Hostname: page-component-7f64f4797f-m2b9p Total loading time: 0 Render date: 2025-11-03T08:26:52.826Z Has data issue: false hasContentIssue false
  • English
  • Français

A proof-of-concept study applying machine learning methods to putative risk factors for eating disorders: results from the multi-centre European project on healthy eating

Published online by Cambridge University Press:  29 November 2021

I. Krug Open the ORCID record for I. Krug [Opens in a new window] ,
J. Linardon ,
C. Greenwood ,
G. Youssef ,
J. Treasure ,
F. Fernandez-Aranda ,
A. Karwautz ,
G. Wagner ,
D. Collier  and
M. Anderluh
...Show all authors
I. Krug*
Affiliation:
Melbourne School of Psychological Sciences, The University of Melbourne, Melbourne, VIC, Australia
J. Linardon
Affiliation:
School of Psychology, Deakin University, Geelong, Australia
C. Greenwood
Affiliation:
Centre for Social and Early Emotional Development, Deakin University, Burwood, Australia Centre for Adolescent Health, Murdoch Children's Research Institute, Royal Children's Hospital, Melbourne, VIC, Australia
G. Youssef
Affiliation:
School of Psychology, Deakin University, Geelong, Australia Centre for Adolescent Health, Murdoch Children's Research Institute, Royal Children's Hospital, Melbourne, VIC, Australia
J. Treasure
Affiliation:
Department of Psychological Medicine, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
F. Fernandez-Aranda
Affiliation:
Eating Disorders Unit, Department of Psychiatry, University Hospital of Bellvitge, Barcelona, Spain Consorcio CIBER, Fisiopatología de la Obesidad y Nutrición (CIBERObn), Instituto de Salud Carlos III (ISCIII), Madrid, Spain Department of Clinical Sciences, School of Medicine and Health Sciences, University of Barcelona, Barcelona, Spain Psychiatry and Mental Health Group, Neuroscience Program, Institut d'Investigació Biomèdica de Bellvitge—IDIBELL, L'Hospitalet de Llobregat, Spain
A. Karwautz
Affiliation:
Department of Child and Adolescent Psychiatry, Medical University of Vienna, Vienna, Austria
G. Wagner
Affiliation:
Department of Child and Adolescent Psychiatry, Medical University of Vienna, Vienna, Austria
D. Collier
Affiliation:
SGDP Centre, Institute of Psychiatry, Psychology & Neuroscience, King's College London, De Crespigny Park, Denmark Hill, London, UK Discovery Neuroscience Research, Eli Lilly and Company Ltd, Lilly Research Laboratories, Erl Wood Manor, Surrey, UK
M. Anderluh
Affiliation:
Department of Child Psychiatry, University Children's Hospital, University Medical Center Ljubljana, Ljubljana, Slovenia
K. Tchanturia
Affiliation:
Department of Psychological Medicine, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
V. Ricca
Affiliation:
Department of Neuroscience, Psychology, Drug Research and Child Health, University of Florence, Florence, Italy IRCCS Fondazione Don Carlo Gnocchi, Florence, Italy
S. Sorbi
Affiliation:
Department of Neuroscience, Psychology, Drug Research and Child Health, University of Florence, Florence, Italy IRCCS Fondazione Don Carlo Gnocchi, Florence, Italy
B. Nacmias
Affiliation:
Department of Neuroscience, Psychology, Drug Research and Child Health, University of Florence, Florence, Italy IRCCS Fondazione Don Carlo Gnocchi, Florence, Italy
L. Bellodi
Affiliation:
Department of Neuropsychiatric Sciences, Fondazione Centro San Raffaele del Monte Tabor, Milan, Italy
M. Fuller-Tyszkiewicz
Affiliation:
School of Psychology, Deakin University, Geelong, Australia Centre for Social and Early Emotional Development, Deakin University, Burwood, Australia
*
Author for correspondence: I. Krug, E-mail: isabel.krug@unimelb.edu.au
Get access Rights & Permissions [Opens in a new window]

Abstract

Background

Despite a wide range of proposed risk factors and theoretical models, prediction of eating disorder (ED) onset remains poor. This study undertook the first comparison of two machine learning (ML) approaches [penalised logistic regression (LASSO), and prediction rule ensembles (PREs)] to conventional logistic regression (LR) models to enhance prediction of ED onset and differential ED diagnoses from a range of putative risk factors.

Method

Data were part of a European Project and comprised 1402 participants, 642 ED patients [52% with anorexia nervosa (AN) and 40% with bulimia nervosa (BN)] and 760 controls. The Cross-Cultural Risk Factor Questionnaire, which assesses retrospectively a range of sociocultural and psychological ED risk factors occurring before the age of 12 years (46 predictors in total), was used.

Results

All three statistical approaches had satisfactory model accuracy, with an average area under the curve (AUC) of 86% for predicting ED onset and 70% for predicting AN v. BN. Predictive performance was greatest for the two regression methods (LR and LASSO), although the PRE technique relied on fewer predictors with comparable accuracy. The individual risk factors differed depending on the outcome classification (EDs v. non-EDs and AN v. BN).

Conclusions

Even though the conventional LR performed comparably to the ML approaches in terms of predictive accuracy, the ML methods produced more parsimonious predictive models. ML approaches offer a viable way to modify screening practices for ED risk that balance accuracy against participant burden.

Keywords

Anorexia nervosabulimia nervosaeating disordersmachine learningrisk and protective factors

Information

Type
Original Article
Information
Psychological Medicine , Volume 53 , Issue 7 , May 2023 , pp. 2913 - 2922
Check for updates
Copyright
Copyright © The Author(s), 2021. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Ali, A., Ali, S., Khan, S. A., Khan, D. M., Abbas, K., Khalil, A., … Khalil, U. (2019). Sample size issues in multilevel logistic regression models. PLoS One, 14(11), e0225427. doi: 10.1371/journal.pone.0225427CrossRefGoogle ScholarPubMed
American Psychiatric Association (2000). Diagnostic and statistical manual of mental disorders (4th ed., Text Revision). Washington, DC: American Psychiatric Association.Google Scholar
American Psychiatric Association (2013). Diagnostic and statistical manual of mental disorders (DSM-5®). American Psychiatric Publication.Google Scholar
Bardone-Cone, A. M., Abramson, L. Y., Vohs, K. D., Heatherton, T. F., & Joiner, T. E. (2006). Predicting bulimic symptoms: An interactive model of self-efficacy, perfectionism, and perceived weight status. Behavior Research and Therapy, 44(1), 27–42. doi: 10.1016/j.brat.2004.09.009CrossRefGoogle ScholarPubMed
Bzdok, D., & Meyer-Lindenberg, A. (2018). Machine learning for precision psychiatry: Opportunities and challenges. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, 3(3), 223–230. doi: 10.1016/j.bpsc.2017.11.007Google ScholarPubMed
Chekroud, A. M., Zotti, R. J., Shehzad, Z., Gueorguieva, R., Johnson, M. K., Trivedi, M. H., … Corlett, P. R. (2016). Cross-trial prediction of treatment outcome in depression: A machine learning approach. The Lancet Psychiatry, 3(3), 243–250. doi: 10.1016/S2215-0366(15)00471-XCrossRefGoogle ScholarPubMed
Christodoulou, E., Ma, J., Collins, G. S., Steyerberg, E. W., Verbakel, J. Y., & Van Calster, B. (2019). A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. Journal of Clinical Epidemiology, 110, 12–22. doi: 10.1016/j.jclinepi.2019.02.004CrossRefGoogle ScholarPubMed
Dwyer, D. B., Falkai, P., & Koutsouleris, N. (2018). Machine learning approaches for clinical psychology and psychiatry. Annual Review of Clinical Psychology, 14, 91–118. doi: 10.1146/annurev-clinpsy-032816-045037CrossRefGoogle ScholarPubMed
Easter, A., Naumann, U., Northstone, K., Schmidt, U., Treasure, J., & Micali, N. (2013). A longitudinal investigation of nutrition and dietary patterns in children of mothers with eating disorders. The Journal of Pediatrics, 163(1), 173–178.e171. doi: 10.1016/j.jpeds.2012.11.092CrossRefGoogle ScholarPubMed
Espel-Huynh, H., Zhang, F., Thomas, J. G., Boswell, J. F., Thompson-Brenner, H., Juarascio, A. S., & Lowe, M. R. (2021). Prediction of eating disorder treatment response trajectories via machine learning does not improve performance versus a simpler regression approach. International Journal of Eating Disorders, 54(7), 1250–1259. doi: 10.1002/eat.23510CrossRefGoogle Scholar
Fokkema, M., & Strobl, C. (2020). Fitting prediction rule ensembles to psychological research data: An introduction and tutorial. Psychological Methods, 25(5), 636–652. doi: 10.1037/met0000256CrossRefGoogle ScholarPubMed
Friedman, J., Hastie, T., & Tibshirani, R. (2010). Regularization paths for generalized linear models via coordinate descent. Journal of Statistical Software, 33(1), 1–22. doi: 10.18637/jss.v033.i01CrossRefGoogle ScholarPubMed
Gelman, A. (2008). Scaling regression inputs by dividing by two standard deviations. Statisics in Medicine, 27(15), 2865–2873. doi: 10.1002/sim.3107CrossRefGoogle ScholarPubMed
Goldberg, D. P. (1981). Manual of the General Health Questionnaire (GHQ-28). Swindon, Wiltshire, IK: NFER Nelson Publishing.Google Scholar
Haynos, A. F., Wang, S. B., Lipson, S., Peterson, C. B., Mitchell, J. E., Halmi, K. A., … Crow, S. J. (2020). Machine learning enhances prediction of illness course: A longitudinal study in eating disorders. Psychological Medicine, 51(8), 1392–1402. doi: 10.1017/S0033291720000227CrossRefGoogle ScholarPubMed
Jacobi, C., Hayward, C., de Zwaan, M., Kraemer, H. C., & Agras, W. S. (2004). Coming to terms with risk factors for eating disorders: Application of risk terminology and suggestions for a general taxonomy. Psychological Bulletin, 130(1), 19–65. doi: 10.1037/0033-2909.130.1.19CrossRefGoogle ScholarPubMed
Klump, K. L., Bulik, C. M., Kaye, W. H., Treasure, J., & Tyson, E. (2009). Academy for eating disorders position paper: Eating disorders are serious mental illnesses. International Journal of Eating Disorders, 42(2), 97–103. doi: 10.1002/eat.20589CrossRefGoogle ScholarPubMed
Krug, I., Penelo, E., Fernandez-Aranda, F., Anderluh, M., Bellodi, L., Cellini, E., … Treasure, J. (2013). Low social interactions in eating disorder patients in childhood and adulthood: A multi-centre European case-control study. Journal of Health Psychology, 18(1), 26–37. doi: 10.1177/1359105311435946CrossRefGoogle ScholarPubMed
Krug, I., Treasure, J., Anderluh, M., Bellodi, L., Cellini, E., Collier, D., … Fernández-Aranda, F. (2009). Associations of individual and family eating patterns during childhood and early adolescence: A multicentre European study of associated eating disorder factors. British Journal of Nutrition, 101(6), 909–918. doi: 10.1017/s0007114508047752CrossRefGoogle ScholarPubMed
MacBrayer, E. K., Smith, G. T., McCarthy, D. M., Demos, S., & Simmons, J. (2001). The role of family of origin food-related experiences in bulimic symptomatology. International Journal of Eating Disorders, 30(2), 149–160. doi: 10.1002/eat.1067CrossRefGoogle ScholarPubMed
Mitchell, J. E., King, W. C., Courcoulas, A., Dakin, G., Elder, K., Engel, S., … Wolfe, B. (2015). Eating behavior and eating disorders in adults before bariatric surgery. International Journal of Eating Disorders, 48(2), 215–222. DOI: 10.1002/eat.22275CrossRefGoogle ScholarPubMed
Penelo, E., Granero, R., Krug, I., Treasure, J., Karwautz, A., Anderluh, M., … Fernández-Aranda, F. (2011). Factors of risk and maintenance for eating disorders: Psychometric exploration of the cross-cultural questionnaire (CCQ) across five European countries. Clinical Psychology & Psychotherapy, 18(6), 535–552. doi: 10.1002/cpp.728CrossRefGoogle ScholarPubMed
Ranganathan, P., Pramesh, C. S., & Aggarwal, R. (2017). Common pitfalls in statistical analysis: Logistic regression. Perspectives in Clinical Research, 8(3), 148–151. doi: 10.4103/picr.PICR_87_17Google ScholarPubMed
Stice, E. (2002). Risk and maintenance factors for eating pathology: A meta-analytic review. Psychological Bulletin, 128(5), 825–848. doi: 10.1037/0033-2909.128.5.825CrossRefGoogle Scholar
Stice, E. (2016). Interactive and mediational etiologic models of eating disorder onset: Evidence from prospective studies. Annual Review of Clinical Psychology, 12, 359–381. doi: 10.1146/annurev-clinpsy-021815-093317CrossRefGoogle ScholarPubMed
Stice, E., & Desjardins, C. D. (2018). Interactions between risk factors in the prediction of onset of eating disorders: Exploratory hypothesis-generating analyses. Behavior Research and Therapy, 105, 52–62. doi: 10.1016/j.brat.2018.03.005CrossRefGoogle ScholarPubMed
Stice, E., Gau, J. M., Rohde, P., & Shaw, H. (2017). Risk factors that predict future onset of each DSM–5 eating disorder: Predictive specificity in high-risk adolescent females. Journal of Abnormal Psychology, 126(1), 38. doi: 10.1037/abn0000219CrossRefGoogle ScholarPubMed
Stice, E., Marti, C. N., & Durant, S. (2011). Risk factors for onset of eating disorders: Evidence of multiple risk pathways from an 8-year prospective study. Behavior Research and Therapy, 49(10), 622–627. doi: 10.1016/j.brat.2011.06.009CrossRefGoogle ScholarPubMed
Stice, E., Marti, C. N., Shaw, H., & Rohde, P. (2019). Meta-analytic review of dissonance-based eating disorder prevention programs: Intervention, participant, and facilitator features that predict larger effects. Clinical Psychology Review, 70, 91–107. doi: 10.1016/j.cpr.2019.04.004CrossRefGoogle ScholarPubMed
Striegel-Moore, R. H, & Bulik, C. M. (2007). Risk factors for eating disorders. The American Psychologist, 62(3), 181–98. doi: 10.1037/0003-066X.62.3.181.CrossRefGoogle ScholarPubMed
Tibshirani, R. (1996). Regression shrinkage and selection via the Lasso. Journal of the Royal Statistical Society: Series B (Methodological, 58(1), 267–288. doi: 10.1111/j.2517-6161.1996.tb02080.xGoogle Scholar
Van Buuren, S., & Groothuis-Oudshoorn, K. (2011). Multivariate imputation by chained equations in R. Journal of Statistical Software, 45(3), 1–67. doi: 10.18637/jss.v045.i03Google Scholar
Supplementary material: File

Krug et al. supplementary material

Krug et al. supplementary material 1

Download Krug et al. supplementary material(File)
File 15.4 KB
Supplementary material: File

Krug et al. supplementary material

Krug et al. supplementary material 2

Download Krug et al. supplementary material(File)
File 14.7 KB
Supplementary material: File

Krug et al. supplementary material

Krug et al. supplementary material 3

Download Krug et al. supplementary material(File)
File 15.4 KB
Supplementary material: File

Krug et al. supplementary material

Krug et al. supplementary material 4

Download Krug et al. supplementary material(File)
File 16.4 KB
Supplementary material: File

Krug et al. supplementary material

Krug et al. supplementary material 5

Download Krug et al. supplementary material(File)
File 14.5 KB