Driver Cardiovascular Disease Detection Using Seismocardiogram

Abstract

This article deals with the treatment and application of cardiac biosignals, an excited accelerometer, and a gyroscope in the prevention of accidents on the road. Previously conducted studies say that the seismocardiogram is a measure of cardiac microvibration signals that allows for detecting rhythms, heart valve opening and closing disorders, and monitoring of patients' breathing. This article refers to the seismocardiogram hypothesis that the measurements of a seismocardiogram could be used to identify drivers' heart problems before they reach a critical condition and safely stop the vehicle by informing the relevant departments in a nonclinical manner. The proposed system works without an electrocardiogram, which helps to detect heart rhythms more easily. The estimation of the heart rate (HR) is calculated through automatically detected aortic valve opening (AO) peaks. The system is composed of two micro-electromechanical systems (MEMSs) to evaluate physiological parameters and eliminate the effects of external interference on the entire system. The few digital filtering methods are discussed and benchmarked to increase seismocardiogram efficiency. As a result, the fourth adaptive filter obtains the estimated HR = 65 beats per min (bmp) in a still noisy signal (SNR = −11.32 dB). In contrast with the low processing benefit (3.39 dB), 27 AO peaks were detected with a 917.56-ms peak interval mean over 1.11 s, and the calculated root mean square error (RMSE) was 0.1942 m/s2 when the adaptive filter order is 50 and the adaptation step is equal to 0.933.

A Novel Seismocardiogram Mathematical Model for Simplified Adjustment of Adaptive Filter

“…This article is closely related to the previous article of this research group, and will continue the work of improving the quality of the study of nonclinical SCG signals [35]. Also, the work relates to investigations of using wireless sensors and them effective energy consumption [36][37][38].…”

Driver Attention Assessment Using Physiological Measures from EEG, ECG, and EDA Signals

“…The wearability of our proposed system has the advantage of higher accuracy, along with the disadvantage of being slightly intrusive for the driver, while camera-based solutions are contactless and independent from the driver. To solve the problem of intrusiveness, non-wearable biological sensors have been presented in the literature, for instance, sensors integrated in the driver’s seat such as capacitive electrocardiogram (cECG), Ballistocardiogram (BCG) [ 50 , 51 ], Seismocardiogram (SCG) [ 52 ], or steering wheel ECG [ 53 ], or radar systems [ 54 ]. However, compared to wearable bio-sensors they have less efficiency and accuracy and are more prone to being affected by other environmental conditions such as humidity, vibration, and the driver’s clothing [ 55 ].…”

M2ECG: Wearable Mechanocardiograms to Electrocardiogram Estimation Using Deep Learning

“…Laurin et al [28] demonstrated the reliability of HRV indices derived from SCG signals, and Tadi et al [29] confirmed a strong association between HRV indices derived from ECG and SCG. Beyond traditional ECG applications, MCG signals have proven effective in classifying cardiovascular anomalies through smartphones [1], [30], estimating respiratory rate (RR) [12], [31], determining tidal volume alongside ECG from SCG [32], estimating cardiac time intervals from SCG [33], real-time cardiovascular disease detection for drivers [34], among other applications. Thus, based on the aforementioned discussions, ECG estimated from MCG components possesses the capability to detect and classify cardiac anomalies in non-healthy patients in advanced applications.…”