An open access database for the evaluation of heart sound algorithms

• Type of Material: Article
• Authors: Chengyu Liu, Emory University; David Springer, University of Oxford; Qiao Li, Emory University; Benjamin Moody, Massachusetts Institute of Technology; Ricardo Abad Juan, Georgia Institute of Technology; Francisco J. Chorro, Universitat Politecnica de Valencia; Francisco Castells, Universitat Politecnica de Valencia; Jose Millet Roig, Universitat Politecnica de Valencia; Ikaro Silva, Massachusetts Institute of Technology; Alistair E.W. Johnson, Massachusetts Institute of Technology; Zeeshan Syed, University of Michigan; Samuel E. Schmidt, Aalborg University; Chrysa D. Papadaniil, Aristotle University of Thessaloniki; Leontios Hadjileontiadis, Aristotle University of Thessaloniki; Hosein Naseri, KN Toosi University of Technology; Ali Moukadem, University of Haute Alsace; Alain Dieterlen, University of Haute Alsace; Christian Brandt, Hospital University of Strasbourg; Hong Tang, Dalian University of Technology; Maryam Samieinasab, Shiraz University; Mohammad Reza Samieinasab, Isfahan University Medical Science; Reza Sameni, Emory University; Roger G. Mark, Massachusetts Institute of Technology; Gari Clifford, Emory University
• Language: English
• Date: 2016-12-01
• Publisher: IOP Publishing Ltd.
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2016 Institute of Physics and Engineering in Medicine.
• Final Published Version (URL): http://dx.doi.org/10.1088/0967-3334/37/12/2181
• Title of Journal or Parent Work: Physiological Measurement
• Volume: 37
• Issue: 12
• Start Page: 2181
• End Page: 2213
• Grant/Funding Information: This work was supported by the National Institutes of Health (NIH) grant R01- EB001659 from the National Institute of Biomedical Imaging and Bioengineering (NIBIB) and R01GM104987 from the National Institute of General Medical Sciences.
• Keywords: database; Features; Engineering, Biomedical; Technology; Segmentation; heart sound; Engineering; Artificial neural network; heart sound segmentation; Physiology; Classification; Diagnosis; phonocardiogram (PCG); Biophysics; Feature extraction; Life Sciences & Biomedicine; Signal; Science & Technology; heart sound classification; Identification; PhysioNet/CinC Challenge; Time frequency representations; Wavelet transform
• Research Categories: Engineering, Biomedical; Biology, Physiology; Biophysics, General; Engineering, Electronics and Electrical

Abstract

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.