What is the clinical evidence from this study?

Study design: Observational. Population: Mental stress (n=20). Intervention: Machine learning-based mental stress detection using smart T-shirt ECG signals vs. Normal state (no work/after sleep). Primary outcome: Intra-subject classification accuracy using Decision Tree leave-one-out model.

June 17, 2022Open Access

Wearable Flexible Electronics Based Cardiac Electrode for Researcher Mental Stress Detection System Using Machine Learning Models on Single Lead Electrocardiogram Signal

Key Result

A Decision Tree classifier using single-lead ECG signals from a smart T-shirt detected mental stress with 93.30% intra-subject accuracy and 94.10% inter-subject accuracy.

Study Design

Type

Observational (n=20)

Structured PICO

Can machine learning models applied to single-lead ECG signals from a wearable smart T-shirt accurately detect mental stress in researchers?

Population

20 subjects (10 with mental stress after 12 hours of continuous laboratory work, 10 normal after sleep or without work)

Intervention

Machine learning models (Decision Tree, Naive Bayes, Random Forest, Logistic Regression) applied to single-lead ECG signals from a wearable smart T-shirt

Comparator

Normal state (without work/after sleep)

Outcome

Classification accuracy, recall, specificity, precision, and F1 score for mental stress detectionsurrogate

A wearable smart T-shirt using a Decision Tree classifier on single-lead ECG signals can accurately detect mental stress, potentially aiding in early cardiovascular risk assessment.

Abstract

In the modern world, wearable smart devices are continuously used to monitor people's health. This study aims to develop an automatic mental stress detection system for researchers based on Electrocardiogram (ECG) signals from smart T-shirts using machine learning classifiers. We used 20 subjects, including 10 from mental stress (after twelve hours of continuous work in the laboratory) and 10 from normal (after completing the sleep or without any work). We also applied three scoring techniques: Chalder Fatigue Scale (CFS), Specific Fatigue Scale (SFS), Depression, Anxiety, and Stress Scale (DASS), to confirm the mental stress. The total duration of ECG recording was 1800 min, including 1200 min during mental stress and 600 min during normal. We calculated two types of features, such as demographic and extracted by ECG signal. In addition, we used Decision Tree (DT), Naive Bayes (NB), Random Forest (RF), and Logistic Regression (LR) to classify the intra-subject (mental stress and normal) and inter-subject classification. The DT leave-one-out model has better performance in terms of recall (93.30%), specificity (96.70%), precision (94.40%), accuracy (93.30%), and F1 (93.50%) in the intra-subject classification. Additionally, The classification accuracy of the system in classifying inter-subjects is 94.10% when using a DT classifier. However, our findings suggest that the wearable smart T-shirt based on the DT classifier may be used in big data applications and health monitoring. Mental stress can lead to mitochondrial dysfunction, oxidative stress, blood pressure, cardiovascular disease, and various health problems. Therefore, real-time ECG signals help assess cardiovascular and related risk factors in the initial stage based on machine learning techniques.

Bookmark

View Full Paper