PMID- 35512699
OWN - NLM
STAT- MEDLINE
DCOM- 20220701
LR  - 20220705
IS  - 1361-6579 (Electronic)
IS  - 0967-3334 (Linking)
VI  - 43
IP  - 6
DP  - 2022 Jun 28
TI  - A multi-scale and multi-domain heart sound feature-based machine learning model 
      for ACC/AHA heart failure stage classification.
LID - 10.1088/1361-6579/ac6d40 [doi]
AB  - Objective.Heart sounds can reflect detrimental changes in cardiac mechanical 
      activity that are common pathological characteristics of chronic heart failure 
      (CHF). The ACC/AHA heart failure (HF) stage classification is essential for 
      clinical decision-making and the management of CHF. Herein, a machine learning 
      model that makes use of multi-scale and multi-domain heart sound features was 
      proposed to provide an objective aid for ACC/AHA HF stage 
      classification.Approach.A dataset containing phonocardiogram (PCG) signals from 
      275 subjects was obtained from two medical institutions and used in this study. 
      Complementary ensemble empirical mode decomposition and tunable-Q wavelet 
      transform were used to construct self-adaptive sub-sequences and multi-level 
      sub-band signals for PCG signals. Time-domain, frequency-domain and nonlinear 
      feature extraction were then applied to the original PCG signal, heart sound 
      sub-sequences and sub-band signals to construct multi-scale and multi-domain 
      heart sound features. The features selected via the least absolute shrinkage and 
      selection operator were fed into a machine learning classifier for ACC/AHA HF 
      stage classification. Finally, mainstream machine learning classifiers, including 
      least-squares support vector machine (LS-SVM), deep belief network (DBN) and 
      random forest (RF), were compared to determine the optimal model.Main results. 
      The results showed that the LS-SVM, which utilized a combination of multi-scale 
      and multi-domain features, achieved better classification performance than the 
      DBN and RF using multi-scale or/and multi-domain features alone or together, with 
      average sensitivity, specificity, and accuracy of 0.821, 0.955 and 0.820 on the 
      testing set, respectively.Significance.PCG signal analysis provides efficient 
      measurement information regarding CHF severity and is a promising noninvasive 
      method for ACC/AHA HF stage classification.
CI  - (c) 2022 Institute of Physics and Engineering in Medicine.
FAU - Zheng, Yineng
AU  - Zheng Y
AUID- ORCID: 0000-0003-1698-6399
AD  - Department of Radiology, The First Affiliated Hospital of Chongqing Medical 
      University, Chongqing 400016, People's Republic of China.
AD  - State Key Laboratory of Ultrasound in Medicine and Engineering, Chongqing Medical 
      University, Chongqing 400016, People's Republic of China.
AD  - Medical Data Science Academy, Chongqing Medical University, Chongqing 400016, 
      People's Republic of China.
FAU - Guo, Xingming
AU  - Guo X
AUID- ORCID: 0000-0003-3872-0866
AD  - Key Laboratory of Biorheology Science and Technology, Ministry of Education, 
      College of Bioengineering, Chongqing University, Chongqing 400044, People's 
      Republic of China.
FAU - Wang, Yingying
AU  - Wang Y
AD  - Department of Cardiology, The First Affiliated Hospital of Chongqing Medical 
      University, Chongqing 400016, People's Republic of China.
FAU - Qin, Jian
AU  - Qin J
AD  - Department of Cardiology, The First Affiliated Hospital of Chongqing Medical 
      University, Chongqing 400016, People's Republic of China.
FAU - Lv, Fajin
AU  - Lv F
AD  - Department of Radiology, The First Affiliated Hospital of Chongqing Medical 
      University, Chongqing 400016, People's Republic of China.
AD  - State Key Laboratory of Ultrasound in Medicine and Engineering, Chongqing Medical 
      University, Chongqing 400016, People's Republic of China.
AD  - Medical Data Science Academy, Chongqing Medical University, Chongqing 400016, 
      People's Republic of China.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20220628
PL  - England
TA  - Physiol Meas
JT  - Physiological measurement
JID - 9306921
SB  - IM
MH  - Algorithms
MH  - *Heart Failure
MH  - *Heart Sounds
MH  - Humans
MH  - Machine Learning
MH  - Phonocardiography
MH  - Support Vector Machine
OTO - NOTNLM
OT  - ACC/AHA heart failure stages
OT  - chronic heart failure
OT  - classification
OT  - heart sounds
EDAT- 2022/05/06 06:00
MHDA- 2022/07/02 06:00
CRDT- 2022/05/05 18:52
PHST- 2022/02/07 00:00 [received]
PHST- 2022/05/05 00:00 [accepted]
PHST- 2022/05/06 06:00 [pubmed]
PHST- 2022/07/02 06:00 [medline]
PHST- 2022/05/05 18:52 [entrez]
AID - 10.1088/1361-6579/ac6d40 [doi]
PST - epublish
SO  - Physiol Meas. 2022 Jun 28;43(6). doi: 10.1088/1361-6579/ac6d40.