Personalizing a Weight Loss Program Using Cognitive-Behavioral Phenotypes to Improve Engagement and Weight Loss in Adults With Overweight or Obesity: Quasi-Experimental Study
Notice bibliographique
Résumé
BACKGROUND: Obesity affects more than one-quarter of adults in the United Kingdom and is a leading cause of preventable disease and health care costs. Digital behavior change programs can provide scalable weight management support, but maintaining engagement is challenging, and engagement is strongly associated with weight loss success. Tailoring interventions to cognitive-behavioral phenotypes, distinct patterns of thinking and behavior, offers one strategy to improve adherence. Although such approaches show promise in controlled settings, evidence from real-world digital programs is limited. OBJECTIVE: This study evaluated whether phenotype-tailored weekly advice improved engagement and weight loss in a national digital weight management program. Secondary aims were to assess correlations between advice use and outcomes, explore moderation by socioeconomic status, and capture participants' perceptions of the advice. METHODS: We conducted a quasi-experimental study among UK adults enrolled in a free 12-week program commissioned by the National Health Service. Eligible participants were aged 18-80 years with a BMI greater than 25 kg/m². The phenotype group (n=148; mean age 48 years; 127/148, 86% female; mean BMI 39 kg/m²) completed a 17-item questionnaire, were classified into one of 4 phenotypes, and received weekly tailored advice for 7 weeks. Comparators included a historical cohort enrolled 1 year earlier without phenotype advice (n=241; mean age 44 years; 171/241, 71% female) and nonresponders who did not complete the questionnaire (n=394; mean age 44 years; 299/394, 76% female). Primary outcomes were program engagement (any in-app activity such as meal logging, activity tracking, content reading, or coach messaging) and self-reported weight. RESULTS: The phenotype group recorded a mean of 257 (SD 232) engagements over 7 weeks, significantly higher than both the historical cohort (mean 159, SD 187; P<.001) and nonresponders (mean 135, SD 198; P<.001), representing 62%-90% greater activity. All engagement types were significantly elevated (P<.001 for all). Mean weight loss was -2.23 kg (SD 7.97) in the phenotype group, compared with -1.60 kg (SD 5.39; P=.29) in the historical cohort and -0.69 kg (SD 13.23; P=.23) in nonresponders. The number of phenotype-specific advice documents opened correlated with engagement (r=0.48; P<.001) but not with weight loss (P=.42). Socioeconomic status did not moderate outcomes. Posttrial interviews (n=16) provided mixed feedback: many participants described the advice as clear, relevant, and motivating, whereas others considered it too general or poorly matched. CONCLUSIONS: Phenotype-tailored weekly advice was associated with substantially higher engagement in a real-world digital program, although short-term weight differences were not statistically significant. While limited by a nonrandomized design, short follow-up, and reliance on self-reported weight, this study suggests phenotype-based tailoring may be a scalable strategy to strengthen adherence in digital weight loss interventions. Larger randomized trials with longer follow-up are warranted to determine whether increased engagement translates into clinically meaningful weight loss.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,009 | 0,007 |
| Méta-épidémiologie (sens strict) | 0,001 | 0,001 |
| Méta-épidémiologie (sens large) | 0,001 | 0,001 |
| Bibliométrie | 0,001 | 0,000 |
| Études des sciences et des technologies | 0,002 | 0,002 |
| Communication savante | 0,001 | 0,001 |
| Science ouverte | 0,001 | 0,001 |
| Intégrité de la recherche | 0,002 | 0,002 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,007 | 0,001 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».