An ECG Delineation and Arrhythmia Classification System Using Slope Variation Measurement by Ternary Second-Order Delta Modulators for Wearable ECG Sensors

• Published in: IEEE transactions on biomedical circuits and systems Vol. 15; no. 5; pp. 1053 - 1065
• Main Authors: Tang, Xiaochen, Tang, Wei
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Analog circuits; Arrhythmia; Arrhythmias, Cardiac - diagnosis; Cardiac arrhythmia; Circuit design; Classification; Delineation; Delta modulation; Density; ECG delineation; EKG; Electrocardiography; Feature extraction; fiducial points; Field programmable gate arrays; Heart Rate; Humans; Integrated circuits; Machine learning; Modulators; patient-specific; Power consumption; second-order delta modulator; Signal Processing, Computer-Assisted; slope variation; support vector machine; Support vector machines; ternary circuits; Variation; Ventricle; Waveforms; Wearable Electronic Devices; Wearable sensors; Wearable technology
• ISSN: 1932-4545; 1940-9990; 1940-9990
• DOI: 10.1109/TBCAS.2021.3113665

This paper presents a system for electrocardiogram (ECG) delineation and arrhythmia classification. The proposed system consists of a front-end integrated circuit, a delineation algorithm implemented on an FPGA board, and an arrhythmia classification algorithm. The front-end circuit applies a ternary second-order Delta modulator to measure the slope variation of the input analog ECG signal. The circuit converts the analog inputs into a pulse density modulated bitstream, whose pulse density is proportional to the slope variation of the input analog signal regardless of the instantaneous amplitude. The front-end chip can detect the minimum slope variation of 3.2 mV/ms<inline-formula><tex-math notation="LaTeX">^2</tex-math></inline-formula> within a 3 ms timing error. The front-end integrated circuit was fabricated with a 180 nm CMOS process occupying a 0.25 mm<inline-formula><tex-math notation="LaTeX">^2</tex-math></inline-formula> area with a 151 nW power consumption at the sampling rate of 1 kS/s. Based on the slope variation obtained from the front-end circuit, a delineation algorithm is designed to detect fiducial points in the ECG waveform. The delineation algorithm was tested on a Spartan-6 FPGA. The delineation system can detect the intervals, slopes, and morphology of the QRS/PT waves and form a feature set that contains 22 features. Based on these features, a rotate linear kernel support vector machine (SVM) is applied for patient-specific arrhythmia classification of the ventricular ectopic beat (VEB), supraventricular ectopic beat (SVEB), and heartbeats originating in sinus node. The performance of the proposed system is comparable to the recently published methods while providing a promising solution for the low-complexity implementation of future wearable ECG monitoring systems.