Classification of Stress via Ambulatory ECG and GSR Data

TL;DR

This paper evaluates machine learning methods for stress detection using ambulatory ECG and GSR data, achieving high accuracy in controlled settings but noting challenges in real-world data.

Contribution

It introduces an empirical assessment of classifiers for stress detection in ambulatory environments and analyzes performance disparities between datasets.

Findings

Optimal classifier achieved 90.77% accuracy in controlled data

Performance dropped to 59.23% accuracy on challenge data

Identifies factors affecting real-world stress detection accuracy

Abstract

In healthcare, detecting stress and enabling individuals to monitor their mental health and wellbeing is challenging. Advancements in wearable technology now enable continuous physiological data collection. This data can provide insights into mental health and behavioural states through psychophysiological analysis. However, automated analysis is required to provide timely results due to the quantity of data collected. Machine learning has shown efficacy in providing an automated classification of physiological data for health applications in controlled laboratory environments. Ambulatory uncontrolled environments, however, provide additional challenges requiring further modelling to overcome. This work empirically assesses several approaches utilising machine learning classifiers to detect stress using physiological data recorded in an ambulatory setting with self-reported stress annotations. A subset of the training portion SMILE dataset enables the evaluation of approaches before submission. The optimal stress detection approach achieves 90.77% classification accuracy, 91.24 F1-Score, 90.42 Sensitivity and 91.08 Specificity, utilising an ExtraTrees classifier and feature imputation methods. Meanwhile, accuracy on the challenge data is much lower at 59.23% (submission #54 from BEaTS-MTU, username ZacDair). The cause of the performance disparity is explored in this work.