Personalized Treatment Selection for Digital Eating Disorder Interventions: A Proof‐of‐Concept for the Personalized Advantage Index.
Objective: Although a range of evidence‐based treatments for eating disorders exist, treatment response varies substantially. The ability to match individuals to a treatment which they are most likely to benefit from may help improve treatment efficiency and therapeutic outcomes. The present study a...
| Publicado en: | International Journal of Eating Disorders Vol. 59; no. 8; pp. 1785 - 1794 |
|---|---|
| Autores principales: | , , , |
| Formato: | Artículo |
| Publicado: |
Wiley-Blackwell
Aug2026
|
| 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=195991235&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 195991235 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: Aug2026 vid: 59 iid: 8 pid: 480 pub: Wiley-Blackwell artinfo: ui: 195991235 10.1002/eat.70112 ppf: 1785 ppct: 9 formats: tig: atl: Personalized Treatment Selection for Digital Eating Disorder Interventions: A Proof‐of‐Concept for the Personalized Advantage Index. aug: au: McClure, Zoe Fuller‐Tyszkiewicz, Matthew Messer, Mariel Linardon, Jake affil: School of Psychology, Deakin University, Geelong Victoria, , Australia su: Australia Treatment of eating disorders Self-evaluation Medical care Internet Digital technology Random forest algorithms Secondary analysis Prediction models T-test (Statistics) Questionnaires Treatment effectiveness Severity of illness index Descriptive statistics Individualized medicine Machine learning Evaluation sug: subj: Treatment of eating disorders Self-evaluation Medical care Internet Australia Internet Publishing and Broadcasting and Web Search Portals Wired Telecommunications Carriers Digital technology Random forest algorithms Secondary analysis Prediction models T-test (Statistics) Questionnaires Treatment effectiveness Severity of illness index Descriptive statistics Individualized medicine Machine learning Evaluation keyword: digital intervention eating disorder personalized advantage index treatment selection digital intervention eating disorder personalized advantage index treatment selection ab: Objective: Although a range of evidence‐based treatments for eating disorders exist, treatment response varies substantially. The ability to match individuals to a treatment which they are most likely to benefit from may help improve treatment efficiency and therapeutic outcomes. The present study applies a treatment selection approach called the personalized advantage index (PAI) and evaluates its utility for matching individuals to a broad versus focused digital program for eating disorder symptoms. Method: Data were used from a randomized non‐inferiority trial comparing the two interventions (n = 214). Machine learning models (elastic net and random forest) were trained to predict post‐intervention symptom severity for a broad and focused digital intervention using 40 self‐reported baseline predictors. The PAI was calculated to identify the predicted optimal treatment for each participant. Results: Elastic net performed marginally better than the random forest at predicting intervention outcomes (Elastic net R2 = 0.29; Random Forest R2 = 0.26). Independent samples t‐tests indicated no significant differences in post‐intervention outcomes between participants who received their PAI‐indicated treatment and those who did not in both the full sample and a subsample with larger predicted differential responses. Discussion: PAI‐based treatment matching did not improve post‐treatment outcomes in this context. Greater utility of the PAI approach may emerge when applied to different treatment orientations or delivery formats, enabling greater opportunity for differential effects to emerge. Summary: We investigated the utility of the personalized advantage index (PAI) for matching participants to a broad versus focused digital program for eating disorder symptoms.The PAI was derived by training machine learning models to predict individual‐level responses to each intervention using baseline predictors.Participants who had received their PAI‐recommended intervention did not have significantly better outcome at post‐intervention compared to those who did not receive their PAI‐recommended intervention.Enhanced utility may require identification of more robust intervention moderators and application to interventions which differ more substantially in therapeutic approach or modality. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|