13_cie39_asap_v1

Acquire, analyze and share auscultation sounds: the ASAP project  
 
Sandra Reichert1,2, Raymond Gass2, Amir Hajjam1, Abderrafiaa Koukam1, Gérard Nguyen3, Christian 
Brandt4, Emmanuel Andres4  
1SeT, UTBM, 90010 Belfort, France ([EMAIL], [EMAIL], 
[EMAIL]) 
2Alcatel-Lucent, 1 route du Dr Albert Schweitzer, 67400 Illkirch, France ([EMAIL]) 
3Hôpital Avicenne, CHU Bobigny, 25 rue de Stalingrad, 93009 Bobigny, France 
([EMAIL]) 
4Hôpital Civil, 1 place de l’hôpital, 67000 Strasbourg, France ([EMAIL], 
[EMAIL]) 
 
ABSTRACT 
Be able to distinguish and characterize abnormal auscultation sounds is important for an accurate medical  diagnosis. 
Even though several researches have been done on the analysis of auscultation sounds, today auscultation remains 
subjective and difficult to share. In the context of the MERCURE telemedicine platform, we started a project called 
ASAP. It deals in developing objective tools for the analysis of auscultation sounds and creating an auscultation sounds’ 
database in order to compare and identify the acoustical and visual signatures of the pathologies. Communication and 
network technologies are fundame ntal elements to be able to collect, document, share and transmit, in real time or not, 
auscultation sounds. Finally, the project aims at capitalizing of these new auscultation techniques around the creation of 
a teaching unit: the Auscultation’s School. 
Keywords: Auscultation’s School, pulmonary sound analysis, telemedicine platform 
1 
                                                         
1  2009-CIE39-FR. 
1. INTRODUCTION 
 
To collect and analyse auscultation sounds, we propose 
to put in place a new architecture  (that will be described 
more in details in paragraph 2  and figure 2). The collect 
of the sounds is realized thanks to a wireless digit 
stethoscope that communicates with a computing unit 
through a Bluetooth Medical Device Area. The 
computing unit can send the data through the network, 
in order to store them, share them ( with a colleague for 
a second opinion or with students for education); the 
collected data will be used for the fundamental 
researches that we started in the ASAP context. These 
researches deal with pulmonary sound analysis and the 
research of new markers characteristics in some specific 
pathologies. 
Actually, distinction between normal respiratory sounds 
and abnormal ones (such as crackles, wheezes ) is 
important for an accurate medical diagnosis. 
Respiratory sounds include invaluable information 
concerning the physiologies and pathologies of lungs 
and airways obstruction. Thus, the spectral density and 
amplitude of sounds can indicate the state of the lungs 
parenchyma, the dimension of the airways and their 
pathological modification [1]. 
 
Limits of human audition 
Studies were performed in order to test the human’s ear 
capability to detect crackles in an auscultation signal [2]. 
The methods used consist in simulated crack les 
superimposed on real breath sound. The results indicate 
that the most important detection errors are due to the 
intensity of the respiratory signal, the type of crackles 
and the amplitude of crackles. It can be inferred from 
these studies that the vali dation of automatic crackles 
detection algorithms should not take auscultation as 
unique reference. 
On the contrary, the understanding of mechanisms 
linked to the creation of breath sounds is, for the 
moment, imperfect. The recording and analysis of 
respiratory sounds allow to improve this understanding 
[3] and an objective relationship between abnormal 
respiratory sounds with respiratory pathology. Besides, 
an objective analysis allows to develop classification 
systems [4] that make it possible to precisely qualify 
normal and adventitious respiratory sounds. Whilst 
conventional stethoscope auscultation is subjective and 
hardly sharable, these systems should provide an 
objective and early diagnostic help, with a better 
sensitivity and reproducibility of the results. 
Moreover, applications, including diagnosis 
establishment, monitoring and data exchange through 
Internet are obviously complementary tools to objective 
and a utomatic auscultation sounds analysis. Sensors 
devices will allow long duration monitoring for patient 
at home or at hospital. It could also be a useful solution 
for less -developed countries and remote communities 
[5]. In addition, this type of system has the great 
advantage to keep the non -invasive and less expensive 
characteristics of auscultation. 
Finally, Sestini and coll.’s studies [6] indicate that an 
association between acoustical signal and its image is 
beneficial to the learning and understanding for students 
in medical science.

Definition of common markers 
Nowadays, there are several definitions for the typical 
markers of wheezes and crackles [7]. Thus, a universal 
semantic has to be created. Several works [8] have 
attempted to collect definitions of terms relating to 
respiratory sounds and have arrived at a collection of 
162 terms commonly used in the «  Computer 
Respiratory Sound Analysis » (CORSA).  Nevertheless, 
it still doesn’t allow physician to have a common 
definition of terms that are used. For example, a wheeze 
is still currently associated to a “whistling sound”, and a 
crackle to “a sound of rice in a frying pan”. 
 
Definition of semiology 
The article of Rossi and coll. [9] gives 
recommendations concerning the experimental 
conditions required for recording respiratory sou nds. It 
describes the optimal experimental conditions 
(principally concerning background noise, including 
sounds other than respiratory such as vocal sounds) and 
the specific procedures according to the type of sounds 
he wanted to record (breath, cough, snores), information 
for the recording (diagnosis, evaluation of a therapy, 
monitoring), the age of subject, and the recording 
method (free field, endobronchial microphone). Lastly, 
for short recordings, a sitting position is recommended, 
but a lay position is preferably for long recordings. 
 
2. ASAP : AN INNOV ATIVE E-HEALTH PROJECT 
 
2.1 Context 
 
ASAP or “ Analyse de Sons Auscultatoires et 
Pathologiques” is a 3 -year-long French collaborative 
project.  It is part of a collaborative telemedicine 
platform called «  MERCURE » ( Mobile Et Réseau 
pour la Clinique, l'Urgence ou la Résidence Externe ). 
MERCURE (figure 1) deals with projects for remote 
monitoring and clinical context thanks to modern tools 
principally coming from the News Technologies of 
Information and Communication. 
 
Fig. 1.  The MERCURE platform  
 
STETAU is the first project of the MERCURE platform; 
it aims at providing the patient and medical staff, 
measurement tools that are non -invasive, mobile, 
communicant and that allows to transmit vital 
information by a secured way, objectively qualified by 
signal processing tools. Thus, physicians will have 
access to a tool for remote monitoring and exploration 
of cardiac and pulmonary sounds. Besides, the proposed 
tools will be made up of an enhanced graphical u ser 
interface. 
The ASAP project, that we will describe more in details 
in the next paragraphs, deals with a worldwide database 
for respiratory sounds, statistical analysis of 
“pathological” sounds, search of new markers, set up of 
a medical school for ausc ultation and a worldwide 
experts network. 
The EPIDAURE project deals with emergency care 
services. The physician will be equipped with wireless 
measurement tools that communicate with a processing 
unit. It will allow him to have access to a first analysis,  
a diagnosis help, and a transmission for remote second 
analysis and saving in a patient database. In this project, 
we will also work on a dedicated call center for 
optimized handling of cars, specialists, tools and current 
location that will lean on geo -localisation and 
navigation. 
MERCURE is a project inside the hospital for the 
deployment of wireless measurement tools, notification 
servers, voice/data/video transmission, voice over 
WiFi/GSM with automatic handover, A -GPS and WiFi 
localization of people, equipment, drugs, foods. 
Finally, the last but not least project is REVES. It 
emphasizes on a robot -friend for children with 
leukaemia in sterile rooms.  The robot-friend is a “new 
multimedia terminal” equipped with a camera, a 
microphone, loudspeakers, Wi Fi transmission, 
geo-localization. It is connected to a call server plus 
video server, notification, etc. This project is realized in 
collaboration with teachers for the development of 
content (educative tools, gaming), and with hospitals 
practitioners (in tensive care unit) for pain stigma 
detection. 
 
2.2 Our value-added 
 
Some projects or products already propose an evolution 
of the stethoscope; we can quote in particular the 
stethoscope Littmann or Jabes.  Some firms propose as 
well as their stethoscope, a  CD-Rom with auscultation 
sounds. Nevertheless, they only allow a basic 
consultation with some examples, most theoretical, and 
that are neither interactive nor a diagnosis support. In 
addition, sounds are quite often synthetic sounds. 
In the ASAP project, our ambition is not to propose a 
stethoscope and to  additionally provide sounds, but the 
exact opposite. Indeed, we will propose a worldwide 
sound database with visual and acoustical signatures, 
that allow to consult and analyze sounds, perform 
standard ex change of data. These sounds will, all the 
more, be a support for learning auscultation.  From

those data, a worldwide auscultation sounds database 
will be created. It will list an important quantity of data 
and will allow to create models or criteria to i mprove 
detecting of pulmonary and cardiac diseases. Another 
innovative aspect of our project is to make diagnosis 
aid. 
 
2.3 Description of the ASAP project 
 
Auscultation is the first medical act that the medical 
students can realise on patients; it is real ised empirically. 
Our project proposes to introduce an evidence -based 
medicine dimension at auscultation thanks to the 
association with signal processing, visualisation and 
archiving technologies. These new technologies will be 
considered for the formation  of the future physicians 
and will be accessible through e-learning.  
ASAP aims at making evolve the auscultation 
techniques: 
 by the development objective tools for the 
analysis of auscultation sounds  : communicant 
wireless electronic stethoscope paired wi th 
computing device (like a PC or PDA) (figure 
2); 
 
Fig. 2.  Remote auscultation  
The physician can locally or remotely perform an 
auscultation, see the auscultation sounds on his PC, 
PDA or IP Phone; he can share it with students for 
education, store it locally or in the hospital’s database. 
 
 by the creation of an auscultation sounds’ 
database in order to compare and identify the 
acoustical and visual signatures of the 
pathologies; 
 by the capitalisation of these new auscultation 
techniques around the creat ion of a teaching 
unit : « Ecole de l’Auscultation  ». This 
auscultation’s school will be destined to the 
initial and continuous formation of the medical 
attendants. 
 
 
 
 
 
There are some major phases in the project (figure 3): 
 
Fig. 3.  ASAP project  
 
The fi rst point is the definition of the relevant 
semiology and thesaurus. It will allow to initialize a 
platform for collecting, validating, storing respiratory 
sounds. 
The next point is the realisation of a worldwide 
auscultation sounds database (WebSound) . 
Then, health professionals and medical students could 
use this database. The students would dispose of a 
diversified palette of sounds via new technologies of 
communication and information. It will allow to make 
continuous formations related to specific pat hologies. 
This will lead to the creation of the Auscultation’s 
School. 
Besides, in order to allow the connection of the 
information systems of the hospitals, further work is 
foreseen, to deal with the normalisation of the data 
formats and semantic. 
Afterwards, it will be possible to share auscultation 
sounds between experts, thanks to a unified format. The 
expert could discuss about a medical case, and refine the 
diagnosis. 
Finally, our project aims at initialising fundamental 
research works for the definit ion of a visual and 
acoustical signature of a pathology.  The first 
pathologies studied will be asthma, bronchitis, CODP 
and cardiac pathologies. The aim is to make auscultation 
more objective and intuit a pathology thanks to the 
symptoms. 
The success of t he projects is conditioned by the 
definition of standard formats of the data and exchange 
protocols. 
 
Application domains 
The applications can be telemedicine with local or  
remote us. Several medical specialties will be interested 
in such a tools, amon g remote monitoring for pat ients, 
second opinion, teaching. We can quote: 
 Pneumology, for patients affected with 
bronchiolitis, asthma, COPD, pneumopathy; 
 Cardiovascular; in particular V alvulopathy with 
the diagnostic of heart murmurs, search of

additional sou nds and peripheral arterial 
disease of the lower limbs, carotid stenosis; 
 Public health, for the prevention in school, 
professional environment; 
 Gynecology obstetrics for prenatal auscultation 
of the foetus health, teleconsultation of a 
specialist; 
 V eterinary. 
 
3. FIRST WORKS DEALING WITH THE 
IDENTIFICATION OF MARKERS 
 
In pulmonary sounds, known markers are crackles and 
wheezes. The principal algorithm families of detection 
of these markers are summarised in table 1. 
 
TABLE I 
THE PRINCIPAL ALGORITHM FAMILIES OF DETECTION OF THE KNOWN 
MARKERS 
SIGNAL CHARACTERISTICS 
AND PROCESSING 
[10] 
ANALYSIS  
Normal sounds 
Lungs Low-pass filtering 
(between 100 and 
1000 Hz) 
Periodogram (power spectral 
density  - PSD), auto - 
regressive models [11] 
Trachea Noise with 
resonances [100, 
3000 Hz] 
 
Adventitious sounds 
Wheezes Sinusoid (range ~ 
100 and 1000Hz; 
duration > 80ms) 
PSD, STFT(s hort-time Fourier 
transform)[11], FFT, linear 
prediction of coefficients  [12], 
genetic algorithms  [13], neural 
networks [13], wavelet  [14]  
Ronchus Series of sinusoid 
(<300Hz and a 
duration > 100ms) 
 
Crackles Wave deflection 
(duration typically  
< 20ms) 
Temporal analysis  [11], FFT, 
linear pr ediction of coefficients  
[12], fuzzy non stationary filter 
[12], genetic algorithms [13], 
neural networks  [13], 
wavelet[15] [16]  
Snores  Temporal analysis, PSD [11] 
Stridors  PSD, STFT, auto reg ressive 
models  [11] 
 
4. PERSPECTIVES: THE AUSCULTATION’S 
SCHOOL 
 
In a nutshell, it can be said that auscultation is an 
individual act, difficult to share. On the contrary, the 
Auscultation’s School will lean o n an objective 
definition of the sounds useful for teaching and 
diagnosis aid. Thanks to communications and network 
technologies, the Auscultation’s School will have for 
purpose to teach to student and professionals the new 
innovative tools. In the same wa y, research programs 
will try to detect new markers, detect pre -markers from 
some pathologies… 
The project begins by the scientific and clinical 
validation of the service and ergonomic for several 
pathologies: COPD, asthma, and bronchitis, and 
cardiopathies. This step allows to collect auscultation 
sounds that are characterized, documented and qualified. 
The final goal is to create a worldwide referential 
interconnected to medical study centres, pharmaceutical 
research laboratories and auscultation sounds processing 
systems. 
Empirical methods provides already results to show the 
value added of the analysis and the comparison of the 
sounds for instance for the correlation between the 
pulmonary  blocking of a patient with cystic fibrosis 
and the rate of detect ed crackles, the evolution of the 
acoustic signature of a cardiac valve, ...  
The main strengths of such a referential are: 
 improving the incontrovertible medical act that 
is auscultation, by making it objective, and 
factual, to share, histories and compar e the 
data; 
 lean on the new technologies to push the 
exploitation of auscultation sounds as a non 
invasive exam and pertinent diagnosis aid and 
local or remote monitoring; 
 create a new language exploitable by all the 
profession. 
The different constitutive parts of the Auscultation’s 
School will be: 
 the good practices of auscultation : how to 
auscultate, what are the abnormalities 
researched; 
 the classical sounds in the various disciplines: 
Cardiology, Pneumo logy, Paediatric, 
Reanimation. The identification of crackles, 
wheezes, and their correlation with  the follow 
up of a pathology; 
 the new auscultation tools: the digital 
stethoscope, signal processing tools, 
visualisation of the sounds and interpretation of 
the obtained images; 
 the ongoing research project; 
 bibliographical references. 
The access to the teaching could be initial for medical 
students or ongoing training for experimented general 
practitioners. Modern learning tools will be privileged. 
This formation will be accessible by each medical 
professional, and maybe more.  
The first goal of such an initiative is the repositioning of 
the auscultation as a fundamental non -invasive exam in 
the medical diagnosis; while pushing to potentialities 
thanks to the new technologies. 
 
5. CONCLUSION 
 
Today, prototypes of the digital stethoscope have been 
tested by medical specialists. Algorithm have shown 
definitive contribution to the improvement of the 
auscultation act, in the context of the ASAP project. The 
next step will consist in analysing deeper the sounds 
with signal analysis techniques to allow the discovery of 
new characteristic markers. 
Real time remote auscultation, commented auscultation 
sounds transfer, education became possible thanks to the 
system we described.

Besides, we are working on protocols to  transmit, in a 
standardized way, auscultation data, associated with 
comments and medical information.  
Previous studies demonstrate the need of performing an 
exhaustive scientific approach, that account of both the 
definition of a semiology, the consolidation of definition 
of known characteristics markers, the definition of 
common or even universal semantics, the development 
of determinist tools that will allow the detection of these 
markers. It is precisely the context of an ambitious study 
of in the so -called ASAP project. This study is handled 
by a multidisciplinary team including medical from 
CHRU of Strasbourg, IRCAD for web -based teaching 
tools, Alcatel -Lucent research teams for the 
development of the devices, tools, ergonomic, 
algorithms and communic ation infrastructure. Among 
the most identified outcome from the project, it is force 
in to create auscultation school hosted by the ” Faculté 
de Médecine” of Strasbourg (France). 
 
ACKNOWLEDGEMENT 
 
This work has been performed in the framework of the 
projects from the platform MERCURE, and more 
specifically especially the ASAP project. We would like 
to acknowledge the partners of the project. 
 
GRANT 
 
ASAP project (ANR convention n° 2006 TLOG 21 04). 
 
REFERENCES 
 
[1] A.R. Sovijarvi, L.P. Malmberg, G. Charbonneau,  J. 
Vandershoot. “Characteristics of breath sounds and 
adventitious respiratory sounds”, Eur Respir Rev  
2000; 10: 591–596. 
[2] H. Kiyokawa, M. Greenberg, K. Shirota, H. 
Pasterkamp. “Auditory detection of stimulated 
crackles in breath sounds”, Chest 2006; 119: 
1886-1892. 
[3] M. Bahoura, «   Analyse des signaux acoustiques 
respiratoires: contribution à la detection automatique 
des sibilants par paquets d’ondelettes  », PhD 
Thesis Univ,  Univ. Rouen, France, 1999.  
[4] J.S. Chuah, Z.K. Moussavi, “Automated respiratory 
phase detection by acoustical means”, proc. Systems, 
Cybernetics & Informatics (SCI) Conference,  July 
2000, pp. 228-231. 
[5] J.E. Earis, B.M. Cheetham. “Future perspectives for 
respiratory sound research, Techniques for 
respiratory sound analysis”, Eur Respir Rev 2000; 10: 
636–640. 
[6] P. Sestini, E. Renzoni, M. Rossi, V. Beltrami, M. 
Vagliasindi. “Multimedia presentation of lung 
sounds as learning aid for medical students”, Eur 
Respir J 1995; 8: 783-788. 
[7] H.E. Elphick, P. Sherlock, G. Foxall, E.J. Simpson, 
N.A. Shiell, R .A. Primhak, M.L. Everard, “Survey 
of respiratory sounds in infants”,  Arch Dis Child  
2001; 84: 35-39. 
[8] A.R. Sovijarvi, F. Dalmasso, J. Vanderschoot, L.P. 
Malmberg, G. Righini, S.A. Stoneman, “Definition 
of terms for applications of respiratory sounds”, Eur 
Respir Rev 2000; 10: 597–610 
[9] M. Rossi, A.R. Sovijarvi, P. Piirila, L. Vannuccini, F. 
Dalmasso, J. Vanderschoot, “Environmental and 
subject conditions and breathing manœuvres for 
respiratory sound recordings”, Eur Respir Rev 2000; 
10: 611–615. 
[10] H. Pasterkam p, S.S. Kraman, G.R. Wodicka.  
“Respiratory sounds, advances beyond the 
stethoscope”, Am J Respir Crit Care Med 1997; 156: 
974-987. 
[11] G. Charbonneau, E. Ademovic, B.M. Cheetham, 
L.P. Malmberg, J. Vanderschoot, A.R. Sovijarvi, 
“Basic techniques for respirator y sound analysis”, 
Eur Respir Rev 2000; 10: 625–635.  
[12] A. Cohen, D. Landsberg, “Analysis and Automatic 
Classification of Breath Sounds”, IEEE Transactions 
on Biomedical Engineering 1984 ; 31(9) : 585-590. 
[13] Guler, H. Polat, U. Ergun, “Combining neural 
network and genetic algorithm for prediction of lung 
sounds”, J Med Syst 2005; 29: 217-231. 
[14] L. Hadjileontiadis, K. Panoulas, T. Penzel, V. 
Gross, S. Panas, “On applying continuous wavelet 
transform in wheeze analysis”, Engineering in 
Medicine and Biology Society IEEE 2004; 2: 
3832-3835. 
[15] M. Du, F.H.Y Chan, F.K. Lam, J. Sun, “Crackles 
detection and classification based on matched 
wavelet analysis”, IEEE / EMBS 1997 ; 1638-1641. 
[16] L. Hadjileontiadis, L. Rekanos, “Detection of 
explosive lung and bowel sounds by means of fractal 
dimension”, Signal Processing Letters IEEE  2003; 
10: 311-314.