Applying Machine Learning to Predict Complex Clinical Course in Youth With Eating Disorders.
Objective: To compare the predictive performance of supervised machine learning models to logistic regression in identifying youth with eating disorders at risk of a complex clinical course based on clinical characteristics from the first treatment episode. Methods: Clinical data from 327 youth trea...
| Publicado en: | International Journal of Eating Disorders Vol. 59; no. 1; pp. 134 - 146 |
|---|---|
| Autores principales: | , , , |
| Formato: | Artículo |
| Publicado: |
Wiley-Blackwell
Jan2026
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=190687308&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 190687308 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 02763478 IJD jtl: International Journal of Eating Disorders issn: 02763478 maglogo: Y pubinfo: dt: Jan2026 vid: 59 iid: 1 pid: 480 pub: Wiley-Blackwell artinfo: ui: 190687308 10.1002/eat.24570 ppf: 134 ppct: 12 formats: tig: atl: Applying Machine Learning to Predict Complex Clinical Course in Youth With Eating Disorders. aug: au: Ryall, Stephanie Bradley, Abigail El Emam, Khaled Obeid, Nicole affil: Children's Hospital of Eastern Ontario Research Institute, Ottawa Ontario,, Canada Faculty of Medicine, University of Ottawa, Ottawa Ontario,, Canada School of Epidemiology and Public Health, University of Ottawa, Ottawa Ontario,, Canada su: Ontario Treatment of eating disorders Body weight Retrospective studies Eating disorders Stature Anthropometry Disease risk factors Adolescence Risk assessment Random forest algorithms Boosting algorithms Prediction models Academic medical centers Body mass index Logistic regression analysis Patient readmissions Symptoms Children's hospitals Tertiary care Descriptive statistics Longitudinal method Support vector machines Medical records Acquisition of data Machine learning Comparative studies Data analysis software Hospital care of teenagers Sensitivity & specificity (Statistics) Disease progression sug: subj: Treatment of eating disorders Body weight Retrospective studies Eating disorders Stature Anthropometry Disease risk factors Adolescence Ontario Specialty (except Psychiatric and Substance Abuse) Hospitals General Medical and Surgical Hospitals Paediatric hospitals Risk assessment Random forest algorithms Boosting algorithms Prediction models Academic medical centers Body mass index Logistic regression analysis Patient readmissions Symptoms Children's hospitals Tertiary care Descriptive statistics Longitudinal method Support vector machines Medical records Acquisition of data Machine learning Comparative studies Data analysis software Hospital care of teenagers Sensitivity & specificity (Statistics) Disease progression keyword: clinical course eating disorders machine learning prediction random forest clinical course eating disorders machine learning prediction random forest ab: Objective: To compare the predictive performance of supervised machine learning models to logistic regression in identifying youth with eating disorders at risk of a complex clinical course based on clinical characteristics from the first treatment episode. Methods: Clinical data from 327 youth treated at any level of care at the Children's Hospital of Eastern Ontario Eating Disorders Program (2018–2024) were extracted. Complex clinical course outcome was defined as either readmission after discharge or a treatment trajectory deviating from the expected step‐down in intensity, including return to the same or escalation to a higher level of care. Thirty‐four intake and discharge variables from the first treatment episode were used to train seven machine learning models and logistic regression using repeated nested cross‐validation. Performance was assessed by AUC and brier scores. Models using intake‐only versus intake plus discharge data were compared. A parsimonious model using the top 10 predictors was also evaluated. Results: Random forest model with intake and discharge data achieved the best performance (AUC = 0.723; Brier = 0.176) that was significantly superior to logistic regression. Models trained on intake‐only data showed poor discrimination (AUCs < 0.6). Including discharge data improved model performance across all algorithms. The most important predictor was weight change throughout treatment. Random forest performance declined when restricted to the top 10 predictors. Discussion: Supervised machine learning demonstrates improved predictive performance for eating disorder disease course outcomes compared to traditional statistical methods, especially in higher‐dimensionality settings. These findings support future application of machine learning to complex biopsychosocial datasets to advance precision medicine initiatives in the eating disorder field and better understand the etiology of disease trajectory. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|