An open access database for the evaluation of heart sound algorithms

被引:481
作者
Liu, Chengyu [1 ]
Springer, David [2 ]
Li, Qiao [1 ]
Moody, Benjamin [3 ]
Juan, Ricardo Abad [4 ,5 ]
Chorro, Francisco J. [6 ]
Castells, Francisco [5 ]
Roig, Jose Millet [5 ]
Silva, Ikaro [3 ]
Johnson, Alistair E. W.
Syed, Zeeshan [7 ]
Schmidt, Samuel E. [8 ]
Papadaniil, Chrysa D. [9 ]
Hadjileontiadis, Leontios [9 ]
Naseri, Hosein [10 ]
Moukadem, Ali [11 ]
Dieterlen, Alain [11 ]
Brandt, Christian [12 ]
Tang, Hong [13 ]
Samieinasab, Maryam [14 ]
Samieinasab, Mohammad Reza [15 ]
Sameni, Reza [14 ]
Mark, Roger G. [3 ]
Clifford, Gari D. [1 ,4 ]
机构
[1] Emory Univ, Dept Biomed Informat, Atlanta, GA 30322 USA
[2] Univ Oxford, Dept Engn Sci, Inst Biomed Engn, Oxford, England
[3] MIT, Inst Med Engn & Sci, 77 Massachusetts Ave, Cambridge, MA 02139 USA
[4] Georgia Inst Technol, Dept Biomed Engn, Atlanta, GA 30332 USA
[5] Univ Politecn Valencia, ITACA Inst, Valencia, Spain
[6] Univ Valencia, Clin Hosp, Serv Cardiol, INCLIVA, Valencia, Spain
[7] Univ Michigan, Dept Biomed Engn, Ann Arbor, MI 48109 USA
[8] Aalborg Univ, Dept Hlth Sci & Technol, Aalborg, Denmark
[9] Aristotle Univ Thessaloniki, Dept Elect & Comp Engn, Thessaloniki, Greece
[10] KN Toosi Univ Technol, Dept Mech Engn, Tehran, Iran
[11] Univ Haute Alsace, MIPS Lab, Mulhouse, France
[12] Hosp Univ Strasbourg, Mulhouse, France
[13] Dalian Univ Technol, Fac Elect & Elect Engn, Dalian, Peoples R China
[14] Shiraz Univ, Sch Elect & Comp Engn, Shiraz, Iran
[15] Isfahan Univ Med Sci, Dept Med, Esfahan, Iran
基金
美国国家卫生研究院;
关键词
heart sound; phonocardiogram (PCG); database; heart sound classification; heart sound segmentation; PhysioNet/CinC Challenge; TIME-FREQUENCY REPRESENTATIONS; ARTIFICIAL NEURAL-NETWORK; SEGMENTATION ALGORITHM; FEATURE-EXTRACTION; WAVELET TRANSFORM; SIGNAL; CLASSIFICATION; IDENTIFICATION; DIAGNOSIS; FEATURES;
D O I
10.1088/0967-3334/37/12/2181
中图分类号
Q6 [生物物理学];
学科分类号
071011 ;
摘要
In the past few decades, analysis of heart sound signals (i.e. the phonocardiogram or PCG), especially for automated heart sound segmentation and classification, has been widely studied and has been reported to have the potential value to detect pathology accurately in clinical applications. However, comparative analyses of algorithms in the literature have been hindered by the lack of high-quality, rigorously validated, and standardized open databases of heart sound recordings. This paper describes a public heart sound database, assembled for an international competition, the PhysioNet/Computing in Cardiology (CinC) Challenge 2016. The archive comprises nine different heart sound databases sourced from multiple research groups around the world. It includes 2435 heart sound recordings in total collected from 1297 healthy subjects and patients with a variety of conditions, including heart valve disease and coronary artery disease. The recordings were collected from a variety of clinical or nonclinical (such as in-home visits) environments and equipment. The length of recording varied from several seconds to several minutes. This article reports detailed information about the subjects/patients including demographics (number, age, gender), recordings (number, location, state and time length), associated synchronously recorded signals, sampling frequency and sensor type used. We also provide a brief summary of the commonly used heart sound segmentation and classification methods, including open source code provided concurrently for the Challenge. A description of the PhysioNet/CinC Challenge 2016, including the main aims, the training and test sets, the hand corrected annotations for different heart sound states, the scoring mechanism, and associated open source code are provided. In addition, several potential benefits from the public heart sound database are discussed.
引用
收藏
页码:2181 / 2213
页数:33
相关论文
共 66 条
[1]   Feature extraction for systolic heart murmur classification [J].
Ahlstrom, Christer ;
Hult, Peter ;
Rask, Peter ;
Karlsson, Jan-Erik ;
Nylander, Eva ;
Dahlstrom, Ulf ;
Ask, Per .
ANNALS OF BIOMEDICAL ENGINEERING, 2006, 34 (11) :1666-1677
[2]   NONINVASIVE DETECTION OF CORONARY-ARTERY DISEASE [J].
AKAY, YM ;
AKAY, M ;
WELKOWITZ, W ;
KOSTIS, J .
IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE, 1994, 13 (05) :761-764
[3]  
[Anonymous], 2001, UNDERSTANDING HEART
[4]  
Ari S., 2008, Journal of Medical Engineering & Technology, V32, P456, DOI 10.1080/03091900601015162
[5]   Detection of cardiac abnormality from PCG signal using LMS based least square SVM classifier [J].
Ari, Samit ;
Hembram, Koushik ;
Saha, Goutam .
EXPERT SYSTEMS WITH APPLICATIONS, 2010, 37 (12) :8019-8026
[6]   Feature Extraction From Parametric Time-Frequency Representations for Heart Murmur Detection [J].
Avendano-Valencia, L. D. ;
Godino-Llorente, J. I. ;
Blanco-Velasco, M. ;
Castellanos-Dominguez, G. .
ANNALS OF BIOMEDICAL ENGINEERING, 2010, 38 (08) :2716-2732
[7]  
Bentley P, 2011, CLASSIFYING HEART SO
[8]   Time-frequency and time-scale techniques for the classification of native and bioprosthetic heart valve sounds [J].
Bentley, PM ;
Grant, PM ;
McDonnell, JTE .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 1998, 45 (01) :125-128
[9]   A classifier based on the artificial neural network approach for cardiologic auscultation in pediatrics [J].
Bhatikar, SR ;
DeGroff, C ;
Mahajan, RL .
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2005, 33 (03) :251-260
[10]  
Castro A, 2013, IEEE ENG MED BIO, P3909, DOI 10.1109/EMBC.2013.6610399