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

Abstract

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.

Predictors, mediators, and moderators of response to digital interventions for eating disorders: A systematic review

“…A growing body of literature has demonstrated the advantages of ML over traditional techniques for predicting prognosis and treatment outcomes across a range of psychiatric conditions including depression (Chekroud et al, 2016), obsessive-compulsive disorder (Lenhard et al, 2018), schizophrenia (Min et al, 2020), and social anxiety disorder (Månsson et al, 2015). However, the use of ML in ED research is still in its infancy (Fardouly et al, 2022), thus we encourage future research to also consider exploring whether ML may be used to enhance our ability to predict outcomes of digital interventions for EDs. To facilitate optimal ML performance, we encourage researchers to collaborate by pooling multiple datasets from clinical trials, as larger datasets generally produce more precise prediction models.…”

Machine Learning and Pharmacogenomics at the Time of Precision Psychiatry

“…ML provides exciting potential for detecting, preventing, and treating psychiatric disorders. However, many factors limit its current use in research and practice [ 61 - 63 ]. Data is arguably the most apparent constraint in developing ML models for diagnosing and treating psychiatric disorders [ 61 ].…”

“…However, many factors limit its current use in research and practice [ 61 - 63 ]. Data is arguably the most apparent constraint in developing ML models for diagnosing and treating psychiatric disorders [ 61 ]. In psychiatry, we do not have the comfort of rich numerical datasets such as those available in intensive care units.…”

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

“…Moreover, machine learning has demonstrated its capacity to enhance group classification without the need for researchers to specify variables ( 14 ). While still at an early stage in the study of ED, machine learning has emerged as an advanced computational too ( 15 , 16 ). Cerasa et al applied the support vector machine (SVM) technique to distinguish individuals with eating disorders from healthy controls (HCs), achieving a diagnostic accuracy of 0.80 in a small sample of ED vs. HCs ( 17 ).…”