study, 1329 (25.87%) students had intermittent fasting behavior. After adjustment for confounding factors, there was a negative association between body image flexibility and intermittent fasting (OR = 0.94, 95%CI = 0.93 to 0.95, p < 0.001). A significant interaction between body image flexibility and intermittent fasting was found in gender, academic year, major, and monthly living expenses (p for interaction < 0.05). E-value analysis suggested there was unlikely to be an unmeasured confounding. This association could contribute to the establishment of personalized health intervention strategies and provide recommendations for promoting the physical and mental health of medical students.

When Eating Intuitively Is Not Always a Positive Response: Using Machine Learning to Better Unravel Eaters Profiles

BACKGROUND

The aim of the present study was to identify eaters profiles using the latest advantages of Machine Learning approach to cluster analysis.

METHODS

A total of 317 participants completed an online-based survey including self-reported measures of body image dissatisfaction, bulimia, restraint, and intuitive eating. Analyses were conducted in two steps: (a) identifying an optimal number of clusters, and (b) validating the clustering model of eaters profile using a procedure inspired by the Causal Reasoning approach.

RESULTS

This study reveals a 7-cluster model of eaters profiles. The characteristics, needs, and strengths of each eater profile are discussed along with the presentation of a continuum of eaters profiles.

CONCLUSIONS

This conceptualization of eaters profiles could guide the direction of health education and treatment interventions targeting perceptual and eating dimensions.

Psychometric properties of an Arabic translation of the Inflexible Eating Questionnaire (IEQ) in a non-clinical sample of adults

BACKGROUND

The Inflexible Eating Questionnaire (IEQ) is an 11-item instrument designed to evaluate the behavioural and psychological components of inflexible eating. However, the psychometric properties of the instrument have been infrequently examined, and no previous work has examined its utility in the context of the Middle East.

METHODS

A total of 826 Lebanese citizens and residents completed a novel Arabic translation of the IEQ, as well as previously validated measures of body appreciation, functionality appreciation, and disordered eating.

RESULTS

The unidimensional factor structure of the IEQ was upheld through both exploratory and confirmatory factor analyses, with all 11 items retained. We obtained evidence of scalar invariance across gender and found that there were no significant differences in observed IEQ scores between men and women. IEQ scores were also found to have adequate composite reliability and adequate patterns of concurrent validity.

CONCLUSION

The present findings provide support for the psychometric properties of the Arabic version of the IEQ in examining inflexible eating in Arabic-speaking adults in Lebanon. Inflexible or rigid dietary restraint reflects an all-or-none approach that encompasses feeling compelled to obey a set of self-imposed dieting rules (e.g., avoiding high-calorie food, calorie counting, fasting to lose weight and/or skipping meals), having a sense of self-control and feeling empowered when adhering to these rules, and not respecting or following internal/external cues of hunger, satiety, and appetite. Therefore, the inflexible eating construct is composed of two dimensions, the first one is behavioural (i.e., obeying restrictive dietary rules) and the second one is psychological (i.e., the belief that following these rules is a consistent must). Until recently, the measures designed to assess inflexible eating focused on the behavioral dimension, while omitting to account for the psychological processes underlying the construct. To bridge this gap, the Inflexible Eating Questionnaire (IEQ), an 11-item self-report measure, was developed to assess both the behavioural and psychological components of dietary restraint. To date, the IEQ is not yet validated in Arabic. Through the present study, we aimed to examine the psychometric properties of an Arabic translation of the IEQ, which would in turn facilitate improved research and clinical practices related to dietary restraint in Arabic-speaking nations. Overall, findings provided support for the good psychometric qualities of the Arabic version of the IEQ, which suggests its utility for detecting inflexible eating in Arabic-speaking adults.

Exploring the links between celebrity worship, body dissatisfaction, and disordered eating among young adult celebrity worshippers in China

Considerable evidence exists on the associations of celebrity worship with body dissatisfaction and disordered eating. However, relevant findings are confined to Western contexts and thinness-oriented body dissatisfaction and disordered eating. Consequently, the relationships of celebrity worship with muscularity-oriented body dissatisfaction and disordered eating are largely underexplored, especially in non-Western countries. Thus, the present study aimed to examine the relationships of celebrity worship with body dissatisfaction and disordered eating in China. A total of 593 young adult celebrity worshippers in China were recruited online. Correlation and mediation analyses were conducted. In contrast to previous findings, celebrity worship was not associated with thinness-oriented body dissatisfaction. However, significant associations were identified between celebrity worship and muscularity-oriented body dissatisfaction for men (r = 0.32, p < .001) and women (r = 0.26, p < .001), thinness-oriented disordered eating for men (r = 0.31, p < .001) and women (r = 0.37, p < .001), and muscularity-oriented disordered eating for men (r = 0.58, p < .001). Body image inflexibility mediated the associations between celebrity worship and disordered eating in men and women. Findings indicate that celebrity worship correlates positively with body dissatisfaction and disordered eating in Chinese young adults.

Transgender congruence, body appreciation, body dissatisfaction, and disordered eating in Chinese transgender adults

OBJECTIVE

Ample evidence shows that transgender congruence is negatively associated with body dissatisfaction and disordered eating in the Western context; however, limited research has explored these relationships in non-Western populations (e.g., Chinese transgender adults). Moreover, to our knowledge, there has been no research describing disordered eating in Chinese transgender adults. Thus, this study aimed to explore group differences in and relationships between transgender congruence, body appreciation, body dissatisfaction, and disordered eating in Chinese transgender adults.

METHODS

This study examined transgender congruence, body appreciation, body dissatisfaction, and disordered eating in a sample of Chinese transgender adults (N = 200). Chi-square, F tests, and correlation analyses were conducted to examine group differences and relationships between study variables.

RESULTS

Of the transgender adults, 31.0% screened positive as probable eating disorder (ED) cases. There were no gender identity differences in the study variables. Transgender congruence was positively associated body appreciation (r = .40, p < .001) and negatively associated with body dissatisfaction (r = -.26, p < .001) and disordered eating (r = -.15, p = .031).

DISCUSSION

Chinese transgender adults may be at high risk of EDs. Transgender congruence and body appreciation may serve a protective role in the context of eating pathology in Chinese transgender adults. Future research is needed to validate the observed relationships between transgender congruence, body appreciation, body dissatisfaction, and disordered eating in Chinese transgender adults.

PUBLIC SIGNIFICANCE

Research on disordered eating and body image in Chinese transgender adults is limited. This study describes disordered eating and its relations with transgender congruence, body appreciation, and body dissatisfaction in Chinese transgender adults. Findings highlight the need for and implications of ED intervention in Chinese transgender adults.

Prevention of eating disorders: 2022 in review

This review of 17 prevention-related publications in Eating Disorders during 2022 is framed by three models: (1) Mental Health Intervention Spectrum: health promotion ➔ types of prevention ➔ case identification/referral ➔ treatment; (2) the prevention cycle: rationale and theory, shaped by critical reviews ➔ clarifying risk and protective factors ➔ program innovation and feasibility studies ➔ efficacy and effectiveness research ➔ program dissemination; and (3) definitions of and links between disordered eating (DE) and eating disorders (EDs). Five articles fell into the category of prevention rationale, theory, and critical analyses, while seven articles addressed risk factors (RFs) for various aspects of DE. Eating Disorders also published two pilot studies, two prevention efficacy trials, and one effectiveness study in 2022. One implication of the 17 articles reviewed is that RF research toward construction of selective and indicated prevention programs for diverse at-risk groups should address a broad range of factors beyond negative body image and internalization of beauty ideals. Another implication is that, to expand and improve current and forthcoming prevention programs, and to shape effective advocacy for prevention-oriented social policy, the field in general and Eating Disorders in particular need more scholarship in the form of critical reviews and meta-analyses, protective factor research, and case studies of multi-step activism at the local, state (province, region), and national levels.

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.