A Wearable Device Dataset for Mental Health Assessment Using Laser Doppler Flowmetry and Fluorescence Spectroscopy Sensors

2025-02-03

AI Summary

Current wearable devices lack sufficient accuracy in assessing mental health states—including stress, anxiety, and depression. Method: This study proposes a novel wearable multimodal sensing framework integrating laser Doppler flowmetry (LDF) and fluorescence spectroscopy to capture dynamic cutaneous microcirculatory signals, coupled with the Depression, Anxiety and Stress Scale-21 (DASS-21) for ground-truth labeling. A multicenter dataset was collected from 132 participants aged 18–94 years across 19 countries. Contribution/Results: We release the first and largest publicly available global LDF-fluorescence multimodal psychophysiological dataset. By extracting wavelet-domain microvascular oscillation features and integrating them with interpretable AI (SHAP and LIME), we achieve transparent model decision-making. The LightGBM classifier achieves an ROC AUC of 0.717 and PR AUC of 0.885 for stress detection; key predictive factors identified include sex, age, BMI, and heart rate.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Brain-Sensing and Analysis
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

In this study, we introduce a novel method to predict mental health by building machine learning models for a non-invasive wearable device equipped with Laser Doppler Flowmetry (LDF) and Fluorescence Spectroscopy (FS) sensors. Besides, we present the corresponding dataset to predict mental health, e.g. depression, anxiety, and stress levels via the DAS-21 questionnaire. To our best knowledge, this is the world's largest and the most generalized dataset ever collected for both LDF and FS studies. The device captures cutaneous blood microcirculation parameters, and wavelet analysis of the LDF signal extracts key rhythmic oscillations. The dataset, collected from 132 volunteers aged 18-94 from 19 countries, explores relationships between physiological features, demographics, lifestyle habits, and health conditions. We employed a variety of machine learning methods to classify stress detection, in which LightGBM is identified as the most effective model for stress detection, achieving a ROC AUC of 0.7168 and a PR AUC of 0.8852. In addition, we also incorporated Explainable Artificial Intelligence (XAI) techniques into our analysis to investigate deeper insights into the model's predictions. Our results suggest that females, younger individuals and those with a higher Body Mass Index (BMI) or heart rate have a greater likelihood of experiencing mental health conditions like stress and anxiety. All related code and data are published online: https://github.com/leduckhai/Wearable_LDF-FS.

Problem

• Wearable Devices
• Mental Health Monitoring
• Biometric Sensors

Innovation

• Wearable Devices
• LightGBM Machine Learning
• Interpretable Artificial Intelligence