Bilateral photoplethysmography for peripheral arterial disease screening in haemodialysis patients using astable multivibrator and machine learning classifier

• Published in: IET science, measurement & technology Vol. 13; no. 9; pp. 1277 - 1286
• Main Authors: Wu, Jian-Xing, Lin, Chia-Hung, Kan, Chung-Dann, Chen, Wei-Ling
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.11.2019
• Subjects: amplitude ratio; astable multivibrator; atherosclerosis; bilateral differences; bilateral timing parameters; blood flow volume; blood vessels; colour relation analysis; continuous variations; diastolic pressures; diseases; duty ratio; embedded system; haemodialysis patients; haemodynamics; HD patients; in vivo examinations; learning (artificial intelligence); lower peripheral arteries; machine learning classifier; machine learning decision‐making process; medical signal processing; noninvasive bilateral photoplethysmography; PAD screening; perceptual colour relationships; peripheral arterial disease screening; peripheral circulation system; photoplethysmography; PPG oscillation; probability; probability values; progressive dialysis access stenosis; radial‐based function; Research Article; resistive index; rising time; screening method; systolic pressures; time constants; type 2 diabetes; upper peripheral arteries; blood flow volume; haemodialysis patients; colour relation analysis; PPG oscillation; probability values; photoplethysmography; screening method; embedded system; resistive index; learning (artificial intelligence); progressive dialysis access stenosis; rising time; in vivo examinations; atherosclerosis; perceptual colour relationships; time constants; duty ratio; bilateral timing parameters; amplitude ratio; lower peripheral arteries; probability; PAD screening; blood vessels; diseases; upper peripheral arteries; systolic pressures; machine learning classifier; bilateral differences; medical signal processing; peripheral circulation system; machine learning decision-making process; type 2 diabetes; noninvasive bilateral photoplethysmography; diastolic pressures; peripheral arterial disease screening; HD patients; astable multivibrator; continuous variations; haemodynamics; radial-based function
• ISSN: 1751-8822; 1751-8830
• DOI: 10.1049/iet-smt.2018.5330

Peripheral arterial disease (PAD) is highly prevalent in haemodialysis (HD) patients with type 2 diabetes. Atherosclerosis may occur in both lower and upper peripheral arteries, causing progressive dialysis access stenosis in HD patients. To assess the risk of PAD, non-invasive bilateral photoplethysmography (PPG) can be used to obtain continuous variations in blood flow volume in in vivo examinations. The authors propose an astable multivibrator to model the peripheral circulation system and to produce PPG oscillation with time constants, duty ratio (rising time), and amplitude ratio of systolic and diastolic pressures. Then, the bilateral differences in the time constant and duty ratio are used to separate the normal condition from PAD. The machine learning decision-making process utilises a screening method to automatically detect subjects with and without the risk of PAD. The radial-based function is employed to parameterise the similarity and dissimilarity levels using probability values. Colour relation analysis incorporates the probability values into the perceptual colour relationships for PAD screening. The experimental results indicate that in comparison with bilateral timing parameters, degree of stenosis, and resistive index, the proposed screening method is efficient in preventing complications of PAD and is easily implemented in an embedded system.