Sensor-Location-Specific Joint Acquisition of Peripheral Artery Bioimpedance and Photoplethysmogram for Wearable Applications

Abstract

Background: Cardiovascular diseases (CVDs), being the culprit for one-third of deaths globally, constitute a challenge for biomedical instrumentation development, especially for early disease detection. Pulsating arterial blood flow, providing access to cardiac-related parameters, involves the whole body. Unobtrusive and continuous acquisition of electrical bioimpedance (EBI) and photoplethysmography (PPG) constitute important techniques for monitoring the peripheral arteries, requiring novel approaches and clever means.

Methods: In this work, five peripheral arteries were selected for EBI and PPG signal acquisition. The acquisition sites were evaluated based on the signal morphological parameters. A small-data-based deep learning model, which increases the data by dividing them into cardiac periods, was proposed to evaluate the continuity of the signals.

Results: The highest sensitivity of EBI was gained for the carotid artery (0.86%), three times higher than that for the next best, the posterior tibial artery (0.27%). The excitation signal parameters affect the measured EBI, confirming the suitability of classical 100 kHz frequency (average probability of 52.35%). The continuity evaluation of the EBI signals confirmed the advantage of the carotid artery (59.4%), while the posterior tibial artery (49.26%) surpasses the radial artery (48.17%). The PPG signal, conversely, commends the location of the posterior tibial artery (97.87%).

Conclusions: The peripheral arteries are highly suitable for non-invasive EBI and PPG signal acquisition. The posterior tibial artery constitutes a candidate for the joint acquisition of EBI and PPG signals in sensor-fusion-based wearable devices-an important finding of this research.

Keywords: cardiovascular system; convolutional neural networks; deep learning; electrical bioimpedance; non-invasive measurements; photoplethysmography; pulse wave; sensor fusion; small data machine learning; wearable devices.

Figure 1

Locations of the chosen arteries and respective body areas for acquiring the signals of EBI and rPPG: brachial artery (arm) (A), carotid artery (neck) (B), radial artery (wrist) (C), posterior tibial artery (leg) (D), and ulnar artery (wrist) (E).

Figure 2

Workflow of the proposed method and deep-learning-based approach for the EBI and rPPG signal evaluation.

Figure 3

Convolutional neural networks architecture of the proposed model.

Figure 4

Sample waveforms of signals of EBI (at the excitation frequency of 100 kHz) and rPPG that were acquired from the chosen sensor locations (A–E). (a) Brachial artery (A); (b) carotid artery (B); (c) radial artery (C); (d) posterior tibial artery (D); (e) ulnar artery (E).

Figure 5

Calculated sensitivities (mean values) (with graphically added $\sigma$) of the EBI and rPPG signals in the cases of the chosen sensor locations (A–E). (a) Signal of EBI; (b) signal of rPPG.

Figure 6

Signal periods (marked with different colors for each period—but not defined as the figure is illustrative) that were represented by the proposed deep learning-based model for evaluation of the signals of EBI at each excitation frequency. (a) Signal periods of EBI at 50 kHz, (b) signal periods of EBI at 100 kHz, (c) signal periods of EBI at 500 kHz, (d) signal periods of EBI at 1000 kHz, and (e) signal periods of rPPG.