Comparison of measurement of the augmentation index from ARTSENS and eTRACKING

A Machine Learning Pipeline for Measurement of Arterial Stiffness in A-Mode Ultrasound

Arterial stiffness (AS) of the carotid artery is an early marker of stratifying cardiovascular disease risk. This article aims to improve the performance of ARTSENS, a noninvasive A-mode ultrasound-based device for measuring AS. The primary objective of ARTSENS is to enable the measurement of elastic modulus using A-Mode ultrasound and blood pressure. As this device is image-free, there is a need to automate: 1) carotid detection; 2) wall localization; and 3) inner lumen diameter measurement. This has been performed using conventional signal processing methods in some of the earlier works in this domain. In this article, deep neural network (DNN) models are employed to perform the above three tasks. The DNNs were trained over data acquired from 82 subjects at two different medical centers. Ground-truth labeling was performed by a trained operator using corresponding measurements from the state-of-the-art Aloka e-Tracking system. All three DNN models had significantly lower errors compared to earlier signal processing methods and could perform their measurements using a single A-Mode frame. Using the DNNs, two different machine learning pipelines have been proposed here to measure the elastic modulus; the best among them could achieve an error of 9.3% with the Pearson correlation coefficient of 0.94 ( ). The models were tested on Raspberry Pi and Jetson Nano single board computers to demonstrate real-time processing on low computational resources.

Assessment of Carotid Arterial Stiffness in Community Settings With ARTSENS®

OBJECTIVE

We investigate the field feasibility of carotid stiffness measurement using ARTSENS® Touch and report the first community-level data from India.

METHOD

In an analytical cross-sectional survey among 1074 adults, we measured specific stiffness index ([Formula: see text]), pressure-strain elastic modulus ([Formula: see text]), arterial compliance (AC), and one-point pulse wave velocity (PWV[Formula: see text]) from the left common carotid artery. Data for established risk factors (waist circumference, blood pressure, plasma glucose, triglycerides, and HDL-C) were also collected. The association of carotid stiffness with age, gender, hypertension/diabetes, smoking, and clustering of risk factors was studied.

RESULTS

Measurements were repeatable with a relative difference (RD) between consecutive readings of < 5% for blood pressure and < 15% for [Formula: see text]% of arterial diameter values. The average RDs for [Formula: see text], [Formula: see text], AC, and PWV[Formula: see text], were 20.51%, 22.31%, 25.10%, and 14.13%, respectively. Typical range for stiffness indices among females and males were [Formula: see text]: 8.12 ± 3.59 vs 6.51 ± 2.78, [Formula: see text]: 113.24 ± 56.12 kPa vs 92.33 ± 40.65 kPa, PWV[Formula: see text]: 6.32 ± 1.38 ms-1 vs 5.81 ± 1.16 ms-1, and AC: 0.54 ± 0.36 mm2 kPa-1 vs 0.72 ± 0.38 mm2 kPa-1. Mean [Formula: see text], [Formula: see text], and PWV[Formula: see text] increased (and mean AC decreased) across decades of age; the trend persisted even after excluding hypertensives and subjects with diabetes. The odds ratio of presence of multiple risk factors for [Formula: see text] kPa and/or PWV[Formula: see text] ms-1 was ≥ 2.12 or above in males. In females, it was just above 2.00 for [Formula: see text] kPa and/or PWV[Formula: see text] ms-1 and increased to ≥ 3.33 for [Formula: see text] kPa and ≥ 3.25 for PWV[Formula: see text] ms-1.

CONCLUSION

The study demonstrated the feasibility of carotid stiffness measurement in a community setting. A positive association between the risk factors and carotid artery stiffness provides evidence for the device's use in resource-constrained settings. Clinical Impact: The device paves the way for epidemiological and clinical studies that are essential for establishing population-level nomograms for wide-spread use of carotid stiffness in clinical practice and field screening of 'at-risk' subjects.