An open access database for the evaluation of heart sound algorithms

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.

Abnormal Heart Sounds Detected from Short Duration Unsegmented Phonocardiograms by Wavelet Entropy

“…The dataset used in this study comprised a training set and test set and is described more completely elsewhere [2]. The algorithm was developed in the Matlab environment.…”

“…Current classification algorithms typically segment and analyse specific heart sounds such as first (S1) and second (S2) heart sounds or the associated diastolic and systolic intervals [2]. However, segmentation of the heart sounds is in itself challenging, particularly in abnormal recordings where there is often less distinction between the individual heart sounds.…”

Identification of Abnormal Heart Sounds

“…For training set an overall 3239 recordings was considered from 764 subject with 79.5% and 20.5% of the dataset corresponding to respectively normal and abnormal instances. The hidden test set comprised of 1353 recording from 308 subjects with 11.3% abnormal, 72.8% normal and 15.9% unsure instances [2].…”

“…In abnormal cases, various markers maybe present beside the fundamental heart sounds such as murmurs. Murmurs are noise-like high frequency sounds and long systolic murmurs as well as diastolic and continuous murmurs are generally pathologic [2].…”

“…In abnormal cases, various markers maybe present beside the fundamental heart sounds such as murmurs. Murmurs are noise-like high frequency sounds and long systolic murmurs as well as diastolic and continuous murmurs are generally pathologic [2].Auscultation is a common cost-effective technique that provides valuable information about heart valve problems. However, by listening to mechanical activity of the heart with a stethoscope, physicians cannot examine all physical characteristics of heart sounds, as it has been shown that only limited activity of heart sounds and murmurs are within human audibility range [1] [3].…”