High accurate detection method for aortic valve opening of seismocardiography signals

Chundi Zheng, Weiming Peng, Tianyao Huang, Yonina C. Eldar, Meiyi Yu

Research output: Contribution to journalArticlepeer-review

Abstract

Accurately detecting the aortic valve opening (AO) peaks of seismocardiography (SCG) is a challenging problem due to interference of other morphological inflection points. In this paper, a high accurate method is proposed to extract AO peaks based solely upon the SCG data. The raw SCG signal is purified by a simple first order interference cancellation method, resulting in a reduced number of modes to be decomposed. The purified SCG signal is then decomposed into a series of quasi-orthogonal modes by successive variational mode decomposition (SVMD) without any prior about the number of modes. Considering the pulsatile nature of the AO signal, a waveform factor criterion is proposed to reconstruct the AO signal based on the pulsatile level of each mode. A seventh power law detector is designed to amplify the AO peak and suppress spurious peaks. The publicly available combined measurement of electrocardiogram (ECG), breathing and seismocardiograms (CEBS) database is exploited to verify the performance of the proposed method. We show that the average sensitivity of our technique is 99.02%, the prediction rate is 99.06%, and the detection accuracy is 98.10%, which is superior to several state-of-the-art methods. In addition, compared with the ECG reference value, the instantaneous heart rate extracted by the proposed method is in good agreement with that of the ECG, e.g., the maximum average absolute error percentage is as low as 2.11 and the maximum average value relative error is about 0.03, further demonstrating that the proposed method can achieve accurate estimates of heart rate with an accelerometer alone.

Original languageEnglish
Article number105484
Number of pages13
JournalBiomedical Signal Processing and Control
Volume87
DOIs
StatePublished - Jan 2024

Keywords

  • AO peak estimation
  • Heart rate estimation
  • Heartbeat detection
  • Seismocardiography (SCG)
  • Vital sign monitoring

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Fingerprint

Dive into the research topics of 'High accurate detection method for aortic valve opening of seismocardiography signals'. Together they form a unique fingerprint.

Cite this