Impact of Digital Phenotypes and Question-Asking on Emotional Disorders in Adolescents: 4-Week Field Study
Notice bibliographique
Résumé
Background: Adolescence is the period with the highest incidence of mental disorders, with approximately one-third, half, and two-thirds of cases emerging by ages 14, 18, and 25 years, respectively. Proactive interventions are essential, and digital phenotyping has emerged as a promising approach for timely detection and management. However, passive digital phenotyping is limited to sensor-detectable behaviors, while active phenotyping is often confined to clinical scales, missing the opportunity to capture users' subjective perspectives and emotional nuances. Furthermore, the potential therapeutic effect of the data collection process itself on emotional disorder management remains underexplored. Objective: This study developed and tested a mobile app that collects passive and active digital phenotypes related to adolescents' emotions and daily behaviors. The study aimed to assess the app's impact on managing emotional disorders through self-monitoring and to identify daily lifestyle indicators that can predict and track the development of such disorders. Methods: A 4-week parallel, nonequivalent control group design was employed. The intervention group installed a digital phenotype collection tool on their mobile devices for 28 days. Passive data (location, sleep, and screen time) were continuously recorded. Active data were collected through ecological momentary assessments delivered randomly up to 8 times daily, prompting participants to report their current mood and levels of depression, anxiety, and stress. The control group received no intervention. Both groups were assessed at time points on emotional disorders, self-efficacy, and time management. Postintervention interviews were conducted with the intervention group. Results: Thirty-six Korean adolescents participated (19 control, 17 intervention). The intervention group showed significant reductions in depression (P=.04, d=0.42) and stress (P=.03, d=0.46) and improvements in self-efficacy (P=.002, d=0.50) and time management abilities (P<.001, d=0.39), with small to large effect sizes. No significant change was observed in anxiety levels (P=.11). Correlational analysis revealed weak but significant links between passive digital phenotypes and daily emotional states. Conclusions: Integrating active and passive digital phenotypes through a mobile collection tool can help manage emotional disorders in adolescents. Use of the tool was associated with moderate reductions in depression and stress, as well as improvements in self-efficacy and time management, while anxiety levels remained unchanged, possibly due to adolescents' differing perceptions of anxiety. Passive digital phenotypes such as location variability and phone usage showed modest correlations with daily emotional states, supporting their potential as ecological markers. These findings suggest that digital phenotype collection not only aids in monitoring but may also have therapeutic benefits by promoting self-reflection on mood and behavior. High adherence rates further support the practicality and acceptability of this approach for long-term emotional disorder management in adolescents.
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 | 0,013 |
| Méta-épidémiologie (sens strict) | 0,001 | 0,001 |
| Méta-épidémiologie (sens large) | 0,001 | 0,002 |
| Bibliométrie | 0,002 | 0,000 |
| Études des sciences et des technologies | 0,002 | 0,001 |
| Communication savante | 0,001 | 0,001 |
| Science ouverte | 0,001 | 0,002 |
| Intégrité de la recherche | 0,001 | 0,002 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,002 | 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 ».