Heart Murmur Detection from Phonocardiogram Recordings: The George B. Moody PhysioNet Challenge 2022

Congenital heart diseases affect about 1% of newborns, representing an
important morbidity and mortality factor for several severe conditions,
including advanced heart failure [[1](https://moody-
challenge.physionet.org/2022/#Burstein19)]. In a 2019 survey, it was estimated
that congenital heart diseases affect over 500,000 children in East Africa
[[2](https://moody-challenge.physionet.org/2022/#Jivanji19)], and about 8 in
every 1000 live births [[3](https://moody-
challenge.physionet.org/2022/#Zuhlke13)]. Acquired heart diseases include
rheumatic fever and the Kawasaki disease, the former being a serious public
health problem in developing regions, e.g., rural Brazil [[4](https://moody-
challenge.physionet.org/2022/#Carvalho12)]. Several regions of developing
countries have difficulties in diagnosing and treating both congenital and
acquired heart conditions in children. This is mainly due to the lack of
infrastructure and cardiology specialists in geographically large areas and
difficulty in accessing health services. In addition, the current COVID-19
pandemic poses new difficulties in the clinical evaluation of patients by
delaying important in-person patient-doctor contacts, negatively impacting
screening and monitoring activities.

A non-invasive assessment of the mechanical function of the heart, performed
at point-of-care settings, can provide early information regarding congenital
and acquired heart diseases in children. The lack of early diagnoses of these
conditions represents a major public health problem, especially in
underprivileged countries with high birth rates [[5](https://moody-
challenge.physionet.org/2022/#Tandon10), [6](https://moody-
challenge.physionet.org/2022/#Seckeler11), [7](https://moody-
challenge.physionet.org/2022/#Gheorghe18)]. In particular, cardiac
auscultation and the analysis of the phonocardiogram (PCG) can unveil
fundamental clinical information regarding heart malfunctioning caused by
congenital and acquired heart disease in pediatric populations. This is
achieved by detecting abnormal sound waves, or heart murmurs, in the PCG
signal. Murmurs are abnormal waves generated by turbulent blood flow in
cardiac and vascular structures. They are closely associated with specific
diseases such as septal defects, failure of ductus arteriosus closure in
newborns, and defective cardiac valves.

Succedent the [2016 Challenge](/content/challenge-2016/), which focused on
classifying normal vs. abnormal heart sounds from a single short recording
from a single precordial location [[8](https://moody-
challenge.physionet.org/2022/#Clifford16), [9](https://moody-
challenge.physionet.org/2022/#Clifford17)], this year's Challenge is devoted
to detecting the presence or absence of murmurs from multiple heart sound
recordings from multiple auscultation locations, as well as detecting the
clinical outcomes.

先天性心脏病（Congenital heart diseases）约影响1%的新生儿，是多种重症（包括晚期心力衰竭）的重要发病与死亡诱因[[1](https://moody-challenge.physionet.org/2022/#Burstein19)]。2019年的一项调查估计，东非地区超过50万名儿童受先天性心脏病影响[[2](https://moody-challenge.physionet.org/2022/#Jivanji19)]，每1000例活产婴儿中约有8例患病[[3](https://moody-challenge.physionet.org/2022/#Zuhlke13)]。获得性心脏病包括风湿热与川崎病，其中风湿热在巴西农村等发展中地区是一项严峻的公共卫生问题[[4](https://moody-challenge.physionet.org/2022/#Carvalho12)]。发展中国家的多个区域在儿童先天性与获得性心脏病的诊断与治疗方面存在困难，这主要源于广袤地域内基础设施与心脏专科医师的匮乏，以及医疗服务可及性不足。此外，当前的COVID-19大流行通过延迟重要的面对面医患沟通，为患者的临床评估带来了新的挑战，对筛查与监测活动造成了负面影响。

在床旁（point-of-care）场景下开展的心脏机械功能无创评估，可为儿童先天性与获得性心脏病提供早期预警信息。这类疾病的早期诊断缺失是一项重大公共卫生难题，在出生率较高的欠发达国家尤为突出[[5](https://moody-challenge.physionet.org/2022/#Tandon10), [6](https://moody-challenge.physionet.org/2022/#Seckeler11), [7](https://moody-challenge.physionet.org/2022/#Gheorghe18)]。具体而言，心脏听诊与心音图（phonocardiogram, PCG）分析可揭示儿科人群中由先天性与获得性心脏病引发的心脏功能异常的关键临床信息，这通过检测心音图信号中的异常声波即心杂音得以实现。心杂音是由心脏与血管结构内的血液湍流产生的异常声波，与室间隔缺损、新生儿动脉导管未闭、心脏瓣膜功能异常等特定疾病密切相关。

继2016年挑战赛[[8](https://moody-challenge.physionet.org/2022/#Clifford16), [9](https://moody-challenge.physionet.org/2022/#Clifford17)]——该赛事聚焦于从单个心前区位置的单次短时录音中区分正常与异常心音——之后，本届挑战赛将致力于从多个听诊位置获取的多组心音录音中检测心杂音的存在与否，并同时识别临床结局。

搜集汇总

背景与挑战

背景概述

该数据集是2022年PhysioNet挑战赛的核心资源，专注于从心音图记录中检测心脏杂音，旨在辅助儿童先天性或获得性心脏疾病的早期诊断。数据来源于巴西东北部儿科患者（1568名，21岁及以下），包含从多个听诊位置采集的心音图音频、人口统计信息以及杂音和临床结果标签，适用于开发机器学习算法进行自动分类。