Volatile Organic Compounds for Stress Detection: A Scoping Review and Exploratory Feasibility Study with Low-Cost Sensors

2025-12-24

AI Summary

Reliable, non-invasive biomarkers of psychological stress remain elusive, particularly for real-world deployment. Method: This study investigates exhaled and cutaneous volatile organic compounds (VOCs) as stress biomarkers using low-cost total VOC (TVOC) sensors (BME688/ENS160). A PRISMA-ScR systematic review first maps the evidence landscape for VOC-based emotion recognition. Concurrently, a 25-participant arithmetic stress experiment collects synchronized TVOC, heart rate (HR), heart rate variability (HRV), and electrodermal activity (EDA) data. Random forest classification with SHAP analysis quantifies feature importance. Contribution/Results: Participants exhibiting high cardiovascular reactivity showed significantly elevated TVOC responses (Cohen’s *d* = 1.38), with latency of 30–80 s and marked inter-individual variability. A multimodal model achieved 77.3% accuracy (5-fold CV) and 65.3% leave-one-subject-out accuracy; VOC features independently contributed 24.9% to discriminative power. These findings demonstrate the clinical deployability potential of ultra-low-power TVOC sensors, establishing a novel paradigm for unobtrusive, continuous stress monitoring.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Volatile organic compounds (VOCs) represent a novel but underexplored modality for emotion recognition. This paper presents a systematic evidence synthesis and exploratory investigation of VOC-based affective computing using low-cost sensors. Study 1, a systematic scoping review following PRISMA-ScR guidelines, analyzed 16 studies from 610 records across breath, sweat, skin, and urine biosources. Evidence indicates that stress and affective states are reflected in VOC signatures (aldehydes, ketones, fatty acids, sulfur compounds), though with considerable heterogeneity. Current research relies predominantly on laboratory-grade GC-MS or PTR-MS, while wearable sensors provide pattern-level outputs without compound-specific identification - a critical gap for practical systems. Study 2 (n=25) investigated whether low-cost TVOC sensors (BME688, ENS160) combined with physiological monitoring (HR, HRV, GSR) can detect laboratory-induced stress. Exploratory analysis revealed that high cardiovascular reactors exhibited elevated TVOC during arithmetic stress (d=1.38), though requiring replication in larger samples. Substantial interindividual variability emerged (CV>80%), with coupling patterns moderated by baseline emission levels and temporal lags of 30-80 seconds. Random Forest-based multimodal classification achieved 77.3% accuracy (5-fold CV). SHAP analysis indicated VOC sensors contributed 24.9% of model performance. Leave-one-subject-out validation yielded 65.3% accuracy, highlighting the need for individual calibration. This work provides three contributions: (1) comprehensive mapping of VOC biomarker evidence and technological gaps, (2) initial demonstration that low-cost sensors can capture stress-related VOC patterns in multimodal fusion, and (3) identification of key implementation challenges. Findings require replication in larger samples (n>=50).

Problem

• Investigates using volatile organic compounds for emotion recognition via low-cost sensors.
• Assesses feasibility of detecting stress with VOC sensors and physiological data fusion.
• Identifies technological gaps and individual variability in VOC-based stress detection.

Innovation

• Systematic scoping review of VOC biomarkers for affective states
• Low-cost VOC sensors combined with physiological monitoring for stress detection
• Multimodal fusion with machine learning for emotion recognition