Paper Type
ERF
Abstract
Anxiety disorders become prevalent and significantly impact individuals, yet traditional monitoring methods are often insufficient and generalized. In this paper, we introduce AnxietySense, a multi-modal anxiety monitoring system leveraging emerging sensing capabilities of earables and smart-phones for continuous, unobtrusive anxiety monitoring. Our approach captures and integrates physiological (e.g., heart rate variability), behavioral (e.g., digital interaction), and contextual (e.g., location) data through an edge-to-cloud architecture. Utilizing multi-modal Transformers for intelligent data fusion, AnxietySense offers context-aware insights adaptable to different anxiety subtypes. The system is designed for secure and privacy-aware integration with clinical workflows via standards like FHIR (Fast Healthcare Interoperability Resources), providing a robust framework for personalized, real-time anxiety assessment, potentially enabling earlier detection and personalized interventions, thus advancing mental health monitoring capabilities.
Paper Number
1613
Recommended Citation
Wang, Zi; Zhao, Jiyue; Zhang, Linghan; Fang, Shiwei; and Li, Lin, "AnxietySense: Multi-Modal Information System for Continuous Anxiety Monitoring" (2026). AMCIS 2026 Proceedings. 7.
https://aisel.aisnet.org/amcis2026/ai_systdesign/ai_systdesign/7
AnxietySense: Multi-Modal Information System for Continuous Anxiety Monitoring
Anxiety disorders become prevalent and significantly impact individuals, yet traditional monitoring methods are often insufficient and generalized. In this paper, we introduce AnxietySense, a multi-modal anxiety monitoring system leveraging emerging sensing capabilities of earables and smart-phones for continuous, unobtrusive anxiety monitoring. Our approach captures and integrates physiological (e.g., heart rate variability), behavioral (e.g., digital interaction), and contextual (e.g., location) data through an edge-to-cloud architecture. Utilizing multi-modal Transformers for intelligent data fusion, AnxietySense offers context-aware insights adaptable to different anxiety subtypes. The system is designed for secure and privacy-aware integration with clinical workflows via standards like FHIR (Fast Healthcare Interoperability Resources), providing a robust framework for personalized, real-time anxiety assessment, potentially enabling earlier detection and personalized interventions, thus advancing mental health monitoring capabilities.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
AI SYSTEM