Large language model improves heart-based stress detection and explanation
Beyond Latent Personalization: Integrating HRV-Conditioned Personalization via LLM for Interpretable Stress Detection
Machine Learning
Summary
Detecting stress by looking at heart signals called heart rate variability (HRV) is helpful but often hard to explain clearly. This paper shows how using a large language model (LLM) can connect personal traits with HRV to better detect stress and provide easy-to-understand explanations. The new method improves accuracy compared to earlier techniques and makes it clearer how individual body signals relate to stress.
What this means in practice
- •For wearable device developers: Create stress-monitoring features that provide clear, personalized feedback from heart rate data and user profiles.$Commercial implications: Enables development of consumer wearables that not only detect stress more accurately but also explain it in human-readable terms for better user engagement.
- •For mental health app developers: Integrate personalized physiological stress detection with explanatory feedback to improve app user understanding and trust.
Tested on one dataset.
Authors
Wei-Hsiang Ma, Ya-Tse Wu, Hsing-Hang Chou, Chi-Chun Lee
Abstract
Stress detection based on heart rate variability (HRV) has received increasing attention. However, existing personalized approaches integrate personal attributes with HRV through latent representations, limiting the interpretability of their interactions. In this work, we propose an LLM-enhanced personalized stress detection framework that integrates HRV features and personal attributes through LLM-based semantic interpretation. The proposed framework achieves a 29.9% relative MCC improvement over the strongest baseline on TILES-2018 while providing human-readable descriptions of individual physiological responses. The results highlight the potential of LLM-based semantic interpretation for achieving both effective and interpretable personalized stress detection.