Increase in rear-end collision risk by acute stress-induced fatigue in on-road truck driving

Abstract

Increasing road crashes related to occupational drivers' deteriorating health has become a social problem. To prevent road crashes, warnings and predictions of increased crash risk based on drivers' conditions are important. However, in on-road driving, the relationship between drivers' physiological condition and crash risk remains unclear due to difficulties in the simultaneous measurement of both. This study aimed to elucidate the relationship between drivers' physiological condition assessed by autonomic nerve function (ANF) and an indicator of rear-end collision risk in on-road driving. Data from 20 male truck drivers (mean ± SD, 49.0±8.2 years; range, 35-63 years) were analyzed. Over a period of approximately three months, drivers' working behavior data, such as automotive sensor data, and their ANF data were collected during their working shift. Using the gradient boosting decision tree method, a rear-end collision risk index was developed based on the working behavior data, which enabled continuous risk quantification. Using the developed risk index and drivers' ANF data, effects of their physiological condition on risk were analyzed employing a logistic quantile regression method, which provides wider information on the effects of the explanatory variables, after hierarchical model selection. Our results revealed that in on-road driving, activation of sympathetic nerve activity and inhibition of parasympathetic nerve activity increased each quantile of the rear-end collision risk index. The findings suggest that acute stress-induced drivers' fatigue increases rear-end collision risk. Hence, in on-road driving, drivers' physiological condition monitoring and ANF-based stress warning and relief system can contribute to promoting the prevention of rear-end truck collisions.

Fig 1. Example of daily obtained data.

(A) Obtained RRI time-series in mid-shift. Red perpendicular lines show pre- and post-shift measures. (B) Time series of LF_score in mid-shift. Red crosses show LF_score in pre- and post-shift. (C) Working behavior including vehicle speed and detailed work shift in mid-shift. (D) Time series of LF_score only during driving.

Fig 2. ROC curve analysis for discriminating near-miss situations.

(A) ROC curve of the risk estimation model for medium-speed scenes (AUC = 0.867). The dotted gray line depicts the ROC curve whose AUC = 0.500 for reference. (B) ROC curve of the risk estimation model for high-speed scenes (AUC = 0.787).

Fig 3. Estimated coefficients of the baseline model.

Coefficients over each quantile of (A) Intercept, (B) average heart rate, AVGHR, (C) Age, (D) Mean speed. Black dashed line shows estimated coefficients, and gray shaded area depicts bootstrapping 95% confidence interval. Red dashed lines show the coefficient of the logistic regression model and its 95% confidence interval.

Fig 4. Estimated coefficients of the selected model 5.

Coefficients over each quantile of (A) Intercept, (B) average heart rate, AVGHR, (C) Age, (D) Mean speed, (E) LF/HF, (F) NN50. Black dashed line shows estimated coefficients, and gray shaded area depicts bootstrapping 95% confidence interval. Red dashed lines show coefficient of logistic regression model and its 95% confidence interval.

Fig 5

Comparison between ANF of resting eye-closing state in pre-shift (left), driving state immediately after starting driving in mid-shift (middle), and resting eye-closing state in post-shift (right). (A) average heart rate, AVGHR; (B) devised score of LF, LF_score; (C) devised score of HF, HF_score; (D) LF/HF. *p<0.05, **p<0.01, and ***p<0.001 by Tukey–Kramer’s test or Steel–Dwass’s test.