EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Personalized prediction and intervention for adolescent mental health: multimodal temporal modeling using transformer

Guiyuan Zhang, Shuang Li

Frontiers in Psychiatry · 23.06.2025 · 16

DOI: 10.3389/fpsyt.2025.1579543 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Psychiatry, online erschienen am 23.06.2025. Verfasst von Guiyuan Zhang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Student Affairs Department of the Party Committee of Guangxi Vocational College of Water Resources and Electric Power, Nanning, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Adolescent mental health problems are becoming increasingly serious, making early prediction and personalized intervention important research topics. Existing methods face limitations in handling complex emotional fluctuations and multimodal data fusion.

Methods

To address these challenges, we propose a novel model, MPHI Trans, which integrates multimodal data and temporal modeling techniques to accurately capture dynamic changes in adolescent mental health status.

Results

Experimental results on the DAIC-WOZ and WESAD datasets demonstrate that MPHI Trans significantly outperforms advanced models such as BERT, T5, and XLNet. On DAIC-WOZ, MPHI Trans achieved an accuracy of 89%, recall of 84%, precision of 85%, F1 score of 84%, and AUC-ROC of 92%. On WESAD, the model attained an accuracy of 88%, recall of 81%, precision of 82%, F1 score of 81%, and AUC-ROC of 91%.

Discussion

Ablation studies confirm the critical contributions of the temporal modeling and multimodal fusion modules, as their removal substantially degrades model performance, underscoring their indispensable roles in capturing emotional fluctuations and information fusion.

Schlagwörter

Stichwörter der Autor:innen

deep learningemotion recognitionmental healthmultimodal fusionpersonalized interventiontemporal modeling

Autor:innen und Institutionen

  • Student Affairs Department of the Party Committee of Guangxi Vocational College of Water Resources and Electric Power, Nanning, China.
  • Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China.

Zitieren

APA

Zhang, G., & Li, S. (2025). Personalized prediction and intervention for adolescent mental health: multimodal temporal modeling using transformer. Frontiers in Psychiatry, 16. https://doi.org/10.3389/fpsyt.2025.1579543

Vancouver

Zhang G, Li S. Personalized prediction and intervention for adolescent mental health: multimodal temporal modeling using transformer. Frontiers in Psychiatry. 2025;16. doi:10.3389/fpsyt.2025.1579543

BibTeX
@article{Zhang2025,
  author = {Zhang, Guiyuan and Li, Shuang},
  title = {Personalized prediction and intervention for adolescent mental health: multimodal temporal modeling using transformer},
  journal = {Frontiers in Psychiatry},
  year = {2025},
  volume = {16},
  doi = {10.3389/fpsyt.2025.1579543}
}
Kostenlos starten →