TY - JOUR
T1 - Efficient syncope prediction from resting state clinical data using wavelet bispectrum and multilayer perceptron neural network
AU - Myrovali, Evangelia
AU - Fragakis, Nikolaos
AU - Vassilikos, Vassilios
AU - Hadjileontiadis, Leontios J.
N1 - Funding Information:
The authors would like to thank the patients that voluntary participated in the HUTT and provided their data for the current research work. They also want to thank the medical and nursing staff of the Third Cardiology Department, Hippocration Hospital for the excellent cooperation. The authors are also grateful to Mr. A. Fotoglidis for his assistance in data collection and to Dr. A. Antoniadis for his valuable suggestions and comments on the manuscript.
Publisher Copyright:
© 2021, International Federation for Medical and Biological Engineering.
PY - 2021/6
Y1 - 2021/6
N2 - Neurally mediated syncope (NMS) is the most common type of syncope, and head up tilt test (HUTT) is, so far, the most appropriate tool to identify NMS. In this work, an effort to predict the NMS before performing the HUTT is attempted. To achieve this, the heart rate variability (HRV) at rest and during the first minutes of tilting position during HUTT was analyzed using both time and frequency domains. Various features from HRV regularity and complexity, along with wavelet higher-order spectrum (WHOS) analysis in low-frequency (LF) and high-frequency (HF) bands were examined. The experimental results from 26 patients with history of NMS have shown that at rest, a time domain entropy measure and WHOS-based features in LF band exhibit significant differences between positive and negative HUTT as well as among 10 healthy subjects and NMS patients. The best performance of multilayer perceptron neural network (MPNN) was achieved by using an input vector consisted of WHOS-based HRV features in the LF zone and systolic blood pressure from the resting period, yielding an accuracy of 89.7%, assessed by 5-fold cross-validation. The promising results presented here pave the way for an early prediction of the HUTT outcome from resting state, contributing to the identification of patients at higher risk NMS. [Figure not available: see fulltext.]
AB - Neurally mediated syncope (NMS) is the most common type of syncope, and head up tilt test (HUTT) is, so far, the most appropriate tool to identify NMS. In this work, an effort to predict the NMS before performing the HUTT is attempted. To achieve this, the heart rate variability (HRV) at rest and during the first minutes of tilting position during HUTT was analyzed using both time and frequency domains. Various features from HRV regularity and complexity, along with wavelet higher-order spectrum (WHOS) analysis in low-frequency (LF) and high-frequency (HF) bands were examined. The experimental results from 26 patients with history of NMS have shown that at rest, a time domain entropy measure and WHOS-based features in LF band exhibit significant differences between positive and negative HUTT as well as among 10 healthy subjects and NMS patients. The best performance of multilayer perceptron neural network (MPNN) was achieved by using an input vector consisted of WHOS-based HRV features in the LF zone and systolic blood pressure from the resting period, yielding an accuracy of 89.7%, assessed by 5-fold cross-validation. The promising results presented here pave the way for an early prediction of the HUTT outcome from resting state, contributing to the identification of patients at higher risk NMS. [Figure not available: see fulltext.]
KW - HRV time domain features
KW - Multilayer perceptron neural network
KW - Syncope characterization
KW - Wavelet higher-order spectral features
UR - http://www.scopus.com/inward/record.url?scp=85105533270&partnerID=8YFLogxK
U2 - 10.1007/s11517-021-02353-7
DO - 10.1007/s11517-021-02353-7
M3 - Article
C2 - 33959855
AN - SCOPUS:85105533270
SN - 0140-0118
VL - 59
SP - 1311
EP - 1324
JO - Medical and Biological Engineering and Computing
JF - Medical and Biological Engineering and Computing
IS - 6
ER -