CARDIOVASCULAR JOURNAL OF AFRICA • Vol 23, No 7, August 2012
AFRICA
405
Review Article
The promise of computer-assisted auscultation in
screening for structural heart disease and clinical
teaching
L ZÜHLKE, L MYER, BM MAYOSI
Abstract
Cardiac auscultation has been the central clinical tool for
the diagnosis of valvular and other structural heart diseases
for over a century. Physicians acquire competence in this
technique through considerable training and experience. In
Africa, however, we face a shortage of physicians and have the
lowest health personnel-to-population ratio in the world. One
of the proposed solutions for tackling this crisis is the adop-
tion of health technologies and product innovations to support
different cadres of health workers as part of task shifting.
Computer-assisted auscultation (CAA) uses a digital
stethoscope combined with acoustic neural networking to
provide a visual display of heart sounds and murmurs, and
analyses the recordings to distinguish between innocent and
pathological murmurs. In so doing, CAA may serve as an
objective tool for the screening of structural heart disease
and facilitate the teaching of cardiac auscultation. This
article reviews potential clinical applications of CAA.
Keywords:
auscultation, screening for cardiac disease, clinical
teaching, primary healthcare
Submitted 10/11/11, accepted 3/2/12
Published online 23/2/12
Cardiovasc J Afr
2012;
23
: 405–408
DOI: 10.5830/CVJA-2012-007
Prior to the development of echocardiography and
other imaging modalities, the stethoscope was the central
investigative tool for the diagnosis of structural heart disease.
While the stethoscope is relatively inexpensive and widely
available, it remains a qualitative and subjective method of
evaluating heart sounds, murmurs and other cardiac noises.
The development of the digital stethoscope with additional
analysis software promises to transform the stethoscope into
a tool for quantitative and objective clinical evaluation of the
heart. Such a tool may improve the assessment of innocent
murmurs, reduce observer variation due to human acoustic
abilities, and facilitate the teaching of cardiac auscultation.
The assessment of innocent murmurs
Up to 80% of paediatric patients have a cardiac murmur,
although less than 1% will eventually have a pathological
condition underlying the murmur.
1
Praecordial murmurs are also
common among young adults, occurring in between 29 and 52%
of the general population.
2
The ability to distinguish between an
innocent and a pathological murmur is therefore a fundamental
clinical skill that should be imparted to doctors and other
healthcare professionals involved in the screening and diagnosis
of heart disease.
The innocent murmur is, however, the most frequently
misdiagnosed condition when testing auscultation skills of
medical practitioners.
3
As a consequence, large numbers of
patients with an innocent murmur are inappropriately referred
for echocardiography, which has serious economic implications,
in addition to causing undue concern among healthy individuals
and their families.
4
Echocardiography is the first-line imaging modality for the
confirmation of a diagnosis of structural heart disease.
5
The
American HeartAssociation andAmerican College of Cardiology
define a class 1 recommendation for echocardiography as:
‘where clinical features indicate at least a moderate probability
that a murmur reflects structural heart disease’.
6
These guidelines discourage the indiscriminate use of
echocardiography as a screening tool due to the cost and the
potential for overdiagnosis of disease. Despite this, patients
are still referred inappropriately for echocardiography for the
evaluation of innocent murmurs. In a retrospective review of 3
460 adult referrals for echocardiogram with the coding ‘murmur’
as the primary reason for referral, less than 50% had significant
valvular disease.
7
A study in Norway showed that only 10% of
children referred to a cardiac centre for investigation of a cardiac
murmur were subsequently found to have a congenital cardiac
lesion.
8
The majority of these children (71%) were referred by
general practitioners, though in only 17% was a diagnosis made
by the referring physician.
There is therefore a major need to improve the ability of
School of Adolescent and Child Health, Red Cross War
Memorial Children’s Hospital, and Department of Medicine,
University of Cape Town, Cape Town, South Africa
L ZÜHLKE, MB ChB, DCH, FCPaed (SA), Cert Cardiology (Paed),
MPH,
School of Public Health and Family Medicine, University of
Cape Town, Cape Town, South Africa
L MYER, PhD, MB ChB, MPhil, MA, BA
Department of Medicine, Groote Schuur Hospital and
University of Cape Town, Cape Town, South Africa
BM MAYOSI, DPhil, FCP (SA)
