WatchAnxiety: A Transfer Learning Approach for State Anxiety Prediction from Smartwatch Data

Md Sabbir Ahmed, Noah French, Mark Rucker, Zhiyuan Wang, Taylor Myers-Brower, Kaitlyn Petz, Mehdi Boukhechba, Bethany A. Teachman, Laura E. Barnes

Confirmation: I have read and agree with the IEEE BSN 2025 conference submission's policy on behalf of myself and my co-authors.

Keywords: State anxiety, transfer learning, meta-learner, smartwatch

TL;DR: We present a watch-based system using transfer and meta-learning to predict state anxiety, achieving 60.4% balanced accuracy on our dataset and 59.1% on an external dataset of over 10000 anxiety responses, outperforming baseline by at least 7%.

Abstract: Social anxiety is a common mental health condition linked to significant challenges in academic, social, and occupational functioning. A core feature is elevated momentary (state) anxiety in social situations, yet little prior work has measured or predicted fluctuations in this anxiety throughout the day. Capturing these intra-day dynamics is critical for designing real-time, personalized interventions such as Just-In-Time Adaptive Interventions (JITAIs). To address this gap, we conducted a study with socially anxious college students (N=91; 72 after exclusions) using our custom smartwatch-based system over an average of 9.03 days (SD = 2.95). Participants received seven ecological momentary assessments (EMAs) per day to report state anxiety. We developed a base model on over 10,000 days of external heart rate data, transferred its representations to our dataset, and fine-tuned it to generate probabilistic predictions. These were combined with trait-level measures in a meta-learner. Our pipeline achieved 60.4% balanced accuracy in state anxiety detection in our dataset. To evaluate generalizability, we applied the training approach to a separate hold-out set from the TILES-18 dataset—the same dataset used for pretraining. On 10,095 once-daily EMAs, our method achieved 59.1% balanced accuracy, outperforming prior work by at least 7%.

Track: 2. Sensors and systems for digital health, wellness, and athletics

NominateReviewer:

Md Sabbir Ahmed, [e-mail]

I am uncertain whether others will be available to serve as reviewers, but I will be happy to assist. Thank you.

Submission Number: 143