Data-Driven Approach for Automatic Detection of Aortic Valve Opening: B point Detection from Impedance Cardiogram

• Type of Material: Article
• Authors: Shafa-at Ali Sheikh, Emory University; Nil Z. Gurel, University of California, Los Angeles; Shishir Gupta, Emory University; Ikenna V. Chukwu, Emory University; Oleksiy Levantsevych, Emory University; Mhmtjamil Alkhalaf, Emory University; Majd Soudan, Emory University; Rami Abdulbaki, Emory University; Ammer Haffar, Emory University; Viola Vaccarino, Emory University; Omer T. Inan, Georgia Institute of Technology; Amit Shah, Emory University; Gari D. Clifford, Emory University; Ali Bahrami Rad, Emory University
• Language: English
• Date: 2022-06-19
• Publisher: John Wiley and Sons
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2022 Society for Psychophysiological Research.
• Final Published Version (URL): https://doi.org/10.1111/psyp.14128
• Title of Journal or Parent Work: Psychophysiology
• Volume: 59
• Issue: 12
• Start Page: e14128
• Grant/Funding Information: Shafa-at Ali Sheikh is funded by Fulbright Scholarship Program. The authors wish to acknowledge the National Institutes of Health (Grant # NIH K23HL127251, R01HL136205, R01HL125246, R01 AG026255, and R03HL146879), the National Science Foundation Award 1636933, and Emory University for their financial support of this research.
• Keywords: impedance cardiogram (ICG) signals; Pre-ejection period
• Research Categories: Engineering, Biomedical; Biology, Physiology

Abstract

Pre-ejection period (PEP), an indicator of sympathetic nervous system activity, is useful in psychophysiology and cardiovascular studies. Accurate PEP measurement is challenging and relies on robust identification of the timing of aortic valve opening, marked as the B point on impedance cardiogram (ICG) signals. The ICG sensitivity to noise and its waveform’s morphological variability makes automated B point detection difficult, requiring inefficient and cumbersome expert-visual annotation. In this paper, we propose a machine-learning-based automated algorithm to detect the aortic valve opening for PEP measurement, which is robust against noise and ICG morphological variations. We analyzed over 60 hours of synchronized ECG and ICG records from 189 subjects. A total of 3,657 averaged beats were formed using our recently developed ICG noise removal algorithm. Features such as the averaged ICG waveform, its first and second derivatives, as well as high-level morphological and critical hemodynamic parameters were extracted and fed into the regression algorithms to estimate the B point location. The morphological features were extracted from our proposed “variable” physiologically valid search-window related to diverse B point shapes. A subject-wise nested cross-validation procedure was performed for parameter tuning and model assessment. After examining multiple regression models, Adaboost was selected, which demonstrated superior performance and higher robustness to five state-of-the-art algorithms that were evaluated in terms of low mean absolute error of 3.5 ms, low median absolute error of 0.0 ms, high correlation with experts’ estimates (Pearson coefficient = 0.9), and low standard deviation of errors of 9.2 ms. For reproducibility, an open-source toolbox is provided.