Stress influence on real-world driving identified by monitoring heart rate variability and morphologic variability of ECG signals: The case of intercity roads

This study examines which one of the heart rate variability (HRV) and morphologic variability (MV) metrics may have the highest accuracy in different stress detection during real-world driving. This cross-sectional study was carried out among 93 intercity mini-bus male drivers aged 22-67 years. Trillium 5000 Holter Recorder and GARMIN Virb Elite camera were used to determine heart rate and vehicle speed measurements along the path, respectively. We have considered the HRV and MV metrics of ECG signals including mean RR interval (mRR), mean heart rate (mHR), normalized low-frequency spectrum (nLF), normalized high-frequency spectrum (nHF), normalized very low-frequency spectrum (nVLF), a difference of normalized low-frequency spectrum and normalized high-frequency spectrum (dLFHF), and sympathovagal balance index (SVI). The analysis showed that HRV metrics named mHR, mRR, nVLF, nLF, nHF, dLFHF, and SVI are effective in mental stress detection while driving as compared to rest time. We obtained a high accuracy of stress detection for MV metrics as compared to the traditional HRV analysis, approximately 92%. Our findings indicate that driver stress could be detected with an accuracy of 92% using MV metrics as an accurate physiological index of the driver's state.

本研究旨在探究心率变异性（heart rate variability, HRV）与形态变异性（morphologic variability, MV）指标中，哪一项在真实驾驶场景下的不同应激状态检测中具备最高准确率。本项横断面研究以93名年龄22至67岁的城际小巴男性驾驶员为研究对象。研究分别采用Trillium 5000动态心电记录仪采集心率数据，采用GARMIN Virb Elite运动相机采集行驶全程的车辆速度数据。本研究纳入的心电信号（Electrocardiogram, ECG）相关HRV与MV指标包括：平均RR间期（mean RR interval, mRR）、平均心率（mean heart rate, mHR）、归一化低频功率（normalized low-frequency spectrum, nLF）、归一化高频功率（normalized high-frequency spectrum, nHF）、归一化极低频功率（normalized very low-frequency spectrum, nVLF）、归一化低频与高频功率差值（dLFHF）以及交感迷走平衡指数（sympathovagal balance index, SVI）。分析结果显示，相较于静息状态，mHR、mRR、nVLF、nLF、nHF、dLFHF及SVI等HRV指标可有效识别驾驶过程中的心理应激状态。相较于传统HRV分析方法，MV指标用于应激检测的准确率更高，可达约92%。本研究结果表明，以MV指标作为驾驶员状态的精准生理指标，可实现92%准确率的驾驶员应激状态检测。